This study introduces a novel deep learning approach aimed at accurately classifying Gallbladder Cancer (GBC) into benign, malignant, and normal categories using ultrasound images from the challenging GBC USG (GBCU) dataset. The proposed methodology enhances image quality and specifies gallbladder wall boundaries by employing sophisticated image processing techniques like median filtering and contrast-limited adaptive histogram equalization. Unlike traditional convolutional neural networks, which struggle with complex spatial patterns, the proposed transformer-based model, GBC Horizontal-Vertical Transformer (GBCHV), incorporates a GBCHV-Trans block with self-attention mechanisms. In order to make the model anatomy-aware, the square-shaped input patches of the transformer are transformed into horizontal and vertical strips to obtain distinctive spatial relationships within gallbladder tissues. The novelty of this model lies in its anatomy-aware mechanism, which employs horizontal-vertical strip transformations to depict spatial relationships and complex anatomical features of the gallbladder more accurately. The proposed model achieved an overall diagnostic accuracy of 96.21% by performing an ablation study. A performance comparison between the proposed model and seven transfer learning models is further conducted, where the proposed model consistently outperformed the transfer learning models, showcasing its superior accuracy and robustness. Moreover, the decision-making process of the proposed model is further explained visually through the utilization of Gradient-weighted Class Activation Mapping (Grad-CAM). With the integration of advanced deep learning and image processing techniques, the GBCHV-Trans model offers a promising solution for precise and early-stage classification of GBC, surpassing conventional methods with superior accuracy and diagnostic efficacy.

Accurate and precise identification of cholelithiasis is essential for saving the lives of millions of people worldwide. Although several computer-aided cholelithiasis diagnosis approaches have been introduced in the literature, their use is limited because Convolutional Neural Network (CNN) models are black box in nature. Therefore, a novel approach for cholelithiasis classification using custom CNN with post-hoc model explanation is proposed. This paper presents multiple contributions. First, a custom CNN architecture is proposed to classify and predict cholelithiasis from ultrasound image. Second, a modified deep convolutional generative adversarial network is proposed to produce synthetic ultrasound images for better model generalization. Third, a hybrid visual explanation method is proposed by combining gradient-weighted class activation with local interpretable model agnostic explanation to generate a visual explanation using a heatmap. Fourth, an exhaustive performance analysis of the proposed approach on ultrasound images collected from three different Indian hospitals is presented to showcase its efficacy for computer-aided cholelithiasis diagnosis. Fifth, a team of radiologists evaluates and validates the prediction and respective visual explanations made using the proposed approach. The results reveal that the proposed cholelithiasis classification approach beats the performance of state-of-the-art pre-trained CNN and Vision Transformer models. The heatmap generated through the proposed hybrid explanation method offers detailed visual explanations to enhance transparency and trustworthiness in the medical domain.

Gallbladder cancer (GBC) is the most common malignant tumor in the biliary system, characterized by high malignancy, aggressiveness, and poor prognosis. Early diagnosis holds paramount importance in ameliorating therapeutic outcomes. Presently, the clinical diagnosis of GBC primarily relies on clinical-radiological-pathological approach. However, there remains a potential for missed diagnosis and misdiagnose in the realm of clinical practice. We firstly analyzed the blood-based biomarkers, such as carcinoembryonic antigen and carbohydrate antigen 19-9. Subsequently, we evaluated the diagnostic performance of various imaging modalities, including ultrasound (US), endoscopic ultrasound (EUS), computed tomography (CT), magnetic resonance imaging (MRI), positron emission tomography/computed tomography (PET/CT) and pathological examination, emphasizing their strengths and limitations in detecting early-stage GBC. Furthermore, we explored the potential of emerging technologies, particularly artificial intelligence (AI) and liquid biopsy, to revolutionize GBC diagnosis. AI algorithms have demonstrated improved image analysis capabilities, while liquid biopsy offers the promise of non-invasive and real-time monitoring. However, the translation of these advancements into clinical practice necessitates further validation and standardization. The review highlighted the advantages and limitations of current diagnostic approaches and underscored the need for innovative strategies to enhance diagnostic accuracy of GBC. In addition, we emphasized the importance of multidisciplinary collaboration to improve early diagnosis of GBC and ultimately patient outcomes. This review endeavoured to impart fresh perspectives and insights into the early diagnosis of GBC.

Medical image segmentation and classification are two of the most key steps in computer-aided clinical diagnosis. The region of interest were usually segmented in a proper manner to extract useful features for further disease classification. However, these methods are computationally complex and time-consuming. In this paper, we proposed a one-stage multi-task attention network (MTANet) which efficiently classifies objects in an image while generating a high-quality segmentation mask for each medical object. A reverse addition attention module was designed in the segmentation task to fusion areas in global map and boundary cues in high-resolution features, and an attention bottleneck module was used in the classification task for image feature and clinical feature fusion. We evaluated the performance of MTANet with CNN-based and transformer-based architectures across three imaging modalities for different tasks: CVC-ClinicDB dataset for polyp segmentation, ISIC-2018 dataset for skin lesion segmentation, and our private ultrasound dataset for liver tumor segmentation and classification. Our proposed model outperformed state-of-the-art models on all three datasets and was superior to all 25 radiologists for liver tumor diagnosis.

Accurately diagnosing gallbladder polyps (GBPs) is important to avoid misdiagnosis and overtreatment.

To evaluate the efficacy of a deep learning model and the accuracy of a computer-aided diagnosis by physicians for diagnosing GBPs.

This retrospective cohort study was conducted from January 2006 to September 2021, and 3,754 images from 263 patients were analyzed. The outcome of this study was the efficacy of the developed deep learning model in discriminating neoplastic GBPs (NGBPs) from non-NGBPs and to evaluate the accuracy of a computer-aided diagnosis with that made by physicians.

The efficacy of discriminating NGBPs from non- NGBPs using deep learning was 0.944 (accuracy, 0.858; sensitivity, 0.856; specificity, 0.861). The accuracy of an unassisted diagnosis of GBP was 0.634, and that of a computer-aided diagnosis was 0.785 (p<0.001). There were no significant differences in the accuracy of a computer-aided diagnosis between experienced (0.835) and inexperienced (0.772) physicians (p = 0.251). A computer-aided diagnosis significantly assisted inexperienced physicians (0.772 vs. 0.614; p < 0.001) but not experienced physicians.

Deep learning-based models discriminate NGBPs from non- NGBPs with excellent accuracy. As ancillary diagnostic tools, they may assist inexperienced physicians in improving their diagnostic accuracy.

Multimodal medical fusion images have been widely used in clinical medicine, computer-aided diagnosis and other fields. However, the existing multimodal medical image fusion algorithms generally have shortcomings such as complex calculations, blurred details and poor adaptability. To solve this problem, we propose a cascaded dense residual network and use it for grayscale and pseudocolor medical image fusion.

The cascaded dense residual network uses a multiscale dense network and a residual network as the basic network architecture, and a multilevel converged network is obtained through cascade. The cascaded dense residual network contains 3 networks, the first-level network inputs two images with different modalities to obtain a fused Image 1, the second-level network uses fused Image 1 as the input image to obtain fused Image 2 and the third-level network uses fused Image 2 as the input image to obtain fused Image 3. The multimodal medical image is trained through each level of the network, and the output fusion image is enhanced step-by-step.

As the number of networks increases, the fusion image becomes increasingly clearer. Through numerous fusion experiments, the fused images of the proposed algorithm have higher edge strength, richer details, and better performance in the objective indicators than the reference algorithms.

Compared with the reference algorithms, the proposed algorithm has better original information, higher edge strength, richer details and an improvement of the four objective SF, AG, MZ and EN indicator metrics.

We propose a novel deep neural network architecture to learn interpretable representation for medical image analysis. Our architecture generates a global attention for region of interest, and then learns bag of words style deep feature embeddings with local attention. The global, and local feature maps are combined using a contemporary transformer architecture for highly accurate Gallbladder Cancer (GBC) detection from Ultrasound (USG) images. Our experiments indicate that the detection accuracy of our model beats even human radiologists, and advocates its use as the second reader for GBC diagnosis. Bag of words embeddings allow our model to be probed for generating interpretable explanations for GBC detection consistent with the ones reported in medical literature. We show that the proposed model not only helps understand decisions of neural network models but also aids in discovery of new visual features relevant to the diagnosis of GBC. Source-code is available at https://github.com/sbasu276/RadFormer.

The World Federation of Ultrasound in Medicine and Biology (WFUMB) is addressing the issue of incidental findings with a series of position papers to give advice on characterization and management. The biliary system (gallbladder and biliary tree) is the third most frequent site for incidental findings. This first part of the position paper on incidental findings of the biliary system is related to general aspects, gallbladder polyps and other incidental findings of the gallbladder wall. Available evidence on prevalence, diagnostic work-up, malignancy risk, follow-up and treatment is summarized with a special focus on ultrasound techniques. Multiparametric ultrasound features of gallbladder polyps and other incidentally detected gallbladder wall pathologies are described, and their inclusion in assessment of malignancy risk and decision- making on further management is suggested.

Colorectal cancer (CRC) is currently one of the main cancers world-wide, with a high incidence in the elderly. In the diagnosis of CRC, endorectal ultrasound plays an important role in judging benign and early malignant tumors. However, malignant tumors in the early-stage are not easy to identify visually and experts usually seek help from multi-view images, which increases the workload and also exists a certain probability of misdiagnosis. In recent years, with the widespread use of deep learning methods in the analysis of medical images, it becomes necessary to design an effective computer-aided diagnosis (CAD) system of CRC based on multi-view endorectal ultrasound images.

In this study, we proposed a CAD system for judging benign and early malignant colorectal tumors, and constructed the first multi-view ultrasound image dataset of CRC to validate our algorithm. Our system is an end-to-end model based on a deep neural network (DNN) which includes a feature extraction module based on dense blocks, a multi-view fusion module, and a Multi-Layer Perception-based classifier. A center loss was used for the first time in CAD tasks, to optimize our model.

On the constructed dataset, the proposed system surpasses expert diagnosis in accuracy, sensitivity, specificity, and F1-score. Compared with the popular deep classification networks and other CAD methods, the algorithm has reached the best performance. Comparative experiments using different feature extraction methods, different view fusion strategies, and different classifiers verify the effectiveness of each part of the algorithm.

We propose a CAD system for judging benign and early malignant colorectal tumors based on DNN, which combines information of ultrasound images from different views for comprehension. On the first CRC multi-view ultrasound image dataset which we constructed, our method outperforms expert diagnosis results and all other methods, and the effectiveness of each part of the system has been verified. Our system has application value in future medical practice on early diagnosis of CRC.

To automatically recognize polyps of enteroscopy images and avoid pathological change, a novel Joint-Net has been proposed.

The left half of the Joint-Net is constructed by transfer learning VGG16 and its right half is deepened based on the U-Net. In the previous two skip connections, a 3 × 3 convolution layer is added and the original two convolutions are replaced by the identity blocks. To connect the left and the right half part, the asymmetric convolution layer is used. In the output, the loophole-like structure is used.

The enteroscopy images were obtained in Changhai Hospital of Shanghai. The mean values of Dice and intersection over union were 90.05% and 82.71%. The classification accuracy of normal images and polyp images was 93.50%.

The experiments show that the Joint-Net can segment and recognize the polyps successfully.