• Abdominal
• Artificial intelligence
• Pelvic
• Ultrasound

• Humans
• Artificial Intelligence
• Ultrasonography/methods
• Pelvis/diagnostic imaging
• Abdomen/diagnostic imaging
• Image Interpretation, Computer-Assisted/methods

• HSO2 Fellowship in Digital Oncology
• National Center for Tumor Diseases (NCT) Heidelberg
• Universitätsklinikum Heidelberg (8914)

• artificial intelligence
• attitudes
• perceptions
• qualified radiologist
• trainee radiologist

• AI-augmented EBUS
• deep learning
• deep neural networks
• endobronchial ultrasound
• lymph node classification
• lymph node staging

• 46055500 The Liaison Committee for Education, Research, and Innovation in Central Norway (Samar-beidsorganet)
• The Ministry of Health and Care Services of Norway through the Norwegian National Research Center for Minimally Invasive and Image-Guided Diagnostics and Therapy (MiDT) at St. Olavs hospital, Trondheim, Norway
• contract no. 19/2020 The Norwegian Financial Mechanism 2014-2021 under the project RO- NO2019-0138, 19/2020 "Improving Cancer Diagnostics in Flexible Endoscopy using Artificial Intelligence and Medical Robotics" IDEAR (contract no. 19/2020).

• deep learning
• endometrial receptivity
• nomogram
• recurrent pregnancy loss
• routine examination
• ultrasound

• Deep Learning
• Ultrasonography/methods
• Humans
• Urinary Bladder/diagnostic imaging
• Image Processing, Computer-Assisted/methods

• ARDS
• Convolutional neural network
• Machine learning
• Radiology

• Humans
• Respiratory Distress Syndrome/diagnostic imaging
• Neural Networks, Computer
• Radiography, Thoracic
• Deep Learning
• Intensive Care Units
• Male
• Female
• Pneumonia/diagnostic imaging
• Sensitivity and Specificity
• Middle Aged
• Adult

• Depth features
• Hepatic cystic echinococcosis
• Multiclassification
• Multiple kernel learning
• Texture features
• Ultrasound images

• Humans
• Echinococcosis, Hepatic/diagnostic imaging
• Ultrasonography/methods
• Machine Learning
• Male
• Liver/diagnostic imaging
• Female
• Adult
• Middle Aged
• Support Vector Machine
• Reproducibility of Results
• Algorithms
• Aged
• Image Interpretation, Computer-Assisted/methods

• AI-assisted systems
• Artificial intelligence
• Endoscopic ultrasound
• Pancreas

• Humans
• Endosonography/methods
• Artificial Intelligence
• Pancreas/diagnostic imaging
• Machine Learning
• Deep Learning
• Pancreatic Neoplasms/diagnostic imaging
• Pancreatic Diseases/diagnostic imaging
• Image Interpretation, Computer-Assisted/methods
• Image Processing, Computer-Assisted/methods

• artificial intelligence
• biometry
• deep learning
• gestational age
• quality control
• ultrasound

• Humans
• Ultrasonography, Prenatal/standards
• Ultrasonography, Prenatal/methods
• Pregnancy
• Deep Learning
• Female
• Gestational Age
• Quality Control
• Video Recording
• Biometry/methods
• Pregnancy Trimester, Third
• Pregnancy Trimester, Second

• OPP1191684 Bill and Melinda Gates Foundation
• INV003266 Bill and Melinda Gates Foundation

• COVID-19 detection
• Deep learning
• Feature extraction
• HOG
• Machine learning

• MRI
• XAI
• benchmark
• classification
• dataset
• explainability
• interpretability
• pre-training

• European Research Council
• Bundesministerium für Wirtschaft und Klimaschutz

• Classification
• Deep learning
• Medical image identification
• Transfer learning

• Neural Networks, Computer
• Diagnostic Imaging/methods
• Algorithms
• Image Processing, Computer-Assisted/methods
• Machine Learning

• Abdominal screening
• Classification
• Machine learning
• Ultrasound

• Humans
• Neural Networks, Computer
• Ultrasonography
• Abdomen/diagnostic imaging
• Kidney

• 2296317 Engineering and Physical Sciences Research Council

• CT
• Classification
• Deep learning.
• Denoising
• Pancreatic Cancer
• Segmentation

• Humans
• Positron Emission Tomography Computed Tomography/methods
• Magnetic Resonance Imaging/methods
• Multiparametric Magnetic Resonance Imaging
• Pancreatic Neoplasms/diagnostic imaging

• Artificial intelligence
• Chronic kidney disease
• Deep learning
• Radiomics

• deep clustering
• representation learning
• semi-supervised learning
• ultrasound imaging

• Humans
• Artificial Intelligence
• Neural Networks, Computer
• Ultrasonography/methods
• Image Processing, Computer-Assisted/methods
• Biliary Tract/diagnostic imaging

• Machine learning
• Small datasets
• Space medicine
• Transfer learning

• Artificial Intelligence
• Aerospace Medicine
• Algorithms
• Neural Networks, Computer
• Machine Learning

• BloodNet
• Raman spectroscopy
• TSD
• deep learning
• forensic bioinformatics
• machine learning

• CNN
• COVID-19
• artificial intelligence
• bibliometrics
• ultrasound

The neuro-ocular effects of long-duration spaceflight have been termed Spaceflight Associated Neuro-Ocular Syndrome (SANS) and are a potential challenge for future, human space exploration. The underlying pathogenesis of SANS remains ill-defined, but several emerging translational applications of terrestrial head-mounted, visual assessment technology and machine learning frameworks are being studied for potential use in SANS. To develop such technology requires close consideration of the spaceflight environment which is limited in medical resources and imaging modalities. This austere environment necessitates the utilization of low mass, low footprint technology to build a visual assessment system that is comprehensive, accessible, and efficient. In this paper, we discuss the unique considerations for developing this technology for SANS and translational applications on Earth. Several key limitations observed in the austere spaceflight environment share similarities to barriers to care for underserved areas on Earth. We discuss common terrestrial ophthalmic diseases and how machine learning and visual assessment technology for SANS can help increase screening for early intervention. The foundational developments with this novel system may help protect the visual health of both astronauts and individuals on Earth.

• abdominal injuries/diagnostic imaging
• deep learning
• machine learning
• pediatric trauma
• ultrasonography

• Adolescent
• Child
• Deep Learning
• Emergency Service, Hospital
• Focused Assessment with Sonography for Trauma
• Humans
• Retrospective Studies
• Ultrasonography

• UL1 TR001872 NCATS NIH HHS
• R01 HL149670 NHLBI NIH HHS
• R01 HL150394 NHLBI NIH HHS
• UL1 TR001872 NIH HHS
• K08 HL125945 NHLBI NIH HHS

• Brain imaging
• Convolutional neural network algorithms
• Deep learning
• Imaging neuroscience
• Machine learning
• Transfer learning

• Humans
• Neural Networks, Computer
• Reproducibility of Results
• Retrospective Studies
• Ultrasonography

• 19985 Cancer Research UK

• Cross modality
• Kidney segmentation
• Transfer learning
• Ultrasound imaging

• Datasets as Topic
• Deep Learning
• Humans
• Image Processing, Computer-Assisted/methods
• Kidney/diagnostic imaging
• Tomography, X-Ray Computed
• Ultrasonography

• Convolutional neural network
• Deep learning
• Fine-tuning
• Medical image analysis
• Transfer learning

• Databases, Factual
• Humans
• Machine Learning
• Neural Networks, Computer

• Medizinische Fakultät Mannheim der Universität Heidelberg (8990)

• Deep Residual network
• Dynamic learning
• Fuzzy theory
• MapReduce Model
• Text classification

• Artificial intelligence
• Computer aided diagnosis
• Computer vision
• Deep learning
• Medical image analysis

Objective: Current imaging methods used to examine patients with subacromial impingement syndrome (SIS) are limited by their semi-quantitative nature and their capability of capturing dynamic movements. This study aimed to develop a quantitative analytic model to assess subacromial motions using dynamic ultrasound and to examine their reliability and potential influencing factors.

Method: We included 48 healthy volunteers and examined their subacromial motions with dynamic ultrasound imaging. The parameters were the minimal vertical acromiohumeral distance, rotation radius, and degrees of the humeral head. The generalized estimating equation (GEE) was used to investigate the impact of different shoulder laterality, postures, and motion phases on the outcome.

Result: Using the data of the minimal vertical acromiohumeral distance, the intra-rater and inter-rater reliabilities (intra-class correlation coefficient) were determined as 0.94 and 0.88, respectively. In the GEE analysis, a decrease in the minimal vertical acromiohumeral distance was associated with the abduction phase and full-can posture, with a beta coefficient of −0.02 cm [95% confidence interval (CI), −0.03 to −0.01] and −0.07 cm (95% CI, −0.11 to −0.02), respectively. The abduction phase led to a decrease in the radius of humeral rotation and an increase in the angle of humeral rotation, with a beta coefficient of −1.28 cm (95% CI, −2.16 to −0.40) and 6.60° (95% CI, 3.54–9.67), respectively. A significant negative correlation was observed between the rotation angle and radius of the humeral head and between the rotation angle and the minimal vertical acromiohumeral distance.

Conclusion: Quantitative analysis of dynamic ultrasound imaging enables the delineation of subacromial motion with good reliability. The vertical acromiohumeral distance is the lowest in the abduction phase and full-can posture, and the rotation angle of the humeral head has the potential to serve as a new parameter for the evaluation of SIS.

• CT scanning.
• Deep learning
• DenseNet diagnosis
• ResNet
• intracranial hemorrhage
• transfer learning

• Deep Learning
• Humans
• Intracranial Hemorrhages/diagnostic imaging
• Sensitivity and Specificity
• Tomography, X-Ray Computed/methods

• Artificial intelligence
• Bone age
• Deep learning
• Quality
• Safety

• Colorectal cancer
• deep transfer learning
• lymph node
• metastasis

• Colorectal Neoplasms/diagnosis
• Colorectal Neoplasms/genetics
• Colorectal Neoplasms/pathology
• Deep Learning
• Diagnosis, Computer-Assisted
• Humans
• Lymph Nodes/pathology
• Lymphatic Metastasis/genetics
• Lymphatic Metastasis/pathology
• Neoplasm Staging

Increased use of deep learning (DL) in medical imaging diagnoses has led to more frequent use of 10-fold cross-validation (10-CV) for the evaluation of the performance of DL. To eliminate some of the (10-fold) repetitive processing in 10-CV, we proposed a “generalized fitting method in conjunction with every possible coalition of N-combinations (G-EPOC)”, to estimate the range of the mean accuracy of 10-CV using less than 10 results of 10-CV.

G-EPOC was executed as follows. We first provided (2N-1) coalition subsets using a specified N, which was 9 or less, out of 10 result datasets of 10-CV. We then obtained the estimation range of the accuracy by applying those subsets to the distribution fitting twice using a combination of normal, binominal, or Poisson distributions. Using datasets of 10-CVs acquired from the practical detection task of the appendicitis on CT by DL, we scored the estimation success rates if the range provided by G-EPOC included the true accuracy.

G-EPOC successfully estimated the range of the mean accuracy by 10-CV at over 95% rates for datasets with N assigned as 2 to 9.

G-EPOC will help lessen the consumption of time and computer resources in the development of computerbased diagnoses in medical imaging and could become an option for the selection of a reasonable K value in K-CV.

• appendicitis
• computer simulation
• cross validation
• learning curve
• machine learning
• neural networks (computer)

Background: The use of focused assessment with sonography in trauma (FAST) enables clinicians to rapidly screen for injury at the bedsides of patients. Pre-hospital FAST improves diagnostic accuracy and streamlines patient care, leading to dispositions to appropriate treatment centers. In this study, we determine the accuracy of artificial intelligence model-assisted free-fluid detection in FAST examinations, and subsequently establish an automated feedback system, which can help inexperienced sonographers improve their interpretation ability and image acquisition skills.

Methods: This is a single-center study of patients admitted to the emergency room from January 2020 to March 2021. We collected 324 patient records for the training model, 36 patient records for validation, and another 36 patient records for testing. We balanced positive and negative Morison's pouch free-fluid detection groups in a 1:1 ratio. The deep learning (DL) model Residual Networks 50-Version 2 (ResNet50-V2) was used for training and validation.

Results: The accuracy, sensitivity, and specificity of the model performance for ascites prediction were 0.961, 0.976, and 0.947, respectively, in the validation set and 0.967, 0.985, and 0.913, respectively, in the test set. Regarding feedback prediction, the model correctly classified qualified and non-qualified images with an accuracy of 0.941 in both the validation and test sets.

Conclusions: The DL algorithm in ResNet50-V2 is able to detect free fluid in Morison's pouch with high accuracy. The automated feedback and instruction system could help inexperienced sonographers improve their interpretation ability and image acquisition skills.

• FAST
• Morison pouch
• ascites
• deep learning
• hemoperitoneum
• trauma

• Algorithms
• Emergency Nursing
• Humans
• Neural Networks, Computer

Carotid plaque echogenicity in ultrasound images has been found to be closely correlated with the risk of stroke in atherosclerotic patients. The automatic and accurate classification of carotid plaque echogenicity is of great significance for clinically estimating the stability of carotid plaques and predicting cardiovascular events. Existing convolutional neural networks (CNNs) can provide an automatic carotid plaque echogenicity classification; however, they require a fixed-size input image, while the carotid plaques are of varying sizes. Although cropping and scaling the input carotid plaque images is promising, it will cause content loss or distortion and hence reduce the classification accuracy. In this study, we redesign the spatial pyramid pooling (SPP) and propose multilevel strip pooling (MSP) for the automatic and accurate classification of carotid plaque echogenicity in the longitudinal section. The proposed MSP module can accept arbitrarily sized carotid plaques as input and capture a long-range informative context to improve the accuracy of classification. In our experiments, we implement an MSP-based CNN by using the visual geometry group (VGG) network as the backbone. A total of 1463 carotid plaques (335 echo-rich plaques, 405 intermediate plaques, and 723 echolucent plaques) were collected from Zhongnan Hospital of Wuhan University. The 5-fold cross-validation results show that the proposed MSP-based VGGNet achieves a sensitivity of 92.1%, specificity of 95.6%, accuracy of 92.1%, and F1-score of 92.1%. These results demonstrate that our approach provides a way to enhance the applicability of CNN by enabling the acceptance of arbitrary input sizes and improving the classification accuracy of carotid plaque echogenicity, which has a great potential for an efficient and objective risk assessment of carotid plaques in the clinic.

• Artificial intelligence
• Cervical cancer screening
• Deep learning
• Hybrid transfer learning
• Machine learning
• Medical image classification
• Transfer learning

• NLP
• Privacy-preserving
• cancer pathology reports
• information extraction
• multi-task CNN
• transfer learning

• HHSN261201800013I NCI NIH HHS
• P30 CA177558 NCI NIH HHS

• Deep learning
• HER2 molecular marker
• Image analysis
• Immunohistochemical (IHC) analysis
• Transfer learning

• Breast Neoplasms/diagnostic imaging
• Female
• Humans
• Immunohistochemistry
• Machine Learning
• Receptor, ErbB-2

• Acute ischemic stroke
• Computed tomography
• Convolutional neural networks

Artificial intelligence (AI), particularly the deep learning technology, have been proven influential to radiology in the recent decade. Its ability in image classification, segmentation, detection and reconstruction tasks have substantially assisted diagnostic radiology, and has even been viewed as having the potential to perform better than radiologists in some tasks. Gastrointestinal radiology, an important subspecialty dealing with complex anatomy and various modalities including endoscopy, have especially attracted the attention of AI researchers and engineers worldwide. Consequently, recently many tools have been developed for lesion detection and image construction in gastrointestinal radiology, particularly in the fields for which public databases are available, such as diagnostic abdominal magnetic resonance imaging (MRI) and computed tomography (CT). This review will provide a framework for understanding recent advancements of AI in gastrointestinal radiology, with a special focus on hepatic and pancreatobiliary diagnostic radiology with MRI and CT. For fields where AI is less developed, this review will also explain the difficulty in AI model training and possible strategies to overcome the technical issues. The authors’ insights of possible future development will be addressed in the last section.

• Artificial intelligence
• Deep learning
• Image diagnosis
• Radiology
• Magnetic resonance imaging
• Computed tomography

Point-of-care ultrasound (POCUS), realized by recent developments in portable ultrasound imaging systems for prompt diagnosis and treatment, has become a major tool in accidents or emergencies. Concomitantly, the number of untrained/unskilled staff not familiar with the operation of the ultrasound system for diagnosis is increasing. By providing an imaging guide to assist clinical decisions and support diagnosis, the risk brought by inexperienced users can be managed. Recently, deep learning has been employed to guide users in ultrasound scanning and diagnosis. However, in a cloud-based ultrasonic artificial intelligence system, the use of POCUS is limited due to information security, network integrity, and significant energy consumption. To address this, we propose (1) a structure that simultaneously provides ultrasound imaging and a mobile device-based ultrasound image guide using deep learning, and (2) a reverse scan conversion (RSC) method for building an ultrasound training dataset to increase the accuracy of the deep learning model. Experimental results show that the proposed structure can achieve ultrasound imaging and deep learning simultaneously at a maximum rate of 42.9 frames per second, and that the RSC method improves the image classification accuracy by more than 3%.

• classification
• mobile system
• on-device AI
• point-of-care
• portable ultrasound