|
1
|
Margolis DJA, Chatterjee A, deSouza NM, Fedorov A, Fennessy FM, Maier SE, Obuchowski N, Punwani S, Purysko A, Rakow-Penner R, Shukla-Dave A, Tempany CM, Boss M, Malyarenko D. Quantitative Prostate MRI, From the AJR Special Series on Quantitative Imaging. AJR Am J Roentgenol 2024:10.2214/AJR.24.31715. [PMID: 39356481 PMCID: PMC11961719 DOI: 10.2214/ajr.24.31715] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/03/2024]
Abstract
Prostate MRI has traditionally relied on qualitative interpretation. However, quantitative components hold the potential to markedly improve performance. The ADC from DWI is probably the most widely recognized quantitative MRI biomarker and has shown strong discriminatory value for clinically significant prostate cancer (csPCa) as well as for recurrent cancer after treatment. Advanced diffusion techniques, including intravoxel incoherent motion, diffusion kurtosis, diffusion tensor imaging, and specific implementations such as restriction spectrum imaging, purport even better discrimination, but are more technically challenging. The inherent T1 and T2 of tissue also provide diagnostic value, with more advanced techniques deriving luminal water imaging and hybrid-multidimensional MRI. Dynamic contrast-enhanced imaging, primarily using a modified Tofts model, also shows independent discriminatory value. Finally, quantitative size and shape features can be combined with the aforementioned techniques and be further refined using radiomics, texture analysis, and artificial intelligence. Which technique will ultimately find widespread clinical use will depend on validation across a myriad of platforms use-cases.
Collapse
Affiliation(s)
| | | | - Nandita M deSouza
- The Institute of Cancer Research and The Royal Marsden NHS Foundation Trust, London, UK
| | - Andriy Fedorov
- Department of Radiology, Brigham and Women's Hospital, Boston, MA
| | - Fiona M Fennessy
- Department of Radiology, Brigham and Women's Hospital, Boston, MA
| | - Stephan E Maier
- Department of Radiology, Brigham and Women's Hospital, Boston, MA
| | | | - Shonit Punwani
- Centre for Medical Imaging, University College London, London, UK
| | - Andrei Purysko
- Department of Radiology, Cleveland Clinic, Cleveland, OH
| | | | - Amita Shukla-Dave
- Departments of Medical Physics and Radiology, Memorial Sloan Kettering Cancer Center, New York, NY
| | - Clare M Tempany
- Department of Radiology, Brigham and Women's Hospital, Boston, MA
| | | | | |
Collapse
|
|
2
|
Subashi E, LoCastro E, Burleson S, Apte A, Zelefsky M, Tyagi N. Feasibility of quantitative relaxometry for prostate target localization and response assessment in magnetic resonance-guided online adaptive stereotactic body radiotherapy. Phys Imaging Radiat Oncol 2024; 32:100678. [PMID: 39717186 PMCID: PMC11665667 DOI: 10.1016/j.phro.2024.100678] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/28/2024] [Revised: 11/12/2024] [Accepted: 11/14/2024] [Indexed: 12/25/2024] Open
Abstract
Purpose Multiparametric magnetic resonance imaging (MRI) is known to provide predictors for malignancy and treatment outcome. The inclusion of these datasets in workflows for online adaptive planning remains under investigation. We demonstrate the feasibility of longitudinal relaxometry in online MR-guided adaptive stereotactic body radiotherapy (SBRT) to the prostate and dominant intra-prostatic lesion (DIL). Methods Fifty patients with intermediate-risk prostate cancer were included in the study. The clinical target volume (CTV) was defined as the prostate gland plus 1 cm of seminal vesicles. The gross tumor volume (GTV) was defined as the DIL identified on multiparametric MRI. Online adaptive radiotherapy was delivered in a 1.5 T MR-Linac using a prescription of 800 cGy/900 cGy × 5 fractions to the CTV + 3 mm/GTV + 2 mm. Relaxometry and diffusion-weighted imaging were implemented using clinically available sequences. Test-retest measurements were performed in eight patients, at each treatment fraction. Bias and uncertainty in relaxometry measurements were also assessed using a reference phantom. Results The bias in longitudinal/transverse relaxation times was negligible while uncertainty was within 3 %. Test-retest measurements demonstrate that bias/uncertainty in patient T1 and T2 were comparable to bias/uncertainty estimated in the phantom. Mean T1 and T2 relaxation were significantly different between the prostate and DIL. The correlation between T1, T2, and diffusion was significant in the DIL, but not in the prostate. During treatment, mean T1 in the DIL approaches mean T1 in the prostate. Conclusions Longitudinal relaxometry for online MR-guided adaptive SBRT is feasible in a high-field MR-Linac and may provide complementary information for target delineation and response assessment.
Collapse
Affiliation(s)
- Ergys Subashi
- Department of Radiation Physics, University of Texas MD Anderson Cancer Center, Houston, TX, United States
| | - Eve LoCastro
- Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, NY, United States
| | - Sarah Burleson
- Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, NY, United States
| | - Aditya Apte
- Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, NY, United States
| | - Michael Zelefsky
- Department of Radiation Oncology, New York University School of Medicine, New York, NY, United States
| | - Neelam Tyagi
- Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, NY, United States
| |
Collapse
|
|
3
|
Vaidya A, Shankardass A, Buford M, Hall R, Qiao P, Wang H, Gao S, Huang J, Tweedle MF, Lu ZR. MR Molecular Imaging of Extradomain-B Fibronectin for Assessing Progression and Therapy Resistance of Prostate Cancer. CHEMICAL & BIOMEDICAL IMAGING 2024; 2:560-568. [PMID: 39211789 PMCID: PMC11351422 DOI: 10.1021/cbmi.4c00002] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 01/05/2024] [Revised: 05/29/2024] [Accepted: 05/31/2024] [Indexed: 09/04/2024]
Abstract
Accurate assessment and characterization of the progression and therapy response of prostate cancer are essential for precision healthcare of patients diagnosed with the disease. MRI is a clinical imaging modality routinely used for diagnostic imaging and treatment planning of prostate cancer. Extradomain B fibronectin (EDB-FN) is an oncofetal subtype of fibronectin highly expressed in the extracellular matrix of aggressive cancers, including prostate cancer. It is a promising molecular target for the detection and risk-stratification of prostate cancer with high-resolution MR molecular imaging (MRMI). In this study, we investigated the effectiveness of MRMI with an EDB-FN specific contrast agent MT218 for assessing the progression and therapy resistance of prostate cancer. Low grade LNCaP prostate cancer cells became an invasive phenotype LNCaP-CXCR2 with elevated EDB-FN expression after acquisition of the C-X-C motif chemokine receptor 2 (CXCR2). MT218-MRMI showed brighter signal enhancement in LNCaP-CXCR2 tumor xenografts with a ∼2-fold contrast-to-noise (CNR) increase than in LNCaP tumors in mice. Enzalutamide-resistant C4-2-DR prostate cancer cells were more invasive, with higher EDB-FN expression than parental C4-2 cells. Brighter signal enhancement with a ∼2-fold CNR increase was observed in the C4-2-DR xenografts compared to that of C4-2 tumors in mice with MT218-MRMI. Interestingly, when invasive PC3 prostate cancer cells developed resistance to paclitaxel, the drug-resistant PC3-DR cells became less invasive with reduced EDB-FN expression than the parental PC3 cells. MT218-MRMI detected reduced brightness in the PC3-DR xenografts with more than 2-fold reduction of CNR compared to PC3 tumors in mice. The signal enhancement in all tumors was supported by the immunohistochemical staining of EDB-FN with the G4 monoclonal antibody. The results indicate that MRMI of EDB-FN with MT218 has promise for detection, risk stratification, and monitoring the progression and therapy response of invasive prostate cancer.
Collapse
Affiliation(s)
- Amita Vaidya
- Department
of Biomedical Engineering, Case Western
Reserve University, Cleveland, Ohio 44106, United States
| | - Aman Shankardass
- Department
of Biomedical Engineering, Case Western
Reserve University, Cleveland, Ohio 44106, United States
| | - Megan Buford
- Department
of Biomedical Engineering, Case Western
Reserve University, Cleveland, Ohio 44106, United States
| | - Ryan Hall
- Department
of Biomedical Engineering, Case Western
Reserve University, Cleveland, Ohio 44106, United States
| | - Peter Qiao
- Department
of Biomedical Engineering, Case Western
Reserve University, Cleveland, Ohio 44106, United States
| | - Helen Wang
- Department
of Biomedical Engineering, Case Western
Reserve University, Cleveland, Ohio 44106, United States
| | - Songqi Gao
- Molecular
Theranostics LLC, Cleveland, Ohio 44103, United States
| | - Jiaoti Huang
- Department
of Pathology, Duke University, Durham, North Carolina 27705, United States
| | - Michael F. Tweedle
- Wright
Center of Innovation, Department of Radiology, The Ohio State University, Columbus, Ohio 43212, United States
| | - Zheng-Rong Lu
- Department
of Biomedical Engineering, Case Western
Reserve University, Cleveland, Ohio 44106, United States
- Case
Comprehensive Cancer Center, Case Western
Reserve University, Cleveland, Ohio 44106, United States
| |
Collapse
|
|
4
|
Mukherjee S, Papadopoulos D, Chari N, Ellis D, Charitopoulos K, Charitopoulos I, Bishara S. High-grade prostate cancer demonstrates preferential growth in the cranio-caudal axis and provides discrimination of disease grade in an MRI parametric model. Br J Radiol 2024; 97:574-582. [PMID: 38276882 PMCID: PMC11027337 DOI: 10.1093/bjr/tqad066] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/12/2023] [Revised: 10/06/2023] [Accepted: 10/16/2023] [Indexed: 01/27/2024] Open
Abstract
OBJECTIVES To determine if multiparametric MRI prostate cancer (PC) lesion dimensions in different axes could distinguish between PC, grade group (GG) >2, and GG >3 on targeted transperineal biopsy and create and validate a predictive model on a separate cohort. METHODS The maximum transverse, anterio-posterior, and cranio-caudal lesion dimensions were assessed against the presence of any cancer, GG >2, and GG >3 on biopsy by binary logistic regression. The optimum multivariate models were evaluated on a separate cohort. RESULTS One hundred and ninety-three lesions from 148 patients were evaluated. Increased lesion volume, Prostate Specific Antigen (PSA), Prostate Imaging Reporting and Data System score, and decreased Apparent Diffusion Coefficient (ADC) were associated with increased GG (P < .001). The ratio of cranio-caudal to anterior-posterior lesion dimension increased from 1.20 (95% CI, 1.14-1.25) for GG ≤ 3 to 1.43 (95% CI, 1.28-1.57) for GG > 3 (P = .0022). The cranio-caudal dimension of the lesion was the strongest predictor of GG >3 (P = .000, area under the receiver operator characteristic curve [AUC] = 0.81). The best multivariate models had an AUC of 0.84 for cancer, 0.88 for GG > 2, and 0.89 for GG > 3. These models were evaluated on a separate cohort of 40 patients with 61 lesions. They demonstrated an AUC, sensitivity, and specificity of 0.82, 82.3%, and 55.5%, respectively, for the detection of cancer. For GG > 2, the models achieved an AUC of 0.84, sensitivity of 91.7%, and specificity of 69.4%. Additionally, for GG > 3, the models showed an AUC of 0.92, sensitivity of 88.9%, and specificity of 98.1%. CONCLUSIONS Cranio-caudal lesion dimension when used in conjunction with other parameters can create a model superior to the Prostate Imaging Reporting and Data Systems score in predicting cancer. ADVANCES IN KNOWLEDGE Higher-grade PC has a propensity to grow in the cranio-caudal direction, and this could be factored into MRI-based predictive models of prostate biopsy grade.
Collapse
Affiliation(s)
- Subhabrata Mukherjee
- Department of Urology, West Middlesex Hospital, Chelsea and Westminster NHS Trust, Twickenham Road, London, TW7 6AF, United Kingdom
| | - Dimitrios Papadopoulos
- Department of Urology, West Middlesex Hospital, Chelsea and Westminster NHS Trust, Twickenham Road, London, TW7 6AF, United Kingdom
| | - Natasha Chari
- Department of Urology, West Middlesex Hospital, Chelsea and Westminster NHS Trust, Twickenham Road, London, TW7 6AF, United Kingdom
| | - David Ellis
- Department of Urology, West Middlesex Hospital, Chelsea and Westminster NHS Trust, Twickenham Road, London, TW7 6AF, United Kingdom
| | - Konstantinos Charitopoulos
- Department of Urology, West Middlesex Hospital, Chelsea and Westminster NHS Trust, Twickenham Road, London, TW7 6AF, United Kingdom
| | - Ivo Charitopoulos
- Department of Urology, West Middlesex Hospital, Chelsea and Westminster NHS Trust, Twickenham Road, London, TW7 6AF, United Kingdom
| | - Samuel Bishara
- Department of Urology, West Middlesex Hospital, Chelsea and Westminster NHS Trust, Twickenham Road, London, TW7 6AF, United Kingdom
| |
Collapse
|
|
5
|
Chen X, Liu X, Wu Y, Wang Z, Wang SH. Research related to the diagnosis of prostate cancer based on machine learning medical images: A review. Int J Med Inform 2024; 181:105279. [PMID: 37977054 DOI: 10.1016/j.ijmedinf.2023.105279] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/21/2023] [Revised: 09/06/2023] [Accepted: 10/29/2023] [Indexed: 11/19/2023]
Abstract
BACKGROUND Prostate cancer is currently the second most prevalent cancer among men. Accurate diagnosis of prostate cancer can provide effective treatment for patients and greatly reduce mortality. The current medical imaging tools for screening prostate cancer are mainly MRI, CT and ultrasound. In the past 20 years, these medical imaging methods have made great progress with machine learning, especially the rise of deep learning has led to a wider application of artificial intelligence in the use of image-assisted diagnosis of prostate cancer. METHOD This review collected medical image processing methods, prostate and prostate cancer on MR images, CT images, and ultrasound images through search engines such as web of science, PubMed, and Google Scholar, including image pre-processing methods, segmentation of prostate gland on medical images, registration between prostate gland on different modal images, detection of prostate cancer lesions on the prostate. CONCLUSION Through these collated papers, it is found that the current research on the diagnosis and staging of prostate cancer using machine learning and deep learning is in its infancy, and most of the existing studies are on the diagnosis of prostate cancer and classification of lesions, and the accuracy is low, with the best results having an accuracy of less than 0.95. There are fewer studies on staging. The research is mainly focused on MR images and much less on CT images, ultrasound images. DISCUSSION Machine learning and deep learning combined with medical imaging have a broad application prospect for the diagnosis and staging of prostate cancer, but the research in this area still has more room for development.
Collapse
Affiliation(s)
- Xinyi Chen
- School of Electronic and Electrical Engineering, Shanghai University of Engineering Science, Shanghai 201620, China.
| | - Xiang Liu
- School of Electronic and Electrical Engineering, Shanghai University of Engineering Science, Shanghai 201620, China.
| | - Yuke Wu
- School of Electronic and Electrical Engineering, Shanghai University of Engineering Science, Shanghai 201620, China.
| | - Zhenglei Wang
- Department of Medical Imaging, Shanghai Electric Power Hospital, Shanghai 201620, China.
| | - Shuo Hong Wang
- Department of Molecular and Cellular Biology and Center for Brain Science, Harvard University, Cambridge, MA 02138, USA.
| |
Collapse
|
|
6
|
Guljaš S, Dupan Krivdić Z, Drežnjak Madunić M, Šambić Penc M, Pavlović O, Krajina V, Pavoković D, Šmit Takač P, Štefančić M, Salha T. Dynamic Contrast-Enhanced Study in the mpMRI of the Prostate-Unnecessary or Underutilised? A Narrative Review. Diagnostics (Basel) 2023; 13:3488. [PMID: 37998624 PMCID: PMC10670922 DOI: 10.3390/diagnostics13223488] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/26/2023] [Revised: 10/30/2023] [Accepted: 11/16/2023] [Indexed: 11/25/2023] Open
Abstract
The aim of this review is to summarise recent scientific literature regarding the clinical use of DCE-MRI as a component of multiparametric resonance imaging of the prostate. This review presents the principles of DCE-MRI acquisition and analysis, the current role of DCE-MRI in clinical practice with special regard to its role in presently available categorisation systems, and an overview of the advantages and disadvantages of DCE-MRI described in the current literature. DCE-MRI is an important functional sequence that requires intravenous administration of a gadolinium-based contrast agent and gives information regarding the vascularity and capillary permeability of the lesion. Although numerous studies have confirmed that DCE-MRI has great potential in the diagnosis and monitoring of prostate cancer, its role is still inadequate in the PI-RADS categorisation. Moreover, there have been numerous scientific discussions about abandoning the intravenous application of gadolinium-based contrast as a routine part of MRI examination of the prostate. In this review, we summarised the recent literature on the advantages and disadvantages of DCE-MRI, focusing on an overview of currently available data on bpMRI and mpMRI, as well as on studies providing information on the potential better usability of DCE-MRI in improving the sensitivity and specificity of mpMRI examinations of the prostate.
Collapse
Affiliation(s)
- Silva Guljaš
- Clinical Department of Radiology, University Hospital Centre, 31000 Osijek, Croatia; (S.G.); (Z.D.K.)
- Faculty of Medicine, Josip Juraj Strossmayer University of Osijek, 31000 Osijek, Croatia; (M.D.M.); (M.Š.P.); (O.P.); (V.K.); (D.P.)
| | - Zdravka Dupan Krivdić
- Clinical Department of Radiology, University Hospital Centre, 31000 Osijek, Croatia; (S.G.); (Z.D.K.)
- Faculty of Medicine, Josip Juraj Strossmayer University of Osijek, 31000 Osijek, Croatia; (M.D.M.); (M.Š.P.); (O.P.); (V.K.); (D.P.)
| | - Maja Drežnjak Madunić
- Faculty of Medicine, Josip Juraj Strossmayer University of Osijek, 31000 Osijek, Croatia; (M.D.M.); (M.Š.P.); (O.P.); (V.K.); (D.P.)
- Department of Oncology, University Hospital Centre, 31000 Osijek, Croatia
| | - Mirela Šambić Penc
- Faculty of Medicine, Josip Juraj Strossmayer University of Osijek, 31000 Osijek, Croatia; (M.D.M.); (M.Š.P.); (O.P.); (V.K.); (D.P.)
- Department of Oncology, University Hospital Centre, 31000 Osijek, Croatia
| | - Oliver Pavlović
- Faculty of Medicine, Josip Juraj Strossmayer University of Osijek, 31000 Osijek, Croatia; (M.D.M.); (M.Š.P.); (O.P.); (V.K.); (D.P.)
- Department of Urology, University Hospital Centre, 31000 Osijek, Croatia
| | - Vinko Krajina
- Faculty of Medicine, Josip Juraj Strossmayer University of Osijek, 31000 Osijek, Croatia; (M.D.M.); (M.Š.P.); (O.P.); (V.K.); (D.P.)
- Department of Urology, University Hospital Centre, 31000 Osijek, Croatia
| | - Deni Pavoković
- Faculty of Medicine, Josip Juraj Strossmayer University of Osijek, 31000 Osijek, Croatia; (M.D.M.); (M.Š.P.); (O.P.); (V.K.); (D.P.)
- Department of Urology, University Hospital Centre, 31000 Osijek, Croatia
| | - Petra Šmit Takač
- Clinical Department of Surgery, Osijek University Hospital Centre, 31000 Osijek, Croatia;
| | - Marin Štefančić
- Department of Radiology, National Memorial Hospital Vukovar, 32000 Vukovar, Croatia;
| | - Tamer Salha
- Faculty of Medicine, Josip Juraj Strossmayer University of Osijek, 31000 Osijek, Croatia; (M.D.M.); (M.Š.P.); (O.P.); (V.K.); (D.P.)
- Department of Teleradiology and Artificial Intelligence, Health Centre Osijek-Baranja County, 31000 Osijek, Croatia
- Faculty of Dental Medicine and Health, Josip Juraj Strossmayer University of Osijek, 31000 Osijek, Croatia
| |
Collapse
|
|
7
|
Lee J, Yoon SK, Cho JH, Kwon HJ, Kim DW, Lee JW. Variability of Transrectal Shear Wave Elastography in a Phantom Model. JOURNAL OF THE KOREAN SOCIETY OF RADIOLOGY 2023; 84:1110-1122. [PMID: 37869125 PMCID: PMC10585080 DOI: 10.3348/jksr.2023.0051] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 05/03/2023] [Revised: 06/18/2023] [Accepted: 06/30/2023] [Indexed: 10/24/2023]
Abstract
Purpose This study aimed to assess the variability of transrectal shear wave elastography (SWE) using a designed phantom. Materials and Methods In a phantom, the SWE values were examined by two radiologists using agarose and emulsion silicone of different sizes (1, 2, and 3 cm) and shapes (round, cubic) at three depths (1, 2, and 3 cm), two region of interest (ROI) and locations (central, peripheral) using two ultrasound machines (A, B from different vendors). Variability was evaluated using the coefficient of variation (CV). Results The CVs decreased with increasing phantom size. Significant changes in SWE values included; agarose phantom at 3 cm depth (p < 0.001; machine A), 1 cm depth (p = 0.01; machine B), emulsion silicone at 2 cm depth (p = 0.047, p = 0.020; both machines). The CVs increased with increasing depth. Significant changes in SWE values included; 1 cm agarose (p = 0.037, p = 0.021; both machines) and 2 cm agarose phantom (p = 0.047; machine A). Significant differences in SWE values were observed between the shapes for emulsion silicone phantom (p = 0.032; machines A) and between ROI locations on machine B (p ≤ 0.001). The SWE values differed significantly between the two machines (p < 0.05). The intra-/inter-operator agreements were excellent (intraclass correlation coefficient > 0.9). Conclusion The phantom size, depth, and different machines affected the variability of transrectal SWE.
Collapse
|
|
8
|
Jiang M, Yuan B, Kou W, Yan W, Marshall H, Yang Q, Syer T, Punwani S, Emberton M, Barratt DC, Cho CCM, Hu Y, Chiu B. Prostate cancer segmentation from MRI by a multistream fusion encoder. Med Phys 2023; 50:5489-5504. [PMID: 36938883 DOI: 10.1002/mp.16374] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/08/2022] [Revised: 02/15/2023] [Accepted: 03/03/2023] [Indexed: 03/21/2023] Open
Abstract
BACKGROUND Targeted prostate biopsy guided by multiparametric magnetic resonance imaging (mpMRI) detects more clinically significant lesions than conventional systemic biopsy. Lesion segmentation is required for planning MRI-targeted biopsies. The requirement for integrating image features available in T2-weighted and diffusion-weighted images poses a challenge in prostate lesion segmentation from mpMRI. PURPOSE A flexible and efficient multistream fusion encoder is proposed in this work to facilitate the multiscale fusion of features from multiple imaging streams. A patch-based loss function is introduced to improve the accuracy in segmenting small lesions. METHODS The proposed multistream encoder fuses features extracted in the three imaging streams at each layer of the network, thereby allowing improved feature maps to propagate downstream and benefit segmentation performance. The fusion is achieved through a spatial attention map generated by optimally weighting the contribution of the convolution outputs from each stream. This design provides flexibility for the network to highlight image modalities according to their relative influence on the segmentation performance. The encoder also performs multiscale integration by highlighting the input feature maps (low-level features) with the spatial attention maps generated from convolution outputs (high-level features). The Dice similarity coefficient (DSC), serving as a cost function, is less sensitive to incorrect segmentation for small lesions. We address this issue by introducing a patch-based loss function that provides an average of the DSCs obtained from local image patches. This local average DSC is equally sensitive to large and small lesions, as the patch-based DSCs associated with small and large lesions have equal weights in this average DSC. RESULTS The framework was evaluated in 931 sets of images acquired in several clinical studies at two centers in Hong Kong and the United Kingdom. In particular, the training, validation, and test sets contain 615, 144, and 172 sets of images, respectively. The proposed framework outperformed single-stream networks and three recently proposed multistream networks, attaining F1 scores of 82.2 and 87.6% in the lesion and patient levels, respectively. The average inference time for an axial image was 11.8 ms. CONCLUSION The accuracy and efficiency afforded by the proposed framework would accelerate the MRI interpretation workflow of MRI-targeted biopsy and focal therapies.
Collapse
Affiliation(s)
- Mingjie Jiang
- Department of Electrical Engineering, City University of Hong Kong, Hong Kong SAR, China
| | - Baohua Yuan
- Department of Electrical Engineering, City University of Hong Kong, Hong Kong SAR, China
- Aliyun School of Big Data, Changzhou University, Changzhou, China
| | - Weixuan Kou
- Department of Electrical Engineering, City University of Hong Kong, Hong Kong SAR, China
| | - Wen Yan
- Department of Electrical Engineering, City University of Hong Kong, Hong Kong SAR, China
- Centre for Medical Image Computing, Wellcome/EPSRC Centre for Interventional & Surgical Sciences, Department of Medical Physics & Biomedical Engineering, University College London, London, UK
| | - Harry Marshall
- Schulich School of Medicine & Dentistry, Western University, Ontario, Canada
| | - Qianye Yang
- Centre for Medical Image Computing, Wellcome/EPSRC Centre for Interventional & Surgical Sciences, Department of Medical Physics & Biomedical Engineering, University College London, London, UK
| | - Tom Syer
- Centre for Medical Imaging, University College London, London, UK
| | - Shonit Punwani
- Centre for Medical Imaging, University College London, London, UK
| | - Mark Emberton
- Division of Surgery & Interventional Science, University College London, London, UK
| | - Dean C Barratt
- Centre for Medical Image Computing, Wellcome/EPSRC Centre for Interventional & Surgical Sciences, Department of Medical Physics & Biomedical Engineering, University College London, London, UK
| | - Carmen C M Cho
- Prince of Wales Hospital and Department of Imaging and Intervention Radiology, Chinese University of Hong Kong, Hong Kong SAR, China
| | - Yipeng Hu
- Centre for Medical Image Computing, Wellcome/EPSRC Centre for Interventional & Surgical Sciences, Department of Medical Physics & Biomedical Engineering, University College London, London, UK
| | - Bernard Chiu
- Department of Electrical Engineering, City University of Hong Kong, Hong Kong SAR, China
| |
Collapse
|
|
9
|
Ageeli W, Soha N, Zhang X, Szewcyk-Bieda M, Wilson J, Li C, Nabi G. Preoperative imaging accuracy in size determination of prostate cancer in men undergoing radical prostatectomy for clinically localised disease. Insights Imaging 2023; 14:105. [PMID: 37286770 DOI: 10.1186/s13244-023-01450-5] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/06/2022] [Accepted: 03/06/2023] [Indexed: 06/09/2023] Open
Abstract
OBJECTIVES To compare the accuracy of pre-surgical prostate size measurements using mpMRI and USWE with imaging-based 3D-printed patient-specific whole-mount moulds facilitated histopathology, and to assess whether size assessment varies between clinically significant and non-significant cancerous lesions including their locations in different zones of the prostate. METHODS The study population included 202 men with clinically localised prostate cancer opting for radical surgery derived from two prospective studies. Protocol-based imaging data was used for measurement of size of prostate cancer in clinically localised disease using MRI (N = 106; USWE (N = 96). Forty-eight men overlapped between two studies and formed the validation cohort. The primary outcome of this study was to assess the accuracy of pre-surgical prostate cancerous size measurements using mpMRI and USWE with imaging-based 3D-printed patient-specific whole-mount moulds facilitated histopathology as a reference standard. Independent-samples T-tests were used for the continuous variables and a nonparametric Mann-Whitney U test for independent samples was applied to examine the distribution and median differences between mpMRI and USWE groups. RESULTS A significant number of men had underestimation of prostate cancer using both mpMRI (82.1%; 87/106) and USWE (64.6%; 62/96). On average, tumour size was underestimated by a median size of 7 mm in mpMRI, and 1 mm in USWE. There were 327 cancerous lesions (153 with mpMRI and 174 for USWE). mpMRI and USWE underestimated the majority of cancerous lesions (108/153; 70.6%) and (88/174; 50.6%), respectively. Validation cohort data confirmed these findings MRI had a nearly 20% higher underestimation rate than USWE (χ2 (1, N = 327) = 13.580, p = 0.001); especially in the mid and apical level of the gland. Clinically non-significant cancers were underestimated in significantly higher numbers in comparison to clinically significant cancers. CONCLUSIONS Size measurement of prostate cancers on preoperative imaging utilising maximum linear extent technique, underestimated the extent of cancer. Further research is needed to confirm our observations using different sequences, methods and approaches for cancer size measurement.
Collapse
Affiliation(s)
- Wael Ageeli
- Division of Imaging Sciences and Technology, School of Medicine, University of Dundee, Ninewells Hospital, Dundee, DD1 9SY, UK
- Diagnostic Radiology Department, College of Applied Medical Sciences, Jazan University, Al Maarefah Rd, P.O. Box 114, Jazan, 45142, Saudi Arabia
| | - Nabi Soha
- Division of Imaging Sciences and Technology, School of Medicine, University of Dundee, Ninewells Hospital, Dundee, DD1 9SY, UK
| | - Xinyu Zhang
- Division of Population Health and Genomics, School of Medicine, University of Dundee, Dundee, DD1 9SY, UK
| | | | - Jennifer Wilson
- Department of Pathology, Ninewells Hospital, Dundee, DD1 9SY, UK
| | - Chunhui Li
- School of Science and Engineering, University of Dundee, Dundee, DD1 4HN, UK
| | - Ghulam Nabi
- Division of Imaging Sciences and Technology, School of Medicine, University of Dundee, Ninewells Hospital, Dundee, DD1 9SY, UK.
| |
Collapse
|
|
10
|
Knull E, Park CKS, Bax J, Tessier D, Fenster A. Toward mechatronic MRI-guided focal laser ablation of the prostate: Robust registration for improved needle delivery. Med Phys 2023; 50:1259-1273. [PMID: 36583505 DOI: 10.1002/mp.16190] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/26/2022] [Revised: 12/04/2022] [Accepted: 12/11/2022] [Indexed: 12/31/2022] Open
Abstract
BACKGROUND Multiparametric MRI (mpMRI) is an effective tool for detecting and staging prostate cancer (PCa), guiding interventional therapy, and monitoring PCa treatment outcomes. MRI-guided focal laser ablation (FLA) therapy is an alternative, minimally invasive treatment method to conventional therapies, which has been demonstrated to control low-grade, localized PCa while preserving patient quality of life. The therapeutic success of FLA depends on the accurate placement of needles for adequate delivery of ablative energy to the target lesion. We previously developed an MR-compatible mechatronic system for prostate FLA needle guidance and validated its performance in open-air and clinical 3T in-bore experiments using virtual targets. PURPOSE To develop a robust MRI-to-mechatronic system registration method and evaluate its in-bore MR-guided needle delivery accuracy in tissue-mimicking prostate phantoms. METHODS The improved registration multifiducial assembly houses thirty-six aqueous gadolinium-filled spheres distributed over a 7.3 × 7.3 × 5.2 cm volume. MRI-guided needle guidance accuracy was quantified in agar-based tissue-mimicking prostate phantoms on trajectories (N = 44) to virtual targets covering the mechatronic system's range of motion. 3T gradient-echo recalled (GRE) MRI images were acquired after needle insertions to each target, and the air-filled needle tracks were segmented. Needle guidance error was measured as the shortest Euclidean distance between the target point and the segmented needle trajectory, and angular error was measured as the angle between the targeted trajectory and the segmented needle trajectory. These measurements were made using both the previously designed four-sphere registration fiducial assembly on trajectories (N = 7) and compared with the improved multifiducial assembly using a Mann-Whitney U test. RESULTS The median needle guidance error of the system using the improved registration fiducial assembly at a depth of 10 cm was 1.02 mm with an interquartile range (IQR) of 0.42-2.94 mm. The upper limit of the one-sided 95% prediction interval of needle guidance error was 4.13 mm. The median (IQR) angular error was 0.0097 rad (0.0057-0.015 rad) with a one-sided 95% prediction interval upper limit of 0.022 rad. The median (IQR) positioning error using the previous four-sphere registration fiducial assembly was 1.87 mm (1.77-2.14 mm). This was found to be significantly different (p = 0.0012) from the median (IQR) positioning error of 0.28 mm (0.14-0.95 mm) using the new registration fiducial assembly on the same trajectories. No significant difference was detected between the medians of the angular errors (p = 0.26). CONCLUSION This is the first study presenting an improved registration method and validation in tissue-mimicking phantoms of our remotely actuated MR-compatible mechatronic system for delivery of prostate FLA needles. Accounting for the effects of needle deflection, the system was demonstrated to be capable of needle delivery with an error of 4.13 mm or less in 95% of cases under ideal conditions, which is a statistically significant improvement over the previous method. The system will next be validated in a clinical setting.
Collapse
Affiliation(s)
- Eric Knull
- Faculty of Engineering, School of Biomedical Engineering, Western University, London, Ontario, Canada
- Robarts Research Institute, Western University, London, Ontario, Canada
| | - Claire Keun Sun Park
- Robarts Research Institute, Western University, London, Ontario, Canada
- Department of Medical Biophysics, Schulich School of Medicine and Dentistry, Western University, London, Ontario, Canada
| | - Jeffrey Bax
- Robarts Research Institute, Western University, London, Ontario, Canada
| | - David Tessier
- Robarts Research Institute, Western University, London, Ontario, Canada
| | - Aaron Fenster
- Faculty of Engineering, School of Biomedical Engineering, Western University, London, Ontario, Canada
- Robarts Research Institute, Western University, London, Ontario, Canada
- Department of Medical Biophysics, Schulich School of Medicine and Dentistry, Western University, London, Ontario, Canada
| |
Collapse
|
|
11
|
Bergen RV, Ryner L, Essig M. Comparison of DCE-MRI parametric mapping using MP2RAGE and variable flip angle T1 mapping. Magn Reson Imaging 2023; 95:103-109. [PMID: 32646633 DOI: 10.1016/j.mri.2020.01.001] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/11/2019] [Revised: 12/23/2019] [Accepted: 01/03/2020] [Indexed: 12/15/2022]
Abstract
Quantitative dynamic contrast enhanced magnetic resonance imaging (DCE-MRI) measures the rate of transfer of contrast agent from the vascular space to the tissue space by fitting signal-time data to pharmacokinetic models. However, these models are very sensitive to errors in T1 mapping. Accurate T1 mapping is necessary for high quality quantitative DCE-MRI studies. This study compares magnetization prepared rapid (two) gradient echo sequence (MP2RAGE) T1-mapping accuracy to the conventional variable flip angle (VFA) approach, and also determines the effect of the new T1-mapping method on the Ktrans parameter. VFA and MP2RAGE T1 values were compared to the gold standard inverse recovery (IR) method in phantom over manually drawn ROIs. In vivo, ROIs were manually drawn over prostate and prostatic lesions. Average T1 values over ROIs were compared and Ktrans maps for each method were calculated via the extended Tofts model. VFA-T1 maps overestimated T1 values by up to 50% compared to gold standard IR T1 values in phantom. MP2RAGE differed by up to 9%. MP2RAGE-T1 and Ktrans values were significantly different from VFA values over prostatic lesions (p < 0.05). Ktrans was consistently underestimated using VFA compared to MP2RAGE (p < 0.05). MP2RAGE T1 maps are shown to be more accurate, leading to more reliable pharmacokinetic modeling. This can potentially lead to better lesion characterization and improve clinical outcomes.
Collapse
Affiliation(s)
- Robert V Bergen
- Department of Physics & Astronomy, University of Manitoba, Canada; Medical Physics, CancerCare Manitoba, Canada
| | - Lawrence Ryner
- Department of Physics & Astronomy, University of Manitoba, Canada; Medical Physics, CancerCare Manitoba, Canada.
| | - Marco Essig
- Department of Radiology, University of Manitoba, Canada
| |
Collapse
|
|
12
|
Mavrogiorgou A, Kiourtis A, Kleftakis S, Mavrogiorgos K, Zafeiropoulos N, Kyriazis D. A Catalogue of Machine Learning Algorithms for Healthcare Risk Predictions. SENSORS (BASEL, SWITZERLAND) 2022; 22:8615. [PMID: 36433212 PMCID: PMC9695983 DOI: 10.3390/s22228615] [Citation(s) in RCA: 12] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 10/01/2022] [Revised: 11/04/2022] [Accepted: 11/04/2022] [Indexed: 05/27/2023]
Abstract
Extracting useful knowledge from proper data analysis is a very challenging task for efficient and timely decision-making. To achieve this, there exist a plethora of machine learning (ML) algorithms, while, especially in healthcare, this complexity increases due to the domain's requirements for analytics-based risk predictions. This manuscript proposes a data analysis mechanism experimented in diverse healthcare scenarios, towards constructing a catalogue of the most efficient ML algorithms to be used depending on the healthcare scenario's requirements and datasets, for efficiently predicting the onset of a disease. To this context, seven (7) different ML algorithms (Naïve Bayes, K-Nearest Neighbors, Decision Tree, Logistic Regression, Random Forest, Neural Networks, Stochastic Gradient Descent) have been executed on top of diverse healthcare scenarios (stroke, COVID-19, diabetes, breast cancer, kidney disease, heart failure). Based on a variety of performance metrics (accuracy, recall, precision, F1-score, specificity, confusion matrix), it has been identified that a sub-set of ML algorithms are more efficient for timely predictions under specific healthcare scenarios, and that is why the envisioned ML catalogue prioritizes the ML algorithms to be used, depending on the scenarios' nature and needed metrics. Further evaluation must be performed considering additional scenarios, involving state-of-the-art techniques (e.g., cloud deployment, federated ML) for improving the mechanism's efficiency.
Collapse
Affiliation(s)
- Argyro Mavrogiorgou
- Department of Digital Systems, University of Piraeus, 185 34 Piraeus, Greece
| | | | | | | | | | | |
Collapse
|
|
13
|
Numminen R, Montoya Perez I, Jambor I, Pahikkala T, Airola A. Quicksort leave-pair-out cross-validation for ROC curve analysis. Comput Stat 2022. [DOI: 10.1007/s00180-022-01288-3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/25/2022]
Abstract
AbstractReceiver Operating Characteristic (ROC) curve analysis and area under the ROC curve (AUC) are commonly used performance measures in diagnostic systems. In this work, we assume a setting, where a classifier is inferred from multivariate data to predict the diagnostic outcome for new cases. Cross-validation is a resampling method for estimating the prediction performance of a classifier on data not used for inferring it. Tournament leave-pair-out (TLPO) cross-validation has been shown to be better than other resampling methods at producing a ranking of data that can be used for estimating the ROC curves and areas under them. However, the time complexity of TLPOCV, $$O\left( n^2\right)$$
O
n
2
, means that it is impractical in many applications. In this article, a method called quicksort leave-pair-out cross-validation (QLPOCV) is presented in order to decrease the time complexity of obtaining a reliable ranking of data to $$O\left( n\log n\right)$$
O
n
log
n
. The proposed method is compared with existing ones in an experimental study, demonstrating that in terms of ROC curves and AUC values QLPOCV produces as accurate performance estimation as TLPOCV, outperforming both k-fold and leave-one-out cross-validation.
Collapse
|
|
14
|
Fernandes MC, Yildirim O, Woo S, Vargas HA, Hricak H. The role of MRI in prostate cancer: current and future directions. MAGMA (NEW YORK, N.Y.) 2022; 35:503-521. [PMID: 35294642 PMCID: PMC9378354 DOI: 10.1007/s10334-022-01006-6] [Citation(s) in RCA: 25] [Impact Index Per Article: 8.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 07/16/2021] [Revised: 01/16/2022] [Accepted: 03/03/2022] [Indexed: 06/14/2023]
Abstract
There has been an increasing role of magnetic resonance imaging (MRI) in the management of prostate cancer. MRI already plays an essential role in the detection and staging, with the introduction of functional MRI sequences. Recent advancements in radiomics and artificial intelligence are being tested to potentially improve detection, assessment of aggressiveness, and provide usefulness as a prognostic marker. MRI can improve pretreatment risk stratification and therefore selection of and follow-up of patients for active surveillance. MRI can also assist in guiding targeted biopsy, treatment planning and follow-up after treatment to assess local recurrence. MRI has gained importance in the evaluation of metastatic disease with emerging technology including whole-body MRI and integrated positron emission tomography/MRI, allowing for not only better detection but also quantification. The main goal of this article is to review the most recent advances on MRI in prostate cancer and provide insights into its potential clinical roles from the radiologist's perspective. In each of the sections, specific roles of MRI tailored to each clinical setting are discussed along with its strengths and weakness including already established material related to MRI and the introduction of recent advancements on MRI.
Collapse
Affiliation(s)
- Maria Clara Fernandes
- Department of Radiology, Memorial Sloan Kettering Cancer Center, 1275 York Ave, New York, NY, 10065, USA
| | - Onur Yildirim
- Department of Radiology, Memorial Sloan Kettering Cancer Center, 1275 York Ave, New York, NY, 10065, USA
| | - Sungmin Woo
- Department of Radiology, Memorial Sloan Kettering Cancer Center, 1275 York Ave, New York, NY, 10065, USA.
| | - Hebert Alberto Vargas
- Department of Radiology, Memorial Sloan Kettering Cancer Center, 1275 York Ave, New York, NY, 10065, USA
| | - Hedvig Hricak
- Department of Radiology, Memorial Sloan Kettering Cancer Center, 1275 York Ave, New York, NY, 10065, USA
| |
Collapse
|
|
15
|
Semi-Automatic Multiparametric MR Imaging Classification Using Novel Image Input Sequences and 3D Convolutional Neural Networks. ALGORITHMS 2022. [DOI: 10.3390/a15070248] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/17/2022]
Abstract
The role of multi-parametric magnetic resonance imaging (mp-MRI) is becoming increasingly important in the diagnosis of the clinical severity of prostate cancer (PCa). However, mp-MRI images usually contain several unaligned 3D sequences, such as DWI image sequences and T2-weighted image sequences, and there are many images among the entirety of 3D sequence images that do not contain cancerous tissue, which affects the accuracy of large-scale prostate cancer detection. Therefore, there is a great need for a method that uses accurate computer-aided detection of mp-MRI images and minimizes the influence of useless features. Our proposed PCa detection method is divided into three stages: (i) multimodal image alignment, (ii) automatic cropping of the sequence images to the entire prostate region, and, finally, (iii) combining multiple modal images of each patient into novel 3D sequences and using 3D convolutional neural networks to learn the newly composed 3D sequences with different modal alignments. We arrange the different modal methods to make the model fully learn the cancerous tissue features; then, we predict the clinical severity of PCa and generate a 3D cancer response map for the 3D sequence images from the last convolution layer of the network. The prediction results and 3D response map help to understand the features that the model focuses on during the process of 3D-CNN feature learning. We applied our method to Toho hospital prostate cancer patient data; the AUC (=0.85) results were significantly higher than those of other methods.
Collapse
|
|
16
|
Guljaš S, Benšić M, Krivdić Dupan Z, Pavlović O, Krajina V, Pavoković D, Šmit Takač P, Hranić M, Salha T. Dynamic Contrast Enhanced Study in Multiparametric Examination of the Prostate—Can We Make Better Use of It? Tomography 2022; 8:1509-1521. [PMID: 35736872 PMCID: PMC9231365 DOI: 10.3390/tomography8030124] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/28/2022] [Revised: 05/18/2022] [Accepted: 06/04/2022] [Indexed: 11/16/2022] Open
Abstract
We sought to investigate whether quantitative parameters from a dynamic contrast-enhanced study can be used to differentiate cancer from normal tissue and to determine a cut-off value of specific parameters that can predict malignancy more accurately, compared to the obturator internus muscle as a reference tissue. This retrospective study included 56 patients with biopsy proven prostate cancer (PCa) after multiparametric magnetic resonance imaging (mpMRI), with a total of 70 lesions; 39 were located in the peripheral zone, and 31 in the transition zone. The quantitative parameters for all patients were calculated in the detected lesion, morphologically normal prostate tissue and the obturator internus muscle. Increase in the Ktrans value was determined in lesion-to-muscle ratio by 3.974368, which is a cut-off value to differentiate between prostate cancer and normal prostate tissue, with specificity of 72.86% and sensitivity of 91.43%. We introduced a model to detect prostate cancer that combines Ktrans lesion-to-muscle ratio value and iAUC lesion-to-muscle ratio value, which is of higher accuracy compared to individual variables. Based on this model, we identified the optimal cut-off value with 100% sensitivity and 64.28% specificity. The use of quantitative DCE pharmacokinetic parameters compared to the obturator internus muscle as reference tissue leads to higher diagnostic accuracy for prostate cancer detection.
Collapse
Affiliation(s)
- Silva Guljaš
- Clinical Department of Radiology, University Hospital Centre, 31000 Osijek, Croatia; (Z.K.D.); (M.H.)
- Correspondence:
| | - Mirta Benšić
- Department of Mathematics, Josip Juraj Strossmayer University of Osijek, 31000 Osijek, Croatia;
| | - Zdravka Krivdić Dupan
- Clinical Department of Radiology, University Hospital Centre, 31000 Osijek, Croatia; (Z.K.D.); (M.H.)
- Department of Radiology, Faculty of Medicine, Josip Juraj Strossmayer University of Osijek, 31000 Osijek, Croatia;
| | - Oliver Pavlović
- Department of Urology, University Hospital Centre Osijek, 31000 Osijek, Croatia; (O.P.); (V.K.); (D.P.)
| | - Vinko Krajina
- Department of Urology, University Hospital Centre Osijek, 31000 Osijek, Croatia; (O.P.); (V.K.); (D.P.)
| | - Deni Pavoković
- Department of Urology, University Hospital Centre Osijek, 31000 Osijek, Croatia; (O.P.); (V.K.); (D.P.)
| | - Petra Šmit Takač
- Clinical Department of Surgery, Osijek University Hospital Centre, 31000 Osijek, Croatia;
| | - Matija Hranić
- Clinical Department of Radiology, University Hospital Centre, 31000 Osijek, Croatia; (Z.K.D.); (M.H.)
| | - Tamer Salha
- Department of Radiology, Faculty of Medicine, Josip Juraj Strossmayer University of Osijek, 31000 Osijek, Croatia;
- Department of Teleradiology and Artificial Intelligence, Health Centre Osijek-Baranja County, 31000 Osijek, Croatia
- Faculty of Dental Medicine and Health, Josip Juraj Strossmayer University of Osijek, 31000 Osijek, Croatia
| |
Collapse
|
|
17
|
Kubihal V, Kundra V, Lanka V, Sharma S, Das P, Nayyar R, Das CJ. Prospective evaluation of PI-RADS v2 and quantitative MRI for clinically significant prostate cancer detection in Indian men – East meets West. Arab J Urol 2022; 20:126-136. [PMID: 35935908 PMCID: PMC9354636 DOI: 10.1080/2090598x.2022.2072141] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/02/2022] Open
Affiliation(s)
- Vijay Kubihal
- Department of Radiodiagnosis and Interventional Radiology, Urology All India Institute of Medical Sciences, New Delhi, India
| | - Vikas Kundra
- Department of diagnostic radiology, MD Anderson Cancer Center, Houston, Texas, USA
| | - Vivek Lanka
- Department of Radiodiagnosis and Interventional Radiology, Urology All India Institute of Medical Sciences, New Delhi, India
| | - Sanjay Sharma
- Department of Radiodiagnosis and Interventional Radiology, Urology All India Institute of Medical Sciences, New Delhi, India
| | - Prasenjit Das
- Department of Radiodiagnosis and Interventional Radiology, Urology All India Institute of Medical Sciences, New Delhi, India
| | - Rishi Nayyar
- Department of Radiodiagnosis and Interventional Radiology, Urology All India Institute of Medical Sciences, New Delhi, India
| | - Chandan J Das
- Department of Radiodiagnosis and Interventional Radiology, Urology All India Institute of Medical Sciences, New Delhi, India
| |
Collapse
|
|
18
|
Musa IH, Afolabi LO, Zamit I, Musa TH, Musa HH, Tassang A, Akintunde TY, Li W. Artificial Intelligence and Machine Learning in Cancer Research: A Systematic and Thematic Analysis of the Top 100 Cited Articles Indexed in Scopus Database. Cancer Control 2022; 29:10732748221095946. [PMID: 35688650 PMCID: PMC9189515 DOI: 10.1177/10732748221095946] [Citation(s) in RCA: 8] [Impact Index Per Article: 2.7] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/03/2023] Open
Abstract
INTRODUCTION Cancer is a major public health problem and a global leading cause of death where the screening, diagnosis, prediction, survival estimation, and treatment of cancer and control measures are still a major challenge. The rise of Artificial Intelligence (AI) and Machine Learning (ML) techniques and their applications in various fields have brought immense value in providing insights into advancement in support of cancer control. METHODS A systematic and thematic analysis was performed on the Scopus database to identify the top 100 cited articles in cancer research. Data were analyzed using RStudio and VOSviewer.Var1.6.6. RESULTS The top 100 articles in AI and ML in cancer received a 33 920 citation score with a range of 108 to 5758 times. Doi Kunio from the USA was the most cited author with total number of citations (TNC = 663). Out of 43 contributed countries, 30% of the top 100 cited articles originated from the USA, and 10% originated from China. Among the 57 peer-reviewed journals, the "Expert Systems with Application" published 8% of the total articles. The results were presented in highlight technological advancement through AI and ML via the widespread use of Artificial Neural Network (ANNs), Deep Learning or machine learning techniques, Mammography-based Model, Convolutional Neural Networks (SC-CNN), and text mining techniques in the prediction, diagnosis, and prevention of various types of cancers towards cancer control. CONCLUSIONS This bibliometric study provides detailed overview of the most cited empirical evidence in AI and ML adoption in cancer research that could efficiently help in designing future research. The innovations guarantee greater speed by using AI and ML in the detection and control of cancer to improve patient experience.
Collapse
Affiliation(s)
- Ibrahim H. Musa
- Department of Software Engineering, School of Computer Science and Engineering, Southeast University, Nanjing, China
- Key Laboratory of Computer Network and Information Integration, Ministry of Education, Southeast University, Nanjing, China
| | - Lukman O. Afolabi
- Guangdong Immune Cell Therapy Engineering and Technology Research Center, Center for Protein and Cell-Based Drugs, Institute of Biomedicine and Biotechnology, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China
- University of Chinese Academy of Sciences, Beijing, China
| | - Ibrahim Zamit
- University of Chinese Academy of Sciences, Beijing, China
- Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, Guangdong, China
| | - Taha H. Musa
- Biomedical Research Institute, Darfur University College, Nyala, South Darfur, Sudan
- Key Laboratory of Environmental Medicine Engineering, Ministry of Education, Department of Epidemiology and Health Statistics, School of Public Health, Southeast University, Nanjing, Jiangsu Province, China
| | - Hassan H. Musa
- Faculty of Medical Laboratory Sciences, University of Khartoum, Khartoum, Sudan
| | - Andrew Tassang
- Faculty of Health Sciences, University of Buea, Cameroon
- Buea Regional Hospital, Annex, Cameroon
| | - Tosin Y. Akintunde
- Department of Sociology, School of Public Administration, Hohai University, Nanjing, China
| | - Wei Li
- Department of quality management, Children’s hospital of Nanjing Medical University, Nanjing, China
| |
Collapse
|
|
19
|
Breit HC, Block TK, Winkel DJ, Gehweiler JE, Glessgen CG, Seifert H, Wetterauer C, Boll DT, Heye TJ. Revisiting DCE-MRI: Classification of Prostate Tissue Using Descriptive Signal Enhancement Features Derived From DCE-MRI Acquisition With High Spatiotemporal Resolution. Invest Radiol 2021; 56:553-562. [PMID: 33660631 PMCID: PMC8373655 DOI: 10.1097/rli.0000000000000772] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/26/2022]
Abstract
METHODS A retrospective study (from January 2016 to July 2019) including 75 subjects (mean, 65 years; 46-80 years) with 2.5-second temporal resolution DCE-MRI and PIRADS 4 or 5 lesions was performed. Fifty-four subjects had biopsy-proven prostate cancer (Gleason 6, 15; Gleason 7, 20; Gleason 8, 13; Gleason 9, 6), whereas 21 subjects had negative MRI/ultrasound fusion-guided biopsies. Voxel-wise analysis of contrast signal enhancement was performed for all time points using custom-developed software, including automatic arterial input function detection. Seven descriptive parameter maps were calculated: normalized maximum signal intensity, time to start, time to maximum, time-to-maximum slope, and maximum slope with normalization on maximum signal and the arterial input function (SMN1, SMN2). The parameters were compared with ADC using multiparametric machine-learning models to determine classification accuracy. A Wilcoxon test was used for the hypothesis test and the Spearman coefficient for correlation. RESULTS There were significant differences (P < 0.05) for all 7 DCE-derived parameters between the normal peripheral zone versus PIRADS 4 or 5 lesions and the biopsy-positive versus biopsy-negative lesions. Multiparametric analysis showed better performance when combining ADC + DCE as input (accuracy/sensitivity/specificity, 97%/93%/100%) relative to ADC alone (accuracy/sensitivity/specificity, 94%/95%/95%) and to DCE alone (accuracy/sensitivity/specificity, 78%/79%/77%) in differentiating the normal peripheral zone from PIRADS lesions, biopsy-positive versus biopsy-negative lesions (accuracy/sensitivity/specificity, 68%/33%/81%), and Gleason 6 versus ≥7 prostate cancer (accuracy/sensitivity/specificity, 69%/60%/72%). CONCLUSIONS Descriptive perfusion characteristics derived from high-resolution DCE-MRI using model-free computations show significant differences between normal and cancerous tissue but do not reach the accuracy achieved with solely ADC-based classification. Combining ADC with DCE-based input features improved classification accuracy for PIRADS lesions, discrimination of biopsy-positive versus biopsy-negative lesions, and differentiation between Gleason 6 versus Gleason ≥7 lesions.
Collapse
Affiliation(s)
- Hanns C. Breit
- Department of Radiology, University Hospital Basel, Basel, Switzerland
| | | | - David J. Winkel
- Department of Radiology, University Hospital Basel, Basel, Switzerland
| | | | - Carl G. Glessgen
- Department of Radiology, University Hospital Basel, Basel, Switzerland
| | - Helge Seifert
- Department of Radiology, University Hospital Basel, Basel, Switzerland
| | | | - Daniel T. Boll
- Department of Radiology, University Hospital Basel, Basel, Switzerland
| | - Tobias J. Heye
- Department of Radiology, University Hospital Basel, Basel, Switzerland
| |
Collapse
|
|
20
|
Wegener D, Zips D, Gani C, Boeke S, Nikolaou K, Othman AE, Almansour H, Paulsen F, Müller AC. [Primary treatment of prostate cancer using 1.5 T MR-linear accelerator]. Radiologe 2021; 61:839-845. [PMID: 34297139 PMCID: PMC8410708 DOI: 10.1007/s00117-021-00882-8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 06/17/2021] [Indexed: 11/26/2022]
Abstract
Hintergrund Der potenzielle Nutzen des verbesserten Weichteilkontrastes von MR-Sequenzen gegenüber der Computertomographie (CT) für die Radiotherapie des Prostatakarzinoms ist bekannt und führt zu konsistenteren und kleineren Zielvolumina sowie verbesserter Risikoorganschonung. Hybridgeräte aus Magnetresonanztomographie (MRT) und Linearbeschleuniger (MR-Linac) stellen eine neue vielversprechende Erweiterung der radioonkologischen Therapieoptionen dar. Material und Methoden Dieser Artikel gibt eine Übersicht über bisherige Erfahrungen, Indikationen, Vorteile und Herausforderungen für die Radiotherapie des primären Prostatakarzinoms mit dem 1,5-T-MR-Linac. Ergebnisse Alle strahlentherapeutischen Therapieindikationen für das primäre Prostatakarzinom können mit dem 1,5-T-MR-Linac abgedeckt werden. Die potenziellen Vorteile umfassen die tägliche MR-basierte Lagekontrolle in Bestrahlungsposition und die Möglichkeit der täglichen Echtzeitanpassung des Bestrahlungsplans an die aktuelle Anatomie der Beckenorgane (adaptive Strahlentherapie). Zusätzlich werden am 1,5-T-MR-Linac funktionelle MRT-Sequenzen für individuelles Response-Assessment für die Therapieanpassung untersucht. Dadurch soll das therapeutische Fenster weiter optimiert werden. Herausforderungen stellen u. a. die technische Komplexität und die Dauer der Behandlungssitzung dar. Schlussfolgerung Der 1,5-T-MR-Linac erweitert das radioonkologische Spektrum in der Therapie des Prostatakarzinoms und bietet Vorteile durch tagesaktuelle MRT-basierte Zielvolumendefinition und Planadaptation. Weitere klinische Untersuchungen sind notwendig, um die Patienten zu identifizieren, die von der Behandlung am MR-Linac gegenüber anderen strahlentherapeutischen Methoden besonders profitieren.
Collapse
Affiliation(s)
- Daniel Wegener
- Universitätsklinik für Radioonkologie, Universitätsklinikum Tübingen, Eberhard Karls Universität Tübingen, Hoppe-Seyler-Str. 3, 72076, Tübingen, Deutschland.
| | - Daniel Zips
- Universitätsklinik für Radioonkologie, Universitätsklinikum Tübingen, Eberhard Karls Universität Tübingen, Hoppe-Seyler-Str. 3, 72076, Tübingen, Deutschland
| | - Cihan Gani
- Universitätsklinik für Radioonkologie, Universitätsklinikum Tübingen, Eberhard Karls Universität Tübingen, Hoppe-Seyler-Str. 3, 72076, Tübingen, Deutschland
| | - Simon Boeke
- Universitätsklinik für Radioonkologie, Universitätsklinikum Tübingen, Eberhard Karls Universität Tübingen, Hoppe-Seyler-Str. 3, 72076, Tübingen, Deutschland
| | - Konstantin Nikolaou
- Universitätsklinik für Radiologie, Eberhard Karls Universität Tübingen, Tübingen, Deutschland
| | - Ahmed E Othman
- Universitätsklinik für Radiologie, Eberhard Karls Universität Tübingen, Tübingen, Deutschland
- Universitätsklink für Neuroradiologie, Johannes Gutenberg-Universität Mainz, Mainz, Deutschland
| | - Haidara Almansour
- Universitätsklinik für Radiologie, Eberhard Karls Universität Tübingen, Tübingen, Deutschland
| | - Frank Paulsen
- Universitätsklinik für Radioonkologie, Universitätsklinikum Tübingen, Eberhard Karls Universität Tübingen, Hoppe-Seyler-Str. 3, 72076, Tübingen, Deutschland
| | | |
Collapse
|
|
21
|
Lai CC, Wang HK, Wang FN, Peng YC, Lin TP, Peng HH, Shen SH. Autosegmentation of Prostate Zones and Cancer Regions from Biparametric Magnetic Resonance Images by Using Deep-Learning-Based Neural Networks. SENSORS 2021; 21:s21082709. [PMID: 33921451 PMCID: PMC8070192 DOI: 10.3390/s21082709] [Citation(s) in RCA: 7] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 02/25/2021] [Revised: 04/01/2021] [Accepted: 04/09/2021] [Indexed: 12/21/2022]
Abstract
The accuracy in diagnosing prostate cancer (PCa) has increased with the development of multiparametric magnetic resonance imaging (mpMRI). Biparametric magnetic resonance imaging (bpMRI) was found to have a diagnostic accuracy comparable to mpMRI in detecting PCa. However, prostate MRI assessment relies on human experts and specialized training with considerable inter-reader variability. Deep learning may be a more robust approach for prostate MRI assessment. Here we present a method for autosegmenting the prostate zone and cancer region by using SegNet, a deep convolution neural network (DCNN) model. We used PROSTATEx dataset to train the model and combined different sequences into three channels of a single image. For each subject, all slices that contained the transition zone (TZ), peripheral zone (PZ), and PCa region were selected. The datasets were produced using different combinations of images, including T2-weighted (T2W) images, diffusion-weighted images (DWI) and apparent diffusion coefficient (ADC) images. Among these groups, the T2W + DWI + ADC images exhibited the best performance with a dice similarity coefficient of 90.45% for the TZ, 70.04% for the PZ, and 52.73% for the PCa region. Image sequence analysis with a DCNN model has the potential to assist PCa diagnosis.
Collapse
Affiliation(s)
- Chih-Ching Lai
- Department of Biomedical Engineering and Environmental Sciences, National Tsing Hua University, Hsinchu 300044, Taiwan; (C.-C.L.); (F.-N.W.)
| | - Hsin-Kai Wang
- Department of Radiology, Taipei Veterans General Hospital, Taipei 112201, Taiwan;
- School of Medicine, National Yang Ming Chiao Tung University, Taipei 112304, Taiwan; (Y.-C.P.); (T.-P.L.)
| | - Fu-Nien Wang
- Department of Biomedical Engineering and Environmental Sciences, National Tsing Hua University, Hsinchu 300044, Taiwan; (C.-C.L.); (F.-N.W.)
| | - Yu-Ching Peng
- School of Medicine, National Yang Ming Chiao Tung University, Taipei 112304, Taiwan; (Y.-C.P.); (T.-P.L.)
- Department of Pathology and Laboratory Medicine, Taipei Veterans General Hospital, Taipei 112201, Taiwan
| | - Tzu-Ping Lin
- School of Medicine, National Yang Ming Chiao Tung University, Taipei 112304, Taiwan; (Y.-C.P.); (T.-P.L.)
- Department of Urology, Taipei Veterans General Hospital, Taipei 112201, Taiwan
| | - Hsu-Hsia Peng
- Department of Biomedical Engineering and Environmental Sciences, National Tsing Hua University, Hsinchu 300044, Taiwan; (C.-C.L.); (F.-N.W.)
- Correspondence: (H.-H.P.); (S.-H.S.); Tel.: +886-3-571-5131 (ext. 80189) (H.-H.P.); +886-2-28757350 (S.-H.S.)
| | - Shu-Huei Shen
- Department of Radiology, Taipei Veterans General Hospital, Taipei 112201, Taiwan;
- School of Medicine, National Yang Ming Chiao Tung University, Taipei 112304, Taiwan; (Y.-C.P.); (T.-P.L.)
- Correspondence: (H.-H.P.); (S.-H.S.); Tel.: +886-3-571-5131 (ext. 80189) (H.-H.P.); +886-2-28757350 (S.-H.S.)
| |
Collapse
|
|
22
|
Brain tissues have single-voxel signatures in multi-spectral MRI. Neuroimage 2021; 234:117986. [PMID: 33757906 DOI: 10.1016/j.neuroimage.2021.117986] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/17/2020] [Revised: 03/03/2021] [Accepted: 03/15/2021] [Indexed: 12/20/2022] Open
Abstract
Since the seminal works by Brodmann and contemporaries, it is well-known that different brain regions exhibit unique cytoarchitectonic and myeloarchitectonic features. Transferring the approach of classifying brain tissues - and other tissues - based on their intrinsic features to the realm of magnetic resonance (MR) is a longstanding endeavor. In the 1990s, atlas-based segmentation replaced earlier multi-spectral classification approaches because of the large overlap between the class distributions. Here, we explored the feasibility of performing global brain classification based on intrinsic MR features, and used several technological advances: ultra-high field MRI, q-space trajectory diffusion imaging revealing voxel-intrinsic diffusion properties, chemical exchange saturation transfer and semi-solid magnetization transfer imaging as a marker of myelination and neurochemistry, and current neural network architectures to analyze the data. In particular, we used the raw image data as well to increase the number of input features. We found that a global brain classification of roughly 97 brain regions was feasible with gross classification accuracy of 60%; and that mapping from voxel-intrinsic MR data to the brain region to which the data belongs is possible. This indicates the presence of unique MR signals of different brain regions, similar to their cytoarchitectonic and myeloarchitectonic fingerprints.
Collapse
|
|
23
|
Digiacomo L, Caputo D, Coppola R, Cascone C, Giulimondi F, Palchetti S, Pozzi D, Caracciolo G. Efficient pancreatic cancer detection through personalized protein corona of gold nanoparticles. Biointerphases 2021; 16:011010. [PMID: 33706529 DOI: 10.1116/6.0000540] [Citation(s) in RCA: 11] [Impact Index Per Article: 2.8] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/17/2022] Open
Abstract
Characterization of the personalized protein corona (PC) that forms around nanomaterials upon exposure to human plasma is emerging as powerful technology for early cancer detection. However, low material stability and interbatch variability have limited its clinical application so far. Here, we present a nanoparticle-enabled blood (NEB) test that uses 120 nm gold nanoparticles (NPs) as the accumulator of blood plasma proteins. In the test, the personalized PC of gold NPs is characterized by sodium dodecyl sulfate polyacrylamide gel electrophoresis. As a paradigmatic case study, pancreatic ductal adenocarcinoma (PDAC) was chosen due to the lack of effective detection strategies that lead to poor survival rate after diagnosis (<1 year) and extremely low 5-years survival rate (15-20%). Densitometric analysis of 75 protein patterns (28 from healthy subjects and 47 from PDAC patients) allowed us to distinguish nononcological and PDAC patients with good sensitivity (78.6%) and specificity (85.3%). The gold NEB test is completely aligned to affordable, sensitive, specific, user-friendly, rapid and robust, equipment-free, and deliverable to end users criteria stated by the World Health Organization for cancer screening and detection. Thus, it could be very useful in clinical practice at the first level of investigation to decide whether to carry out more invasive analyses or not.
Collapse
Affiliation(s)
- Luca Digiacomo
- Nanodelivery Lab, Department of Molecular Medicine, Sapienza University of Rome, Rome 00161, Italy
| | - Damiano Caputo
- General Surgery Unit, University Campus Bio-Medico di Roma, Rome 00128, Italy
| | - Roberto Coppola
- General Surgery Unit, University Campus Bio-Medico di Roma, Rome 00128, Italy
| | - Chiara Cascone
- General Surgery Unit, University Campus Bio-Medico di Roma, Rome 00128, Italy
| | - Francesca Giulimondi
- Nanodelivery Lab, Department of Molecular Medicine, Sapienza University of Rome, Rome 00161, Italy
| | - Sara Palchetti
- Nanodelivery Lab, Department of Molecular Medicine, Sapienza University of Rome, Rome 00161, Italy
| | - Daniela Pozzi
- Nanodelivery Lab, Department of Molecular Medicine, Sapienza University of Rome, Rome 00161, Italy
| | - Giulio Caracciolo
- Nanodelivery Lab, Department of Molecular Medicine, Sapienza University of Rome, Rome 00161, Italy
| |
Collapse
|
|
24
|
Dai WB, Xu J, Yu B, Chen L, Chen Y, Zhan J. Correlation of Stiffness of Prostate Cancer Measured by Shear Wave Elastography with Grade Group: A Preliminary Study. ULTRASOUND IN MEDICINE & BIOLOGY 2021; 47:288-295. [PMID: 33234327 DOI: 10.1016/j.ultrasmedbio.2020.10.018] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 06/17/2020] [Revised: 10/15/2020] [Accepted: 10/27/2020] [Indexed: 06/11/2023]
Abstract
The aim of study was to explore the correlation between shear wave elastography (SWE) and grade group (GG) of prostate cancer (PCa). This retrospective study involved prostate-specific antigen elevated patients with elevated prostate-specific antigen levels who underwent SWE before transrectal ultrasound-guided needle biopsy. A total of 49 PCa lesions were reviewed after radical prostatectomy; 3-7 regions of interest were placed within the cancerous area on axial view compared with the tumor foci outlined on the slides by pathologist. The maximum SWE value was measured, quantitative SWE parameters (Emax, Emean, Emin and standard deviation [SD]) were recorded and correlated with GG and then parameters were compared between indolent (≤2) and aggressive (≥3) GGs. The diagnostic value of each parameter was compared with the receiver operating characteristic curve. Forty-nine PCa foci were divided into two groups on the basis of their GGs. All SWE parameters exhibited a significant linear trend with GG. The area under the receiver operating characteristic curve (AUC) was 0.816 for Emax; with a cutoff point of 84 kPa, sensitivity and specificity were 81.3% and 82.4% to differentiate low and high GGs in PCa. The AUC was 0.776 for Emean; with a cutoff point of 71 kPa, sensitivity and specificity were 78.1% and 76.5%. For Emin, the AUC was 0.739; with a cutoff point of 60 kPa, sensitivity and specificity were 68.8% and 70.6%. For SD, the AUC was 0.681; with a cutoff point of 8.3 kPa, sensitivity and specificity were 46.9% and 94.1%. There were no significant differences between the four SWE parameters (p < 0.05 for all). SWE features were correlated with GGs, and this correlation may have excellent diagnostic performance in predicting high GG in PCa.
Collapse
Affiliation(s)
- Wen-Bin Dai
- Department of Urology Surgery, Huadong Hospital, Fudan University, Shanghai, China
| | - Jun Xu
- Department of Urology Surgery, Huadong Hospital, Fudan University, Shanghai, China
| | - Bo Yu
- Department of Pathology, Huadong Hospital, Fudan University, Shanghai, China
| | - Lin Chen
- Department of Ultrasound, Huadong Hospital, Fudan University, Shanghai, China
| | - Yue Chen
- Department of Ultrasound, Huadong Hospital, Fudan University, Shanghai, China
| | - Jia Zhan
- Department of Ultrasound, Huadong Hospital, Fudan University, Shanghai, China.
| |
Collapse
|
|
25
|
Das C, Kubihal V, Sharma S, Kumar R, Seth A, Kumar R, Kaushal S, Sarangi J, Gupta R. Multiparametric magnetic resonance imaging, 68Ga prostate-specific membrane antigen positron emission tomography–Computed tomography, and respective quantitative parameters in detection and localization of clinically significant prostate cancer in intermediate- and high-risk group patients: An Indian demographic study. Indian J Nucl Med 2021; 36:362-370. [PMID: 35125753 PMCID: PMC8771078 DOI: 10.4103/ijnm.ijnm_80_21] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/03/2021] [Revised: 09/12/2021] [Accepted: 09/14/2021] [Indexed: 11/09/2022] Open
Abstract
Objectives: The objective of this study was to evaluate the diagnostic accuracy of multiparametric magnetic resonance imaging (mpMRI) and 68Ga prostate-specific membrane antigen positron emission tomography–computed tomography (PSMA PET-CT) and respective quantitative parameters (Ktrans – influx rate contrast, Kep – efflux rate constant, ADC – apparent diffusion coefficient, and SUVmax ratio – prostate SUVmax to background SUVmax ratio) in detection and localization of clinically significant prostate cancer (CSPCa) in D’Amico intermediate- and high-risk group patients (prostate-specific antigen [PSA] >10 ng/ml). Methodology: The study included thirty-three consecutive adult men with serum prostate specific antigen >10ng/ml, and systematic 12 core prostate biopsy proven prostate cancer. All the 33 patients, were evaluated with mpMRI, and 68Ga PSMA PET-CT. The biopsy specimens and imaging were evaluated for 12 sectors per prostate by a predetermined scheme. Results: MpMRI Prostate Imaging Reporting and Data System version 2 (PI-RADS v2) score ≥3 showed higher sensitivity than 68Ga PSMA PET-CT (96.3% vs. 82.4%), with similar specificity (54.5% vs. 54.5%) (n = 33 patients, 396 sectors). Combined use of MRI and 68Ga PSMA PET-CT in parallel increased sensitivity (99.5%) and NPV (98.7%) for detection of CSPCa and combined use of MRI and 68Ga PSMA PET-CT in series increased specificity (71.8%) and PPV (71.5%) (n = 33 patients, 396 sectors). ADC showed a strong negative correlation with Gleason score (r = −0.77), and the highest discriminative ability for detection and localization of CSPCa (area under curve [AUC]: 0.91), followed by Ktrans (r = 0.74; AUC: 0.89), PI-RADS (0.73; 0.86), SUVmax ratio (0.49; 0.74), and Kep (0.24; 0.66). Conclusion: MpMRI PI-RADS v2 score and 68Ga PSMA PET-CT (individually as well as in combination) are reliable tool for detection and localization of CSPCa. Quantitative MRI and 68Ga PSMA PET-CT parameters have potential to predict Gleason score and detect CSPCa.
Collapse
|
|
26
|
Computer-Aided Diagnosis in Multiparametric MRI of the Prostate: An Open-Access Online Tool for Lesion Classification with High Accuracy. Cancers (Basel) 2020; 12:cancers12092366. [PMID: 32825612 PMCID: PMC7565879 DOI: 10.3390/cancers12092366] [Citation(s) in RCA: 8] [Impact Index Per Article: 1.6] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/12/2020] [Revised: 08/09/2020] [Accepted: 08/20/2020] [Indexed: 01/23/2023] Open
Abstract
Computer-aided diagnosis (CADx) approaches could help to objectify reporting on prostate mpMRI, but their use in many cases is hampered due to common-built algorithms that are not publicly available. The aim of this study was to develop an open-access CADx algorithm with high accuracy for classification of suspicious lesions in mpMRI of the prostate. This retrospective study was approved by the local ethics commission, with waiver of informed consent. A total of 124 patients with 195 reported lesions were included. All patients received mpMRI of the prostate between 2014 and 2017, and transrectal ultrasound (TRUS)-guided and targeted biopsy within a time period of 30 days. Histopathology of the biopsy cores served as a standard of reference. Acquired imaging parameters included the size of the lesion, signal intensity (T2w images), diffusion restriction, prostate volume, and several dynamic parameters along with the clinical parameters patient age and serum PSA level. Inter-reader agreement of the imaging parameters was assessed by calculating intraclass correlation coefficients. The dataset was stratified into a train set and test set (156 and 39 lesions in 100 and 24 patients, respectively). Using the above parameters, a CADx based on an Extreme Gradient Boosting algorithm was developed on the train set, and tested on the test set. Performance optimization was focused on maximizing the area under the Receiver Operating Characteristic curve (ROCAUC). The algorithm was made publicly available on the internet. The CADx reached an ROCAUC of 0.908 during training, and 0.913 during testing (p = 0.93). Additionally, established rule-in and rule-out criteria allowed classifying 35.8% of the malignant and 49.4% of the benign lesions with error rates of <2%. All imaging parameters featured excellent inter-reader agreement. This study presents an open-access CADx for classification of suspicious lesions in mpMRI of the prostate with high accuracy. Applying the provided rule-in and rule-out criteria might facilitate to further stratify the management of patients at risk.
Collapse
|
|
27
|
Kim SH. Determination of Gleason score discrepancy for risk stratification in magnetic resonance-ultrasound fusion prostate biopsy. Acta Radiol 2020; 61:1134-1142. [PMID: 31825763 DOI: 10.1177/0284185119891695] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/16/2022]
Abstract
BACKGROUND Magnetic resonance imaging (MRI)-ultrasound (US) fusion biopsy remains challenging and highlights the need towards standardization. PURPOSE To characterize the clinical and MRI features of clinically significant prostate cancer (csPCa) with discrepant Gleason score (GS) in MRI-US fusion biopsy. MATERIAL AND METHODS A total of 400 consecutive patients with suspected cancer lesions who underwent MRI-US fusion biopsy and subsequent prostatectomy were included. In the comparison of biopsy GS with pathology GS, matched lesions were defined as a GS, and discrepant lesions were defined as an upgrade of the GS. Descriptive statistics were used to define clinical characteristics, including age, prostate-specific antigen (PSA), PSA density, and maximal cancer core length (MCCL). Differences between lesions with matched and discrepant GS were determined considering the location and PI-RADS v2 score. A paired comparison of the volumes between the two groups was performed. RESULTS There were 130 lesions with discrepant GS in 124 patients. There was no significant difference in the age, PSA, and PSA density between the two groups, except for the MCCL (P = 0.028). The lesions were distributed in the peripheral (n = 88) and transition (n = 42) zones; 33, 50, and 47 lesions were at the apex, mid-gland, and base levels, respectively. PI-RADS scores were as follows: 2 (n = 5), 3 (n = 8), 4 (n = 68), and 5 (n = 39). In comparison with matched lesions, discrepant lesions had significantly smaller multiparametric MRI-measured cancer volumes (P < 0.05). CONCLUSION Knowledge of discrepant GS in MRI-US fusion biopsy is important, and a careful approach is needed to reduce this discrepancy.
Collapse
Affiliation(s)
- See Hyung Kim
- Departmet of Radiology, School of Medicine, Kyungpook National University, Kyungpook National University Hospital, Daegu, Republic of Korea
| |
Collapse
|
|
28
|
Huang X, Schurr RN, Wang S, Miao Q, Li T, Jia G. Development of Radiofrequency Saturation Amplitude-independent Quantitative Markers for Magnetization Transfer MRI of Prostate Cancer. Curr Med Imaging 2020; 16:695-702. [PMID: 32723241 DOI: 10.2174/1573405615666190318153328] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.2] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/01/2018] [Revised: 02/06/2019] [Accepted: 03/19/2019] [Indexed: 11/22/2022]
Abstract
BACKGROUND In the United States, prostate cancer has a relatively large impact on men's health. Magnetic resonance imaging (MRI) is useful for the diagnosis and treatment of prostate cancer. INTRODUCTION The purpose of this study was to develop a quantitative marker for use in prostate cancer magnetization transfer (MT) magnetic resonance imaging (MRI) studies that is independent of radiofrequency (RF) saturation amplitude. METHODS Eighteen patients with biopsy-proven prostate cancer were enrolled in this study. MTMRI images were acquired using four RF saturation amplitudes at 33 frequency offsets. ROIs were delineated for the peripheral zone (PZ), central gland (CG), and tumor. Z-spectral data were collected in each region and fit to a three-parameter equation. The three parameters are: the magnitude of the bulk water pool (Aw), the full width at half maximum of the water pool (Gw), and the magnitude of the bound pool (Ab), while, the slopes from the linear regressions of Gw and Ab on RF saturation amplitude (called kAb and kGw) were used as quantitative markers. RESULTS A pairwise statistically significant difference was found between the PZ and tumor regions for the two saturation amplitude-independent quantitative markers. No pairwise statistically significant differences were found between the CG and tumor regions for any quantitative markers. CONCLUSION The significant differences between the values of the two RF saturation amplitudeindependent quantitative markers in the PZ and tumor regions reveal that these markers may be capable of distinguishing healthy PZ tissue from prostate cancer.
Collapse
Affiliation(s)
- Xunan Huang
- Xi'an Key Laboratory of Big Data and Intelligent Vision, School of Computer Science and Technology, Xidian University, Xi'an, Shaanxi 710071, China
| | - Ryan N Schurr
- Department of Physics and Astronomy, Louisiana State University, Baton Rouge, LA, 70803, United States
| | - Shuzhen Wang
- Xi'an Key Laboratory of Big Data and Intelligent Vision, School of Computer Science and Technology, Xidian University, Xi'an, Shaanxi 710071, China
| | - Qiguang Miao
- Xi'an Key Laboratory of Big Data and Intelligent Vision, School of Computer Science and Technology, Xidian University, Xi'an, Shaanxi 710071, China
| | - Tanping Li
- School of Physics and Optoelectronic Engineering, Xidian University, Xi'an, Shaanxi 710071, China
| | - Guang Jia
- Xi'an Key Laboratory of Big Data and Intelligent Vision, School of Computer Science and Technology, Xidian University, Xi'an, Shaanxi 710071, China
| |
Collapse
|
|
29
|
Bielak L, Wiedenmann N, Nicolay NH, Lottner T, Fischer J, Bunea H, Grosu AL, Bock M. Automatic Tumor Segmentation With a Convolutional Neural Network in Multiparametric MRI: Influence of Distortion Correction. ACTA ACUST UNITED AC 2020; 5:292-299. [PMID: 31572790 PMCID: PMC6752289 DOI: 10.18383/j.tom.2019.00010] [Citation(s) in RCA: 9] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/14/2022]
Abstract
Precise tumor segmentation is a crucial task in radiation therapy planning. Convolutional neural networks (CNNs) are among the highest scoring automatic approaches for tumor segmentation. We investigate the difference in segmentation performance of geometrically distorted and corrected diffusion-weighted data using data of patients with head and neck tumors; 18 patients with head and neck tumors underwent multiparametric magnetic resonance imaging, including T2w, T1w, T2*, perfusion (ktrans), and apparent diffusion coefficient (ADC) measurements. Owing to strong geometrical distortions in diffusion-weighted echo planar imaging in the head and neck region, ADC data were additionally distortion corrected. To investigate the influence of geometrical correction, first 14 CNNs were trained on data with geometrically corrected ADC and another 14 CNNs were trained using data without the correction on different samples of 13 patients for training and 4 patients for validation each. The different sets were each trained from scratch using randomly initialized weights, but the training data distributions were pairwise equal for corrected and uncorrected data. Segmentation performance was evaluated on the remaining 1 test-patient for each of the 14 sets. The CNN segmentation performance scored an average Dice coefficient of 0.40 ± 0.18 for data including distortion-corrected ADC and 0.37 ± 0.21 for uncorrected data. Paired t test revealed that the performance was not significantly different (P = .313). Thus, geometrical distortion on diffusion-weighted imaging data in patients with head and neck tumor does not significantly impair CNN segmentation performance in use.
Collapse
Affiliation(s)
- Lars Bielak
- Radiology, Medical Physics.,German Cancer Consortium (DKTK), Partner Site Freiburg, Freiburg, Germany
| | - Nicole Wiedenmann
- Radiation Oncology, Medical Center University of Freiburg, Faculty of Medicine, University of Freiburg, Freiburg, Germany; and.,German Cancer Consortium (DKTK), Partner Site Freiburg, Freiburg, Germany
| | - Nils Henrik Nicolay
- Radiation Oncology, Medical Center University of Freiburg, Faculty of Medicine, University of Freiburg, Freiburg, Germany; and.,German Cancer Consortium (DKTK), Partner Site Freiburg, Freiburg, Germany
| | | | | | - Hatice Bunea
- Radiation Oncology, Medical Center University of Freiburg, Faculty of Medicine, University of Freiburg, Freiburg, Germany; and.,German Cancer Consortium (DKTK), Partner Site Freiburg, Freiburg, Germany
| | - Anca-Ligia Grosu
- Radiation Oncology, Medical Center University of Freiburg, Faculty of Medicine, University of Freiburg, Freiburg, Germany; and.,German Cancer Consortium (DKTK), Partner Site Freiburg, Freiburg, Germany
| | - Michael Bock
- Radiology, Medical Physics.,German Cancer Consortium (DKTK), Partner Site Freiburg, Freiburg, Germany
| |
Collapse
|
|
30
|
Labra A, González F, Silva C, Franz G, Pinochet R, Gupta RT. MRI/TRUS fusion vs. systematic biopsy: intra-patient comparison of diagnostic accuracy for prostate cancer using PI-RADS v2. Abdom Radiol (NY) 2020; 45:2235-2243. [PMID: 32249349 DOI: 10.1007/s00261-020-02481-y] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/08/2023]
Abstract
OBJECTIVE To evaluate the efficacy of multiparametric magnetic resonance/transrectal ultrasound fusion (MRI/TRUS fusion) biopsy versus systematic biopsy and its association with PI-RADS v2 categories in patients with suspected prostate cancer. MATERIALS AND METHODS 122 patients undergoing both MRI/TRUS fusion and systematic biopsy, with suspicion of prostate cancer, with suspicious findings on MRI based on PI-RADS v2, were included between April 2016 and March 2017. Comparison of tumor detection rates using each technique and combined techniques was performed for all lesions as well as those that are traditionally difficult to access (i.e., anterior lesions). RESULTS Prostate cancer was detected in 83/122 patients (68%) with 74.6% clinically significant lesions (Gleason 3 + 4 or greater). There was a statistically significant difference in presence of clinically significant prostate cancer in PI-RADS v2 categories of 3, 4, and 5 (20%, 52% and 77%, respectively, p < 0.001). Fusion biopsy was positive in a significantly higher percentage of patients versus systematic biopsy (56% versus 48%, respectively, p < 0.05). The fusion biopsy alone was positive in 20%. Of 34 patients with anterior lesions on MRI, 44% were detected only by fusion biopsy, with a joint yield of 71%. In patients with previous negative systematic biopsies, 48.7% lesions were found by fusion biopsy with 20.5% being exclusively positive by this method. The percentage of positive cores for fusion biopsies was significantly higher than for systematic biopsies (26% vs. 12.3%, p < 0.001). CONCLUSION The incorporation of MRI/TRUS fusion biopsy significantly improves the detection rate of prostate cancer versus systematic biopsy, particularly for anterior lesions.
Collapse
Affiliation(s)
- Andrés Labra
- Universidad del Desarrollo, Servicio de Radiologia, Facultad de Medicina Clínica Alemana De Santiago, 5951 Vitacura, 9160002, Santiago, Chile
| | - Fernando González
- Universidad del Desarrollo, Servicio de Radiologia, Facultad de Medicina Clínica Alemana De Santiago, 5951 Vitacura, 9160002, Santiago, Chile
- Department of Radiology, Duke University Medical Center, DUMC Box 3808, Durham, NC, 27710, USA
| | - Claudio Silva
- Universidad del Desarrollo, Servicio de Radiologia, Facultad de Medicina Clínica Alemana De Santiago, 5951 Vitacura, 9160002, Santiago, Chile
| | - Gerhard Franz
- Universidad del Desarrollo, Servicio de Radiologia, Facultad de Medicina Clínica Alemana De Santiago, 5951 Vitacura, 9160002, Santiago, Chile
| | - Rodrigo Pinochet
- Department of Surgery, Division of Urology, Clínica Alemana de Santiago, 5951 Vitacura, 9160002, Santiago, Chile
| | - Rajan T Gupta
- Department of Radiology, Duke University Medical Center, DUMC Box 3808, Durham, NC, 27710, USA.
- Duke Cancer Institute Center for Prostate and Urologic Cancers, 20 Duke Medicine Circle, DUMC Box 103861, Durham, NC, 27710, USA.
- Department of Surgery, Division of Urologic Surgery and Duke Prostate Center, Duke University Medical Center, DUMC Box 2804, Durham, NC, 27710, USA.
| |
Collapse
|
|
31
|
Thomas JV, Abou Elkassem AM, Ganeshan B, Smith AD. MR Imaging Texture Analysis in the Abdomen and Pelvis. Magn Reson Imaging Clin N Am 2020; 28:447-456. [PMID: 32624161 DOI: 10.1016/j.mric.2020.03.009] [Citation(s) in RCA: 6] [Impact Index Per Article: 1.2] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/12/2022]
Abstract
Add "which is a" before "distribution"? Texture analysis (TA) is a form of radiomics that refers to quantitative measurements of the histogram, distribution and/or relationship of pixel intensities or gray scales within a region of interest on an image. TA can be applied to MR images of the abdomen and pelvis, with the main strength quantitative analysis of pixel intensities and heterogeneity rather than subjective/qualitative analysis. There are multiple limitations of MRTA. Despite these limitations, there is a growing body of literature supporting MRTA. This review discusses application of MRTA to the abdomen and pelvis.
Collapse
Affiliation(s)
- John V Thomas
- Body Imaging Section, Department of Radiology, University of Alabama at Birmingham, N355 Jefferson Tower, 619 19th Street South, Birmingham, AL 35249-6830, USA.
| | - Asser M Abou Elkassem
- Department of Radiology, University of Alabama at Birmingham, 619 19th Street South, Birmingham, AL 35249-6830, USA
| | - Balaji Ganeshan
- Institute of Nuclear Medicine, University College of London, 5th Floor, Tower, 235 Euston Road, London NW1 2BU, UK
| | - Andrew D Smith
- Department of Radiology, University of Alabama at Birmingham, 619 19th Street South, Birmingham, AL 35249-6830, USA
| |
Collapse
|
|
32
|
Wildeboer RR, van Sloun RJG, Wijkstra H, Mischi M. Artificial intelligence in multiparametric prostate cancer imaging with focus on deep-learning methods. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2020; 189:105316. [PMID: 31951873 DOI: 10.1016/j.cmpb.2020.105316] [Citation(s) in RCA: 29] [Impact Index Per Article: 5.8] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 07/03/2019] [Revised: 12/09/2019] [Accepted: 01/04/2020] [Indexed: 05/16/2023]
Abstract
Prostate cancer represents today the most typical example of a pathology whose diagnosis requires multiparametric imaging, a strategy where multiple imaging techniques are combined to reach an acceptable diagnostic performance. However, the reviewing, weighing and coupling of multiple images not only places additional burden on the radiologist, it also complicates the reviewing process. Prostate cancer imaging has therefore been an important target for the development of computer-aided diagnostic (CAD) tools. In this survey, we discuss the advances in CAD for prostate cancer over the last decades with special attention to the deep-learning techniques that have been designed in the last few years. Moreover, we elaborate and compare the methods employed to deliver the CAD output to the operator for further medical decision making.
Collapse
Affiliation(s)
- Rogier R Wildeboer
- Lab of Biomedical Diagnostics, Department of Electrical Engineering, Eindhoven University of Technology, De Zaale, 5600 MB, Eindhoven, the Netherlands.
| | - Ruud J G van Sloun
- Lab of Biomedical Diagnostics, Department of Electrical Engineering, Eindhoven University of Technology, De Zaale, 5600 MB, Eindhoven, the Netherlands.
| | - Hessel Wijkstra
- Lab of Biomedical Diagnostics, Department of Electrical Engineering, Eindhoven University of Technology, De Zaale, 5600 MB, Eindhoven, the Netherlands; Department of Urology, Amsterdam University Medical Centers, University of Amsterdam, Meibergdreef 9, 1105 AZ, Amsterdam, the Netherlands
| | - Massimo Mischi
- Lab of Biomedical Diagnostics, Department of Electrical Engineering, Eindhoven University of Technology, De Zaale, 5600 MB, Eindhoven, the Netherlands
| |
Collapse
|
|
33
|
Falaschi Z, Valenti M, Lanzo G, Attanasio S, Valentini E, García Navarro LI, Aquilini F, Stecco A, Carriero A. Accuracy of ADC ratio in discriminating true and false positives in multiparametric prostatic MRI. Eur J Radiol 2020; 128:109024. [PMID: 32387923 DOI: 10.1016/j.ejrad.2020.109024] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.6] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/26/2020] [Revised: 04/14/2020] [Accepted: 04/15/2020] [Indexed: 01/17/2023]
Abstract
PURPOSE Our goal was to evaluate the usefulness of apparent diffusion coefficient (ADC) ratios in discriminating true from false positives in multiparametric (mp) prostate MRI in clinical practice. METHODS We retrospectively evaluated 98 prostate lesions in a series of 73 patients who had undergone prostate mpMRI and standard 12-core prostatic biopsy in our institution from 2016 to 2018. Two experienced radiologists performed double blind ADC value quantifications of both MRI-identified lesions and apparently benign contralateral prostatic parenchyma in a circular region of interest (ROI) of ∼10 mm2. The ratios between the mean values of both measurements (i.e., ADC ratio mean) and between the minimum value of the lesion and the maximum value of the benign parenchyma (i.e., ADC ratio min-max) were automatically calculated. The malignancy of all lesions was determined through biopsy according to Gleason score (GS ≥ 6) and localization. RESULTS For Reader 1, the area under the ROC curve (AUC) of ADC ratio mean and ADC ratio min-max were 0.72 and 0.67, respectively, whereas for Reader 2 these values were 0.74 and 0.71, respectively. The best cut-off values for ADC ratio means were ≥ 0.5 (Reader 1) and ≥ 0.6 (Reader 2), with a sensitivity of 76.3 % and 84.2 % and a specificity of 51.7 % and 50 %, respectively. Moreover, based on a threshold of 0.6, no clinically significant prostate cancer (csPCa) was missed by Reader 1, while only one went unnoticed by Reader 2. CONCLUSION The ADC ratio is a useful and moderately accurate complementary tool to diagnose prostate cancer in the mp-MRI.
Collapse
Affiliation(s)
- Zeno Falaschi
- Azienda Ospedaliero-Universitaria Maggiore della Carita, Novara, NO, Italy.
| | - Martina Valenti
- Azienda Ospedaliero-Universitaria Maggiore della Carita, Novara, NO, Italy
| | - Giuseppe Lanzo
- Azienda Ospedaliero-Universitaria Maggiore della Carita, Novara, NO, Italy
| | - Silvia Attanasio
- Azienda Ospedaliero-Universitaria Maggiore della Carita, Novara, NO, Italy
| | - Eleonora Valentini
- Azienda Ospedaliero-Universitaria Maggiore della Carita, Novara, NO, Italy
| | | | | | - Alessandro Stecco
- Azienda Ospedaliero-Universitaria Maggiore della Carita, Novara, NO, Italy
| | | |
Collapse
|
|
34
|
High spatiotemporal resolution dynamic contrast-enhanced MRI improves the image-based discrimination of histopathology risk groups of peripheral zone prostate cancer: a supervised machine learning approach. Eur Radiol 2020; 30:4828-4837. [DOI: 10.1007/s00330-020-06849-y] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.2] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/14/2020] [Revised: 02/21/2020] [Accepted: 03/31/2020] [Indexed: 12/15/2022]
|
|
35
|
Winkel DJ, Breit HC, Shi B, Boll DT, Seifert HH, Wetterauer C. Predicting clinically significant prostate cancer from quantitative image features including compressed sensing radial MRI of prostate perfusion using machine learning: comparison with PI-RADS v2 assessment scores. Quant Imaging Med Surg 2020; 10:808-823. [PMID: 32355645 DOI: 10.21037/qims.2020.03.08] [Citation(s) in RCA: 9] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/11/2022]
Abstract
Background To investigate if supervised machine learning (ML) classifiers would be able to predict clinically significant cancer (sPC) from a set of quantitative image-features and to compare these results with established PI-RADS v2 assessment scores. Methods We retrospectively included 201, histopathologically-proven, peripheral zone (PZ) prostate cancer lesions. Gleason scores ≤3+3 were considered as clinically insignificant (inPC) and Gleason scores ≥3+4 as sPC and were encoded in a binary fashion, serving as ground-truth. MRI was performed at 3T with high spatiotemporal resolution DCE using Golden-angle RAdial SParse (GRASP) MRI. Perfusion maps (Ktrans, Kep, Ve), apparent diffusion coefficient (ADC), and absolute T2-signal intensities (SI) were determined in all lesions and served as input parameters for four supervised ML models: Gradient Boosting Machines (GBM), Neural Networks (NNet), Random Forest (RF) and Support Vector Machines (SVM). ML results and PI-RADS scores were compared with the ground-truth. Next ROC-curves and AUC values were calculated. Results All ML models outperformed PI-RADS v2 assessment scores in the prediction of sPC (RF, GBM, NNet and SVM vs. PI-RADS: AUC 0.899, 0.864, 0.884 and 0.874 vs. 0.595, all P<0.001). Conclusions Using quantitative imaging parameters as input, supervised ML models outperformed PI-RADS v2 assessment scores in the prediction of sPC. These results indicate that quantitative imagining parameters contain relevant information for the prediction of sPC from image features.
Collapse
Affiliation(s)
- David Jean Winkel
- Department of Radiology, University Hospital Basel, Basel, Switzerland
| | | | - Bibo Shi
- Siemens Medical Imaging Technologies, Princeton, NJ, USA
| | - Daniel T Boll
- Department of Radiology, University Hospital Basel, Basel, Switzerland
| | | | | |
Collapse
|
|
36
|
Zhang Y, Wells SA, Triche BL, Kelcz F, Hernando D. Stimulated-echo diffusion-weighted imaging with moderate b values for the detection of prostate cancer. Eur Radiol 2020; 30:3236-3244. [PMID: 32064561 DOI: 10.1007/s00330-020-06689-w] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.6] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/27/2019] [Revised: 12/27/2019] [Accepted: 01/29/2020] [Indexed: 12/27/2022]
Abstract
OBJECTIVES Conventional spin-echo (SE) DWI leads to a fundamental trade-off depending on the b value: high b value provides better lesion contrast-to-noise ratio (CNR) by sacrificing signal-to-noise ratio (SNR), image quality, and quantitative reliability. A stimulated-echo (STE) DWI acquisition is evaluated for high-CNR imaging of prostate cancer while maintaining SNR and reliable apparent diffusion coefficient (ADC) mapping. METHODS In this prospective, IRB-approved study, 27 patients with suspected prostate cancer (PCa) were scanned with three DWI sequences (SE b = 800 s/mm2, SE b = 1500 s/mm2, and STE b = 800 s/mm2) after informed consent was obtained. ROIs were drawn on biopsy-confirmed cancer and non-cancerous tissue to perform quantitative SNR, CNR, and ADC measurements. Qualitative metrics (SNR, CNR, and overall image quality) were evaluated by three experienced radiologists. Metrics were compared pairwise between the three acquisitions using a t test (quantitative metrics) and Wilcoxon rank test (qualitative metrics). RESULTS Quantitative measurements showed that STE DWI at b = 800 s/mm2 has significantly better SNR compared to SE DWI at b = 1500 s/mm2 (p < 0.0001) and comparable CNR to high-b value SE DWI at b = 1500 s/mm2 (p < 0.05) in the peripheral zone. Qualitative assessment showed preference to STE b = 800 s/mm2 in SNR and SE b = 1500 s/mm2 in CNR. The overall image quality and lesion detectability among most readers showed no significant preference between STE b = 800 s/mm2 and SE b = 1500 s/mm2. Further, STE DWI had similar ADC contrast between lesion and normal tissue as SE DWI at b = 800 s/mm2 (p = 0.90). CONCLUSION STE DWI has the potential to provide high-SNR, high-CNR imaging of prostate cancer while also enabling reliable ADC mapping. KEY POINTS • Quantitative analysis showed that STE DWI at b = 800 s/mm2is able to achieve simultaneously high CNR, high SNR, and reliable ADC mapping, compared to SE b = 800 s/mm2and SE b = 1500 s/mm2. • Qualitative assessment by three readers showed that STE DWI at b = 800 s/mm2has significantly higher SNR than SE b = 1500 s/mm2. No preference between SE b = 1500 s/mm2and STE b = 800 s/mm2was determined in terms of CNR with no missed lesions were found in both acquisitions. • A single STE DWI acquisition at moderate b value (800-1000 s/mm2) may provide sufficient image quality and quantitative reliability for prostate cancer imaging within a shorter scan time, in place of two DWI acquisitions (one with moderate b value and one with high b value).
Collapse
Affiliation(s)
- Yuxin Zhang
- Department of Medical Physics, University of Wisconsin Madison, Madison, WI, USA
- Department of Radiology, School of Medicine and Public Health, University of Wisconsin Madison, Madison, WI, 53705, USA
| | - Shane A Wells
- Department of Radiology, School of Medicine and Public Health, University of Wisconsin Madison, Madison, WI, 53705, USA
| | - Benjamin L Triche
- Department of Radiology, School of Medicine and Public Health, University of Wisconsin Madison, Madison, WI, 53705, USA
| | - Frederick Kelcz
- Department of Radiology, School of Medicine and Public Health, University of Wisconsin Madison, Madison, WI, 53705, USA
| | - Diego Hernando
- Department of Medical Physics, University of Wisconsin Madison, Madison, WI, USA.
- Department of Radiology, School of Medicine and Public Health, University of Wisconsin Madison, Madison, WI, 53705, USA.
| |
Collapse
|
|
37
|
Cosma I, Tennstedt-Schenk C, Winzler S, Psychogios MN, Pfeil A, Teichgraeber U, Malich A, Papageorgiou I. The role of gadolinium in magnetic resonance imaging for early prostate cancer diagnosis: A diagnostic accuracy study. PLoS One 2019; 14:e0227031. [PMID: 31869380 PMCID: PMC6927639 DOI: 10.1371/journal.pone.0227031] [Citation(s) in RCA: 11] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/30/2019] [Accepted: 12/10/2019] [Indexed: 01/01/2023] Open
Abstract
Objective Prostate lesions detected with multiparametric magnetic resonance imaging (mpMRI) are classified for their malignant potential according to the Prostate Imaging-Reporting And Data System (PI-RADS™2). In this study, we evaluate the diagnostic accuracy of the mpMRI with and without gadolinium, with emphasis on the added diagnostic value of the dynamic contrast enhancement (DCE). Materials and methods The study was retrospective for 286 prostate lesions / 213 eligible patients, n = 116/170, and 49/59% malignant for the peripheral (Pz) and transitional zone (Tz), respectively. A stereotactic MRI-guided prostate biopsy served as the histological ground truth. All patients received a mpMRI with DCE. The influence of DCE in the prediction of malignancy was analyzed by blinded assessment of the imaging protocol without DCE and the DCE separately. Results Significant (CSPca) and insignificant (IPca) prostate cancers were evaluated separately to enhance the potential effects of the DCE in the detection of CSPca. The Receiver Operating Characteristics Area Under Curve (ROC-AUC), sensitivity (Se) and specificity (Spe) of PIRADS-without-DCE in the Pz was 0.70/0.47/0.86 for all cancers (IPca and CSPca merged) and 0.73/0.54/0.82 for CSPca. PIRADS-with-DCE for the same patients showed ROC-AUC/Se/Spe of 0.70/0.49/0.86 for all Pz cancers and 0.69/0.54/0.81 for CSPca in the Pz, respectively, p>0.05 chi-squared test. Similar results for the Tz, AUC/Se/Spe for PIRADS-without-DCE was 0.75/0.61/0.79 all cancers and 0.67/0.54/0.71 for CSPca, not influenced by DCE (0.66/0.47/0.81 for all Tz cancers and 0.61/0.39/0.75 for CSPca in Tz). The added Se and Spe of DCE for the detection of CSPca was 88/34% and 78/33% in the Pz and Tz, respectively. Conclusion DCE showed no significant added diagnostic value and lower specificity for the prediction of CSPca compared to the non-enhanced sequences. Our results support that gadolinium might be omitted without mitigating the diagnostic accuracy of the mpMRI for prostate cancer.
Collapse
Affiliation(s)
- Ilinca Cosma
- Institute of Diagnostic and Interventional Radiology, University Hospital Jena, Jena, Germany
- Institute of Radiology, Suedharz Hospital Nordhausen, Nordhausen, Germany
| | | | - Sven Winzler
- Institute of Radiology, Suedharz Hospital Nordhausen, Nordhausen, Germany
| | - Marios Nikos Psychogios
- Department of Neuroradiology, Clinic of Radiology and Nuclear Medicine, University Hospital Basel, Basel, Switzerland
| | - Alexander Pfeil
- Department of Internal Medicine, University Hospital Jena, Jena, Germany
| | - Ulf Teichgraeber
- Institute of Diagnostic and Interventional Radiology, University Hospital Jena, Jena, Germany
| | - Ansgar Malich
- Institute of Radiology, Suedharz Hospital Nordhausen, Nordhausen, Germany
| | - Ismini Papageorgiou
- Institute of Diagnostic and Interventional Radiology, University Hospital Jena, Jena, Germany
- Institute of Radiology, Suedharz Hospital Nordhausen, Nordhausen, Germany
- * E-mail:
| |
Collapse
|
|
38
|
Ikoma Y, Kishimoto R, Tachibana Y, Omatsu T, Kasuya G, Makishima H, Higashi T, Obata T, Tsuji H. Reference region extraction by clustering for the pharmacokinetic analysis of dynamic contrast-enhanced MRI in prostate cancer. Magn Reson Imaging 2019; 66:185-192. [PMID: 31487532 DOI: 10.1016/j.mri.2019.08.034] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/29/2019] [Revised: 08/13/2019] [Accepted: 08/31/2019] [Indexed: 11/18/2022]
Abstract
PURPOSE Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) measures changes in the concentration of an administered contrast agent to quantitatively evaluate blood circulation in a tumor or normal tissues. This method uses a pharmacokinetic analysis based on the time course of a reference region, such as muscle, rather than arterial input function. However, it is difficult to manually define a homogeneous reference region. In the present study, we developed a method for automatic extraction of the reference region using a clustering algorithm based on a time course pattern for DCE-MRI studies of patients with prostate cancer. METHODS Two feature values related to the shape of the time course were extracted from the time course of all voxels in the DCE-MRI images. Each voxel value of T1-weighted images acquired before administration were also added as anatomical data. Using this three-dimensional feature vector, all voxels were segmented into five clusters by the Gaussian mixture model, and one of these clusters that included the gluteus muscle was selected as the reference region. RESULTS Each region of arterial vessel, muscle, and fat was segmented as a different cluster from the tumor and normal tissues in the prostate. In the extracted reference region, other tissue elements including scattered fat and blood vessels were removed from the muscle region. CONCLUSIONS Our proposed method can automatically extract the reference region using the clustering algorithm with three types of features based on the time course pattern and anatomical data. This method may be useful for evaluating tumor circulatory function in DCE-MRI studies.
Collapse
Affiliation(s)
- Yoko Ikoma
- Department of Molecular Imaging and Theranostics, National Institute of Radiological Sciences, QST, 4-9-1 Anagawa, Inage-ku, Chiba 263-8555, Japan
| | - Riwa Kishimoto
- Department of Molecular Imaging and Theranostics, National Institute of Radiological Sciences, QST, 4-9-1 Anagawa, Inage-ku, Chiba 263-8555, Japan
| | - Yasuhiko Tachibana
- Department of Molecular Imaging and Theranostics, National Institute of Radiological Sciences, QST, 4-9-1 Anagawa, Inage-ku, Chiba 263-8555, Japan
| | - Tokuhiko Omatsu
- Department of Molecular Imaging and Theranostics, National Institute of Radiological Sciences, QST, 4-9-1 Anagawa, Inage-ku, Chiba 263-8555, Japan
| | - Goro Kasuya
- Department of Charged Particle Therapy Research, National Institute of Radiological Sciences, QST, 4-9-1 Anagawa, Inage-ku, Chiba 263-8555, Japan
| | - Hirokazu Makishima
- Department of Charged Particle Therapy Research, National Institute of Radiological Sciences, QST, 4-9-1 Anagawa, Inage-ku, Chiba 263-8555, Japan
| | - Tatsuya Higashi
- Department of Molecular Imaging and Theranostics, National Institute of Radiological Sciences, QST, 4-9-1 Anagawa, Inage-ku, Chiba 263-8555, Japan
| | - Takayuki Obata
- Department of Molecular Imaging and Theranostics, National Institute of Radiological Sciences, QST, 4-9-1 Anagawa, Inage-ku, Chiba 263-8555, Japan.
| | - Hiroshi Tsuji
- Department of Charged Particle Therapy Research, National Institute of Radiological Sciences, QST, 4-9-1 Anagawa, Inage-ku, Chiba 263-8555, Japan
| |
Collapse
|
|
39
|
Abstract
The field of prostate cancer has been the subject of extensive research that has resulted in important discoveries and shaped our appreciation of this disease and its management. Advances in our understanding of the epidemiology, natural history, anatomy, detection, diagnosis, grading, staging, imaging, and management of prostate cancer have changed clinical practice and influenced guideline recommendations. The development of the Gleason score and subsequent modifications enabled accurate prediction of prognosis. Increased anatomical understanding and improved surgical techniques resulted in the development of nerve-sparing surgery for radical prostatectomy. The advent of active surveillance has changed the management of low-risk disease, and chemotherapy and hormonal therapy have improved the outcomes of patients with distant disease. Ongoing research and clinical trials are expected to yield more practice-changing results in the near future.
Collapse
|
|
40
|
Lee CH. Quantitative T2-mapping using MRI for detection of prostate malignancy: a systematic review of the literature. Acta Radiol 2019; 60:1181-1189. [PMID: 30621443 DOI: 10.1177/0284185118820058] [Citation(s) in RCA: 20] [Impact Index Per Article: 3.3] [Reference Citation Analysis] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/18/2022]
Affiliation(s)
- Chau Hung Lee
- 1 Department of Radiology, Charite - Universitätzsmedizin Berlin, Berlin, Germany
- 2 Department of Radiology, Tan Tock Seng Hospital, Singapore
| |
Collapse
|
|
41
|
Gupta RT, Mehta KA, Turkbey B, Verma S. PI‐RADS: Past, present, and future. J Magn Reson Imaging 2019; 52:33-53. [DOI: 10.1002/jmri.26896] [Citation(s) in RCA: 22] [Impact Index Per Article: 3.7] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/30/2019] [Revised: 07/25/2019] [Accepted: 07/26/2019] [Indexed: 12/25/2022] Open
Affiliation(s)
- Rajan T. Gupta
- Department of RadiologyDuke University Medical Center Durham North Carolina USA
- Department of Surgery, Division of Urologic SurgeryDuke University Medical Center Durham North Carolina USA
- Duke Cancer Institute Center for Prostate and Urologic Cancers Durham North Carolina USA
| | - Kurren A. Mehta
- Department of RadiologyDuke University Medical Center Durham North Carolina USA
| | - Baris Turkbey
- National Cancer Institute, Center for Cancer Research Bethesda Maryland USA
| | - Sadhna Verma
- Cincinnati Veterans Hospital, University of Cincinnati Cancer InstituteUniversity of Cincinnati Medical Center Cincinnati Ohio USA
| |
Collapse
|
|
42
|
Chatterjee A, He D, Fan X, Antic T, Jiang Y, Eggener S, Karczmar GS, Oto A. Diagnosis of Prostate Cancer by Use of MRI-Derived Quantitative Risk Maps: A Feasibility Study. AJR Am J Roentgenol 2019; 213:W66-W75. [PMID: 31039019 DOI: 10.2214/ajr.18.20702] [Citation(s) in RCA: 12] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/08/2023]
Abstract
OBJECTIVE. The purpose of this study was to develop a new quantitative image analysis tool for estimating the risk of cancer of the prostate by use of quantitative multiparametric MRI (mpMRI) metrics. MATERIALS AND METHODS. Thirty patients with biopsy-confirmed prostate cancer (PCa) who underwent preoperative 3-T mpMRI were included in the study. Quantitative mpMRI metrics-apparent diffusion coefficient (ADC), T2, and dynamic contrast-enhanced (DCE) signal enhancement rate (α)-were calculated on a voxel-by-voxel basis for the whole prostate and coregistered. A normalized risk value (0-100) for each mpMRI parameter was obtained, with high risk values associated with low T2 and ADC and high signal enhancement rate. The final risk score was calculated as a weighted sum of the risk scores (ADC, 40%; T2, 40%; DCE, 20%). Data from five patients were used as training set to find the threshold for predicting PCa. In the other 25 patients, any region with a minimum of 30 con-joint voxels (≈ 4.8 mm2) with final risk score above the threshold was considered positive for cancer. Lesion-based and sector-based analyses were performed by matching prostatectomyverified malignancy and PCa predicted with the risk analysis tool. RESULTS. The risk map tool had sensitivity of 76.6%, 89.2%, and 100% for detecting all lesions, clinically significant lesions (≥ Gleason 3 + 4), and index lesions, respectively. The sensitivity, specificity, positive predictive value, and negative predictive value for PCa detection for all lesions in the sector-based analysis were 78.9%, 88.5%, 84.4%, and 84.1%, respectively, with an ROC AUC of 0.84. CONCLUSION. The risk analysis tool is effective for detecting clinically significant PCa with reasonable sensitivity and specificity in both peripheral and transition zones.
Collapse
Affiliation(s)
- Aritrick Chatterjee
- 1 Department of Radiology, University of Chicago, 5841 S Maryland Ave, Chicago, IL 60637
| | - Dianning He
- 1 Department of Radiology, University of Chicago, 5841 S Maryland Ave, Chicago, IL 60637
- 2 Sino-Dutch Biomedical and Information Engineering School, Northeastern University, Shenyang, China
| | - Xiaobing Fan
- 1 Department of Radiology, University of Chicago, 5841 S Maryland Ave, Chicago, IL 60637
| | - Tatjana Antic
- 3 Department of Pathology, University of Chicago, Chicago, IL
| | - Yulei Jiang
- 1 Department of Radiology, University of Chicago, 5841 S Maryland Ave, Chicago, IL 60637
| | - Scott Eggener
- 4 Department of Urology, University of Chicago, Chicago, IL
| | - Gregory S Karczmar
- 1 Department of Radiology, University of Chicago, 5841 S Maryland Ave, Chicago, IL 60637
| | - Aytekin Oto
- 1 Department of Radiology, University of Chicago, 5841 S Maryland Ave, Chicago, IL 60637
| |
Collapse
|
|
43
|
Panda A, O’Connor G, Lo WC, Jiang Y, Margevicius S, Schluchter M, Ponsky LE, Gulani V. Targeted Biopsy Validation of Peripheral Zone Prostate Cancer Characterization With Magnetic Resonance Fingerprinting and Diffusion Mapping. Invest Radiol 2019; 54:485-493. [PMID: 30985480 PMCID: PMC6602844 DOI: 10.1097/rli.0000000000000569] [Citation(s) in RCA: 47] [Impact Index Per Article: 7.8] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/08/2023]
Abstract
OBJECTIVE This study aims for targeted biopsy validation of magnetic resonance fingerprinting (MRF) and diffusion mapping for characterizing peripheral zone (PZ) prostate cancer and noncancers. MATERIALS AND METHODS One hundred four PZ lesions in 85 patients who underwent magnetic resonance imaging were retrospectively analyzed with apparent diffusion coefficient (ADC) mapping, MRF, and targeted biopsy (cognitive or in-gantry). A radiologist blinded to pathology drew regions of interest on targeted lesions and visually normal peripheral zone on MRF and ADC maps. Mean T1, T2, and ADC were analyzed using linear mixed models. Generalized estimating equations logistic regression analyses were used to evaluate T1 and T2 relaxometry combined with ADC in differentiating pathologic groups. RESULTS Targeted biopsy revealed 63 cancers (low-grade cancer/Gleason score 6 = 10, clinically significant cancer/Gleason score ≥7 = 53), 15 prostatitis, and 26 negative biopsies. Prostate cancer T1, T2, and ADC (mean ± SD, 1660 ± 270 milliseconds, 56 ± 20 milliseconds, 0.70 × 10 ± 0.24 × 10 mm/s) were significantly lower than prostatitis (mean ± SD, 1730 ± 350 milliseconds, 77 ± 36 milliseconds, 1.00 × 10 ± 0.30 × 10 mm/s) and negative biopsies (mean ± SD, 1810 ± 250 milliseconds, 71 ± 37 milliseconds, 1.00 × 10 ± 0.33 × 10 mm/s). For cancer versus prostatitis, ADC was sensitive and T2 specific with comparable area under curve (AUC; (AUCT2 = 0.71, AUCADC = 0.79, difference between AUCs not significant P = 0.37). T1 + ADC (AUCT1 + ADC = 0.83) provided the best separation between cancer and negative biopsies. Low-grade cancer T2 and ADC (mean ± SD, 75 ± 29 milliseconds, 0.96 × 10 ± 0.34 × 10 mm/s) were significantly higher than clinically significant cancers (mean ± SD, 52 ± 16 milliseconds, 0.65 ± 0.18 × 10 mm/s), and T2 + ADC (AUCT2 + ADC = 0.91) provided the best separation. CONCLUSIONS T1 and T2 relaxometry combined with ADC mapping may be useful for quantitative characterization of prostate cancer grades and differentiating cancer from noncancers for PZ lesions seen on T2-weighted images.
Collapse
Affiliation(s)
- Ananya Panda
- Department of Radiology, Mayo Clinic, Rochester, University Hospitals Cleveland Medical Center, Cleveland, Ohio, USA
| | - Gregory O’Connor
- Department of Case Western University School of Medicine, University Hospitals Cleveland Medical Center, Cleveland, Ohio, USA
| | - Wei-Ching Lo
- Department of Biomedical Engineering, Case Western Reserve University, University Hospitals Cleveland Medical Center, Cleveland, Ohio, USA
| | - Yun Jiang
- Department of Radiology, Case Western Reserve University, University Hospitals Cleveland Medical Center, Cleveland, Ohio, USA
| | - Seunghee Margevicius
- Department of Epidemiology and Biostatistics, Case Western Reserve University, University Hospitals Cleveland Medical Center, Cleveland, Ohio, USA
| | - Mark Schluchter
- Department of Epidemiology and Biostatistics, Case Western Reserve University, University Hospitals Cleveland Medical Center, Cleveland, Ohio, USA
| | - Lee E. Ponsky
- Department of Urology, University Hospitals Cleveland Medical Center, Cleveland, Ohio, USA
| | - Vikas Gulani
- Department of Case Western University School of Medicine, University Hospitals Cleveland Medical Center, Cleveland, Ohio, USA
- Department of Biomedical Engineering, Case Western Reserve University, University Hospitals Cleveland Medical Center, Cleveland, Ohio, USA
- Department of Radiology, University Hospitals Cleveland Medical Center, Cleveland, Ohio, USA
| |
Collapse
|
|
44
|
Al-Mubarak H, Vallatos A, Gallagher L, Birch JL, Gilmour L, Foster JE, Chalmers AJ, Holmes WM. Stacked in-plane histology for quantitative validation of non-invasive imaging biomarkers: Application to an infiltrative brain tumour model. J Neurosci Methods 2019; 326:108372. [PMID: 31348965 DOI: 10.1016/j.jneumeth.2019.108372] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/04/2019] [Revised: 07/20/2019] [Accepted: 07/21/2019] [Indexed: 10/26/2022]
Abstract
BACKGROUND While it is generally agreed that histopathology is the gold standard for assessing non-invasive imaging biomarkers, most validation has been by qualitative visual comparison. To date, the difficulties involved in accurately co-registering histology sections with imaging slices have prevented a voxel-by-voxel assessment of imaging modalities. By contrast with previous studies, which focus on improving the registration algorithms, we have taken the approach of improving the quality of the histological processing and analysis. NEW METHOD To account for imaging slice orientation and thickness, multiple histology sections were cut in the MR imaging plane and averaged to produce stacked in-plane histology (SIH) maps. When combined with intensity sensitive staining this approach gives histopathology maps, which can be used as the gold standard to validate imaging biomarkers. RESULTS We applied this pipeline to a patient-derived mouse model of glioblastoma multiforme (GBM). Increasing the number of stacked histology sections significantly increased SIH measured tumour volume. The SIH technique proposed here resulted in reduced variability of volume measurements and this allowed significant improvements in the quantitative volumetric assessment of multiple MRI modalities. Further, high quality registration enabled a voxel-wise comparison between MRI and histopathology maps. Previous approaches to the validation of imaging biomarkers with histology, have been either qualitative or of limited accuracy. Here we propose a pipeline that allows for a more accurate validation via co-registration with SIH maps, potentially allowing validation in a voxel-wise mode. CONCLUSION This work demonstrates that methodically produced SIH maps facilitate the quantitative histopathologic assessment of imaging biomarkers.
Collapse
Affiliation(s)
- H Al-Mubarak
- Glasgow Experimental MRI Centre, Institute of Neuroscience and Psychology, University of Glasgow, G61 1QH, UK; Department of Physics, College of Science, University of Misan, Iraq.
| | - A Vallatos
- Centre for Clinical Brain Sciences, University of Edinburgh, EH16 4SB, UK.
| | - L Gallagher
- Glasgow Experimental MRI Centre, Institute of Neuroscience and Psychology, University of Glasgow, G61 1QH, UK.
| | - J L Birch
- Wolfson Wohl Translational Cancer Research Centre, Institute of Cancer Sciences University of Glasgow, G61 1QH, UK.
| | - L Gilmour
- Wolfson Wohl Translational Cancer Research Centre, Institute of Cancer Sciences University of Glasgow, G61 1QH, UK.
| | - J E Foster
- Department of Clinical Physics and Bioengineering, Greater Glasgow Health Board and University of Glasgow, B15 2GW, UK.
| | - A J Chalmers
- Wolfson Wohl Translational Cancer Research Centre, Institute of Cancer Sciences University of Glasgow, G61 1QH, UK.
| | - W M Holmes
- Glasgow Experimental MRI Centre, Institute of Neuroscience and Psychology, University of Glasgow, G61 1QH, UK.
| |
Collapse
|
|
45
|
Cristel G, Esposito A, Damascelli A, Briganti A, Ambrosi A, Brembilla G, Brunetti L, Antunes S, Freschi M, Montorsi F, Del Maschio A, De Cobelli F. Can DCE-MRI reduce the number of PI-RADS v.2 false positive findings? Role of quantitative pharmacokinetic parameters in prostate lesions characterization. Eur J Radiol 2019; 118:51-57. [PMID: 31439258 DOI: 10.1016/j.ejrad.2019.07.002] [Citation(s) in RCA: 14] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/18/2019] [Revised: 06/16/2019] [Accepted: 07/01/2019] [Indexed: 12/27/2022]
Abstract
PURPOSE To test the potential impact of pharmacokinetic parameters, derived from DCE-MRI analysis, on the diagnostic performance of PI-RADSv.2 classification in prostate lesions characterization. METHOD Among patients who underwent multiparametric prostate MRI (mpMRI) (January 2016-March 2018) followed by histological evaluation (targeted biopsies/prostatectomy), 103 men were retrospectively selected. For each patient the index lesion was identified and pharmacokinetic parameters (Ktrans, Kep, Ve, Vp) were assessed. MRI diagnostic performance in the detection of significant tumors [Gleason Score (GS)≥7] was assessed, considering PI-RADS≥3 as positive. RESULTS GS ≥ 7 (n = 59) showed higher Ktrans (p < 0.01) and Kep (p = 0.01) compared to GS < 7. At ROC curve analysis, a Ktrans cut-off of 191 × 10-3/min was identified to predict the presence of GS ≥ 7 (AUC:0.75; sensitivity:95%; specificity:61%). Sensitivity and PPV of mpMRI using PI-RADSv.2 were 98% and 61%. Reclassifying PI-RADS≥3 lesions according to Ktrans cut-off, 22 false positives were shifted to true negatives with 3 false negative findings; PPV raised to 79%. Appling Ktrans cut-off to PI-RADS 3 lesions of peripheral zone (n = 18), 12 true negatives, 4 true positives, 2 false positives were identified. CONCLUSIONS Despite its high sensitivity prostate mpMRI generates many false positive cases: Ktrans in addition to PIRADS v.2 seems to improve MRI-PPV and may help in avoiding redundant biopsies.
Collapse
Affiliation(s)
- Giulia Cristel
- Department of Radiology, Experimental Imaging Center, San Raffaele Scientific Institute, via Olgettina 60, 20132 Milan, Italy.
| | - Antonio Esposito
- Department of Radiology, Experimental Imaging Center, San Raffaele Scientific Institute, via Olgettina 60, 20132 Milan, Italy; Vita Salute San Raffaele University, via Olgettina 60, 20132 Milan, Italy
| | - Anna Damascelli
- Department of Radiology, Experimental Imaging Center, San Raffaele Scientific Institute, via Olgettina 60, 20132 Milan, Italy
| | - Alberto Briganti
- Vita Salute San Raffaele University, via Olgettina 60, 20132 Milan, Italy; Department of Urology, San Raffaele Scientific Institute, via Olgettina 60, 20132 Milan, Italy
| | - Alessandro Ambrosi
- Vita Salute San Raffaele University, via Olgettina 60, 20132 Milan, Italy
| | - Giorgio Brembilla
- Department of Radiology, Experimental Imaging Center, San Raffaele Scientific Institute, via Olgettina 60, 20132 Milan, Italy; Vita Salute San Raffaele University, via Olgettina 60, 20132 Milan, Italy
| | - Lisa Brunetti
- Department of Radiology, Experimental Imaging Center, San Raffaele Scientific Institute, via Olgettina 60, 20132 Milan, Italy; Vita Salute San Raffaele University, via Olgettina 60, 20132 Milan, Italy
| | - Sofia Antunes
- Department of Radiology, Experimental Imaging Center, San Raffaele Scientific Institute, via Olgettina 60, 20132 Milan, Italy
| | - Massimo Freschi
- Department of Pathology, San Raffaele Scientific Institute, via Olgettina 60, 20132 Milan, Italy
| | - Francesco Montorsi
- Vita Salute San Raffaele University, via Olgettina 60, 20132 Milan, Italy; Department of Urology, San Raffaele Scientific Institute, via Olgettina 60, 20132 Milan, Italy
| | - Alessandro Del Maschio
- Department of Radiology, Experimental Imaging Center, San Raffaele Scientific Institute, via Olgettina 60, 20132 Milan, Italy; Vita Salute San Raffaele University, via Olgettina 60, 20132 Milan, Italy
| | - Francesco De Cobelli
- Department of Radiology, Experimental Imaging Center, San Raffaele Scientific Institute, via Olgettina 60, 20132 Milan, Italy; Vita Salute San Raffaele University, via Olgettina 60, 20132 Milan, Italy
| |
Collapse
|
|
46
|
Kara D, Fan M, Hamilton J, Griswold M, Seiberlich N, Brown R. Parameter map error due to normal noise and aliasing artifacts in MR fingerprinting. Magn Reson Med 2019; 81:3108-3123. [PMID: 30671999 PMCID: PMC6414267 DOI: 10.1002/mrm.27638] [Citation(s) in RCA: 28] [Impact Index Per Article: 4.7] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/08/2018] [Revised: 10/11/2018] [Accepted: 11/21/2018] [Indexed: 11/10/2022]
Abstract
PURPOSE To introduce a quantitative tool that enables rapid forecasting of T1 and T2 parameter map errors due to normal and aliasing noise as a function of the MR fingerprinting (MRF) sequence, which can be used in sequence optimization. THEORY AND METHODS The variances of normal noise and aliasing artifacts in the collected signal are related to the variances in T1 and T2 maps through derived quality factors. This analytical result is tested against the results of a Monte-Carlo approach for analyzing MRF sequence encoding capability in the presence of aliasing noise, and verified with phantom experiments at 3 T. To further show the utility of our approach, our quality factors are used to find efficient MRF sequences for fewer repetitions. RESULTS Experimental results verify the ability of our quality factors to rapidly assess the efficiency of an MRF sequence in the presence of both normal and aliasing noise. Quality factor assessment of MRF sequences is in agreement with the results of a Monte-Carlo approach. Analysis of MRF parameter map errors from phantom experiments is consistent with the derived quality factors, with T1 (T2 ) data yielding goodness of fit R2 ≥ 0.92 (0.80). In phantom and in vivo experiments, the efficient pulse sequence, determined through quality factor maximization, led to comparable or improved accuracy and precision relative to a longer sequence, demonstrating quality factor utility in MRF sequence design. CONCLUSION The here introduced quality factor framework allows for rapid analysis and optimization of MRF sequence design through T1 and T2 error forecasting.
Collapse
Affiliation(s)
- Danielle Kara
- Physics, Case Western Reserve University, Cleveland, Ohio, United States
| | - Mingdong Fan
- Physics, Case Western Reserve University, Cleveland, Ohio, United States
| | - Jesse Hamilton
- Biomedical Engineering, Case Western Reserve University, Cleveland, Ohio, United States
| | - Mark Griswold
- Physics, Case Western Reserve University, Cleveland, Ohio, United States
- Biomedical Engineering, Case Western Reserve University, Cleveland, Ohio, United States
- Radiology, Case Western Reserve University, Cleveland, Ohio, United States
| | - Nicole Seiberlich
- Biomedical Engineering, Case Western Reserve University, Cleveland, Ohio, United States
- Radiology, Case Western Reserve University, Cleveland, Ohio, United States
| | - Robert Brown
- Physics, Case Western Reserve University, Cleveland, Ohio, United States
| |
Collapse
|
|
47
|
Hambarde P, Talbar SN, Sable N, Mahajan A, Chavan SS, Thakur M. Radiomics for peripheral zone and intra-prostatic urethra segmentation in MR imaging. Biomed Signal Process Control 2019; 51:19-29. [DOI: 10.1016/j.bspc.2019.01.024] [Citation(s) in RCA: 9] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/05/2023]
|
|
48
|
Hameed M, Ganeshan B, Shur J, Mukherjee S, Afaq A, Batura D. The clinical utility of prostate cancer heterogeneity using texture analysis of multiparametric MRI. Int Urol Nephrol 2019; 51:817-824. [PMID: 30929224 DOI: 10.1007/s11255-019-02134-0] [Citation(s) in RCA: 10] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/16/2019] [Accepted: 03/21/2019] [Indexed: 11/28/2022]
Abstract
PURPOSE To determine if multiparametric MRI (mpMRI) derived filtration-histogram based texture analysis (TA) can differentiate between different Gleason scores (GS) and the D'Amico risk in prostate cancer. METHODS We retrospectively studied patients whose pre-operative 1.5T mpMRI had shown a visible tumour and who subsequently underwent radical prostatectomy (RP). Guided by tumour location from the histopathology report, we drew a region of interest around the dominant visible lesion on a single axial slice on the T2, Apparent Diffusion Coefficient (ADC) map and early arterial phase post-contrast T1 image. We then performed TA with a filtration-histogram software (TexRAD -Feedback Medical Ltd, Cambridge, UK). We correlated GS and D'Amico risk with texture using the Spearman's rank correlation test. RESULTS We had 26 RP patients with an MR-visible tumour. Mean of positive pixels (MPP) on ADC showed a significant negative correlation with GS at coarse texture scales. MPP showed a significant negative correlation with GS without filtration and with medium filtration. MRI contrast texture without filtration showed a significant, negative correlation with D'Amico score. MR T2 texture showed a significant, negative correlation with the D'Amico risk, particularly at textures without filtration, medium texture scales and coarse texture scales. CONCLUSION ADC map mpMRI TA correlated negatively with GS, and T2 and post-contrast images with the D'Amico risk score. These associations may allow for better assessment of disease prognosis and a non-invasive method of follow-up for patients on surveillance. Further, identifying clinically significant prostate cancer is essential to reduce harm from over-diagnosis and over-treatment.
Collapse
Affiliation(s)
- Maira Hameed
- Department of Radiology, Imperial College Healthcare NHS Trust, South Wharf Road, London, UK
| | - Balaji Ganeshan
- Institute of Nuclear Medicine, University College London Hospitals NHS Foundation Trust, Euston Road, London, UK
| | - Joshua Shur
- Joint Department of Medical Imaging, University Health Network, Toronto, Canada
| | - Subhabrata Mukherjee
- Department of Urology, Dartford and Gravesham NHS Trust, Darenth Wood Road, Dartford, UK
| | - Asim Afaq
- Institute of Nuclear Medicine, University College London Hospitals NHS Foundation Trust, Euston Road, London, UK
| | - Deepak Batura
- Department of Urology, London North West University Healthcare NHS Trust, Watford Road, London, UK.
| |
Collapse
|
|
49
|
|
|
50
|
Sung K. Modified MR dispersion imaging in prostate dynamic contrast-enhanced MRI. J Magn Reson Imaging 2019; 50:1307-1317. [PMID: 30773769 DOI: 10.1002/jmri.26685] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/23/2018] [Accepted: 02/05/2019] [Indexed: 11/06/2022] Open
Abstract
BACKGROUND An estimation of an intravascular dispersion parameter was previously proposed to improve the overall accuracy and precision of the model parameters, but the high computation complexity can limit its practical usability in prostate dynamic contrast-enhanced MRI (DCE-MRI). PURPOSE To compare and evaluate the model fitting uncertainty and error in the model parameter estimation using different DCE-MRI analysis models and to evaluate the ability of the intravascular dispersion parameter to delineate between noncancerous and cancerous prostate tissue in the transition and peripheral zones. STUDY TYPE Retrospective. POPULATION Fifty-three patients who underwent radical prostatectomy. FIELD STRENGTH/SEQUENCE 3 T/3D RF-spoiled gradient echo sequence. ASSESSMENT The coefficient of variation was used to assess the model fitting uncertainty by adding random noise to the time-concentration curves, and the Akaike information criterion was used to assess the model fitting error. The parametric maps derived from four DCE-MRI analysis models were evaluated by evaluating the delineation between noncancerous tissue and prostate cancer or clinically significant prostate cancer. STATISTICAL TESTS The receiver operating curve analysis was performed to compare the ability to delineate between noncancerous and prostate cancer tissue in the transition and peripheral zones. RESULTS Both MR dispersion imaging (MRDI) and Weinmann analysis models had the maximum coefficient of variation in different tissue types, while the model fitting uncertainty of modified (m)MRDI was similar to the standard Toft model. In mMRDI, the model fitting error was minimum, and the delineation between noncancerous and clinically significant prostate cancer tissue was improved in both transition (area under the curve [AUC] = 0.92) and peripheral zones (AUC = 0.92), in comparison with MRDI (AUC = 0.89 and AUC = 0.85, respectively). DATA CONCLUSION The mMRDI showed promising results in detecting prostate cancer while maintaining a similar model fitting uncertainty. LEVEL OF EVIDENCE 3 Technical Efficacy: Stage 1 J. Magn. Reson. Imaging 2019;50:1307-1317.
Collapse
Affiliation(s)
- Kyunghyun Sung
- Department of Radiological Sciences, UCLA, Los Angeles, California, USA
| |
Collapse
|