UNASSIGNED: It is challenging to accurately distinguish atypical endometrial hyperplasia (AEH) and endometrial cancer (EC) under routine transvaginal ultrasonic (TVU) detection. Our research aims to use the few-shot learning (FSL) method to identify non-atypical endometrial hyperplasia (NAEH), AEH, and EC based on limited TVU images.
UNASSIGNED: The TVU images of pathologically confirmed NAEH, AEH, and EC patients (n = 33 per class) were split into the support set (SS, n = 3 per class) and the query set (QS, n = 30 per class). Next, we used dual pretrained ResNet50 V2 which pretrained on ImageNet first and then on extra collected TVU images to extract 1*64 eigenvectors from the TVU images in SS and QS. Then, the Euclidean distances were calculated between each TVU image in QS and nine TVU images of SS. Finally, the k-nearest neighbor (KNN) algorithm was used to diagnose the TVU images in QS.
UNASSIGNED: The overall accuracy and macro precision of the proposed FSL model in QS were 0.878 and 0.882 respectively, superior to the automated machine learning models, traditional ResNet50 V2 model, junior sonographer, and senior sonographer. When identifying EC, the proposed FSL model achieved the highest precision of 0.964, the highest recall of 0.900, and the highest F1-score of 0.931.
UNASSIGNED: The proposed FSL model combining dual pretrained ResNet50 V2 eigenvectors extractor and KNN classifier presented well in identifying NAEH, AEH, and EC patients with limited TVU images, showing potential in the application of computer-aided disease diagnosis.

Deep learning has been widely used in ultrasound image analysis, and it also benefits kidney ultrasound interpretation and diagnosis. However, the importance of ultrasound image resolution often goes overlooked within deep learning methodologies. In this study, we integrate the ultrasound image resolution into a convolutional neural network and explore the effect of the resolution on diagnosis of kidney tumors. In the process of integrating the image resolution information, we propose two different approaches to narrow the semantic gap between the features extracted by the neural network and the resolution features. In the first approach, the resolution is directly concatenated with the features extracted by the neural network. In the second approach, the features extracted by the neural network are first dimensionally reduced and then combined with the resolution features to form new composite features. We compare these two approaches incorporating the resolution with the method without incorporating the resolution on a kidney tumor dataset of 926 images consisting of 211 images of benign kidney tumors and 715 images of malignant kidney tumors. The area under the receiver operating characteristic curve (AUC) of the method without incorporating the resolution is 0.8665, and the AUCs of the two approaches incorporating the resolution are 0.8926 (P < 0.0001) and 0.9135 (P < 0.0001) respectively. This study has established end-to-end kidney tumor classification systems and has demonstrated the benefits of integrating image resolution, showing that incorporating image resolution into neural networks can more accurately distinguish between malignant and benign kidney tumors in ultrasound images.

Ultrasound images are susceptible to various forms of quality degradation that negatively impact diagnosis. Common degradations include speckle noise, Gaussian noise, salt and pepper noise, and blurring. This research proposes an accurate ultrasound image denoising strategy based on firstly detecting the noise type, then, suitable denoising methods can be applied for each corruption. The technique depends on convolutional neural networks to categorize the type of noise affecting an input ultrasound image. Pre-trained convolutional neural network models including GoogleNet, VGG-19, AlexNet and AlexNet-support vector machine (SVM) are developed and trained to perform this classification. A dataset of 782 numerically generated ultrasound images across different diseases and noise types is utilized for model training and evaluation. Results show AlexNet-SVM achieves the highest accuracy of 99.2% in classifying noise types. The results indicate that, the present technique is considered one of the top-performing models is then applied to real ultrasound images with different noise corruptions to demonstrate efficacy of the proposed detect-then-denoise system. RESEARCH HIGHLIGHTS: Proposes an accurate ultrasound image denoising strategy based on detecting noise type first. Uses pre-trained convolutional neural networks to categorize noise type in input images. Evaluates GoogleNet, VGG-19, AlexNet, and AlexNet-support vector machine (SVM) models on a dataset of 782 synthetic ultrasound images. AlexNet-SVM achieves highest accuracy of 99.2% in classifying noise types. Demonstrates efficacy of the proposed detect-then-denoise system on real ultrasound images.

BACKGROUND: Collision tumor are neoplasms, including two histologically distinct tumors that coexist in the same mass without histological admixture. The incidence of collision tumor is low and is rare clinically.
OBJECTIVE: To investigate ultrasound images and application of ovarian-adnexal reporting and data system (O-RADS) to evaluate the risk and pathological characteristics of ovarian collision tumor.
METHODS: This study retrospectively analyzed 17 cases of ovarian collision tumor diagnosed pathologically from January 2020 to December 2023. All clinical features, ultrasound images and histopathological features were collected and analyzed. The O-RADS score was used for classification. The O-RADS score was determined by two senior doctors in the gynecological ultrasound group. Lesions with O-RADS score of 1-3 were classified as benign tumors, and lesions with O-RADS score of 4 or 5 were classified as malignant tumors.
RESULTS: There were 17 collision tumors detected in 16 of 6274 patients who underwent gynecological surgery. The average age of 17 women with ovarian collision tumor was 36.7 years (range 20-68 years), in whom, one occurred bilaterally and the rest occurred unilaterally. The average tumor diameter was 10 cm, of which three were 2-5 cm, 11 were 5-10 cm, and three were > 10 cm. Five (29.4%) tumors with O-RADS score 3 were endometriotic cysts with fibroma/serous cystadenoma, and unilocular or multilocular cysts contained a small number of parenchymal components. Eleven (64.7%) tumors had an O-RADS score of 4, including two in category 4A, six in category 4B, and three in category 4C; all of which were multilocular cystic tumors with solid components or multiple papillary components. One (5.9%) tumor had an O-RADS score of 5. This case was a solid mass, and a small amount of pelvic effusion was detected under ultrasound. The pathology was high-grade serous cystic cancer combined with cystic mature teratoma. There were nine (52.9%) tumors with elevated serum carbohydrate antigen (CA)125 and two (11.8%) with elevated serum CA19-9. Histological and pathological results showed that epithelial-cell-derived tumors combined with other tumors were the most common, which was different from previous results.
CONCLUSIONS: The ultrasound images of ovarian collision tumor have certain specificity, but diagnosis by preoperative ultrasound is difficult. The combination of epithelial and mesenchymal cell tumors is one of the most common types of ovarian collision tumor. The O-RADS score of ovarian collision tumor is mostly ≥ 4, which can sensitively detect malignant tumors.

Objective.Automated detection and segmentation of breast masses in ultrasound images are critical for breast cancer diagnosis, but remain challenging due to limited image quality and complex breast tissues. This study aims to develop a deep learning-based method that enables accurate breast mass detection and segmentation in ultrasound images.Approach.A novel convolutional neural network-based framework that combines the You Only Look Once (YOLO) v5 network and the Global-Local (GOLO) strategy was developed. First, YOLOv5 was applied to locate the mass regions of interest (ROIs). Second, a Global Local-Connected Multi-Scale Selection (GOLO-CMSS) network was developed to segment the masses. The GOLO-CMSS operated on both the entire images globally and mass ROIs locally, and then integrated the two branches for a final segmentation output. Particularly, in global branch, CMSS applied Multi-Scale Selection (MSS) modules to automatically adjust the receptive fields, and Multi-Input (MLI) modules to enable fusion of shallow and deep features at different resolutions. The USTC dataset containing 28 477 breast ultrasound images was collected for training and test. The proposed method was also tested on three public datasets, UDIAT, BUSI and TUH. The segmentation performance of GOLO-CMSS was compared with other networks and three experienced radiologists.Main results.YOLOv5 outperformed other detection models with average precisions of 99.41%, 95.15%, 93.69% and 96.42% on the USTC, UDIAT, BUSI and TUH datasets, respectively. The proposed GOLO-CMSS showed superior segmentation performance over other state-of-the-art networks, with Dice similarity coefficients (DSCs) of 93.19%, 88.56%, 87.58% and 90.37% on the USTC, UDIAT, BUSI and TUH datasets, respectively. The mean DSC between GOLO-CMSS and each radiologist was significantly better than that between radiologists (p< 0.001).Significance.Our proposed method can accurately detect and segment breast masses with a decent performance comparable to radiologists, highlighting its great potential for clinical implementation in breast ultrasound examination.

The aim of this study is to propose a new diagnostic model based on \"segmentation + classification\" to improve the routine screening of Thyroid nodule ultrasonography by utilizing the key domain knowledge of medical diagnostic tasks. A Multi-scale segmentation network based on a pyramidal pooling structure of multi-parallel void spaces is proposed. First, in the segmentation network, the exact information of the underlying feature space is obtained by an Attention Gate. Second, the inflated convolutional part of Atrous Spatial Pyramid Pooling (ASPP) is cascaded for multiple downsampling. Finally, a three-branch classification network combined with expert knowledge is designed, drawing on doctors\' clinical diagnosis experience, to extract features from the original image of the nodule, the regional image of the nodule, and the edge image of the nodule, respectively, and to improve the classification accuracy of the model by utilizing the Coordinate attention (CA) mechanism and cross-level feature fusion. The Multi-scale segmentation network achieves 94.27%, 93.90% and 88.85% of mean precision (mPA), Dice value (Dice) and mean joint intersection (MIoU), respectively, and the accuracy, specificity and sensitivity of the classification network reaches 86.07%, 81.34% and 90.19%, respectively. Comparison tests show that this method outperforms the U-Net, AGU-Net and DeepLab V3+ classical models as well as the nnU-Net, Swin UNetr and MedFormer models that have emerged in recent years. This algorithm, as an auxiliary diagnostic tool, can help physicians more accurately assess the benign or malignant nature of Thyroid nodules. It can provide objective quantitative indicators, reduce the bias of subjective judgment, and improve the consistency and accuracy of diagnosis. Codes and models are available at https://github.com/enheliang/Thyroid-Segmentation-Network.git.

BACKGROUND: Breast cancer is the most common cancer among women, and ultrasound is a usual tool for early screening. Nowadays, deep learning technique is applied as an auxiliary tool to provide the predictive results for doctors to decide whether to make further examinations or treatments. This study aimed to develop a hybrid learning approach for breast ultrasound classification by extracting more potential features from local and multi-center ultrasound data.
METHODS: We proposed a hybrid learning approach to classify the breast tumors into benign and malignant. Three multi-center datasets (BUSI, BUS, OASBUD) were used to pretrain a model by federated learning, then every dataset was fine-tuned at local. The proposed model consisted of a convolutional neural network (CNN) and a graph neural network (GNN), aiming to extract features from images at a spatial level and from graphs at a geometric level. The input images are small-sized and free from pixel-level labels, and the input graphs are generated automatically in an unsupervised manner, which saves the costs of labor and memory space.
RESULTS: The classification AUCROC of our proposed method is 0.911, 0.871 and 0.767 for BUSI, BUS and OASBUD. The balanced accuracy is 87.6%, 85.2% and 61.4% respectively. The results show that our method outperforms conventional methods.
CONCLUSIONS: Our hybrid approach can learn the inter-feature among multi-center data and the intra-feature of local data. It shows potential in aiding doctors for breast tumor classification in ultrasound at an early stage.

One of the most dangerous conditions in clinical practice is breast cancer because it affects the entire life of women in recent days. Nevertheless, the existing techniques for diagnosing breast cancer are complicated, expensive, and inaccurate. Many trans-disciplinary and computerized systems are recently created to prevent human errors in both quantification and diagnosis. Ultrasonography is a crucial imaging technique for cancer detection. Therefore, it is essential to develop a system that enables the healthcare sector to rapidly and effectively detect breast cancer. Due to its benefits in predicting crucial feature identification from complicated breast cancer datasets, machine learning is widely employed in the categorization of breast cancer patterns. The performance of machine learning models is limited by the absence of a successful feature enhancement strategy. There are a few issues that need to be handled with the traditional breast cancer detection method. Thus, a novel breast cancer detection model is designed based on machine learning approaches and employing ultrasonic images. At first, ultrasound images utilized for the analysis is acquired from the benchmark resources and offered as the input to preprocessing phase. The images are preprocessed by utilizing a filtering and contrast enhancement approach and attained the preprocessed image. Then, the preprocessed images are subjected to the segmentation phase. In this phase, segmentation is performed by employing Fuzzy C-Means, active counter, and watershed algorithm and also attained the segmented images. Later, the segmented images are provided to the pixel selection phase. Here, the pixels are selected by the developed hybrid model Conglomerated Aphid with Galactic Swarm Optimization (CAGSO) to attain the final segmented pixels. Then, the selected segmented pixel is fed in to feature extraction phase for attaining the shape features and the textual features. Further, the acquired features are offered to the optimal weighted feature selection phase, and also their weights are tuned tune by the developed CAGSO. Finally, the optimal weighted features are offered to the breast cancer detection phase. Finally, the developed breast cancer detection model secured an enhanced performance rate than the classical approaches throughout the experimental analysis.

Congenital heart defects (CHD) are one of the serious problems that arise during pregnancy. Early CHD detection reduces death rates and morbidity but is hampered by the relatively low detection rates (i.e., 60%) of current screening technology. The detection rate could be increased by supplementing ultrasound imaging with fetal ultrasound image evaluation (FUSI) using deep learning techniques. As a result, the non-invasive foetal ultrasound image has clear potential in the diagnosis of CHD and should be considered in addition to foetal echocardiography. This review paper highlights cutting-edge technologies for detecting CHD using ultrasound images, which involve pre-processing, localization, segmentation, and classification. Existing technique of preprocessing includes spatial domain filter, non-linear mean filter, transform domain filter, and denoising methods based on Convolutional Neural Network (CNN); segmentation includes thresholding-based techniques, region growing-based techniques, edge detection techniques, Artificial Neural Network (ANN) based segmentation methods, non-deep learning approaches and deep learning approaches. The paper also suggests future research directions for improving current methodologies.

UNASSIGNED: Thyroid nodules are commonly identified through ultrasound imaging, which plays a crucial role in the early detection of malignancy. The diagnostic accuracy, however, is significantly influenced by the expertise of radiologists, the quality of equipment, and image acquisition techniques. This variability underscores the critical need for computational tools that support diagnosis.
UNASSIGNED: This retrospective study evaluates an artificial intelligence (AI)-driven system for thyroid nodule assessment, integrating clinical practices from multiple prominent Thai medical centers. We included patients who underwent thyroid ultrasonography complemented by ultrasound-guided fine needle aspiration (FNA) between January 2015 and March 2021. Participants formed a consecutive series, enhancing the study\'s validity. A comparative analysis was conducted between the AI model\'s diagnostic performance and that of both an experienced radiologist and a third-year radiology resident, using a dataset of 600 ultrasound images from three distinguished Thai medical institutions, each verified with cytological findings.
UNASSIGNED: The AI system demonstrated superior diagnostic performance, with an overall sensitivity of 80% [95% confidence interval (CI): 59.3-93.2%] and specificity of 71.4% (95% CI: 53.7-85.4%). At Siriraj Hospital, the AI achieved a sensitivity of 90.0% (95% CI: 55.5-99.8%), specificity of 100.0% (95% CI: 69.2-100%), positive prediction value (PPV) of 100.0%, negative prediction value (NPV) of 90.9%, and an overall accuracy of 95.0%, indicating the benefits of AI\'s extensive training across diverse datasets. The experienced radiologist\'s sensitivity was 40.0% (95% CI: 21.1-61.3%), while the specificity was 80.0% (95% CIs: 63.6-91.6%), respectively, showing that the AI significantly outperformed the radiologist in terms of sensitivity (P=0.043) while maintaining comparable specificity. The inter-observer variability analysis indicated a moderate agreement (K=0.53) between the radiologist and the resident, contrasting with fair agreement (K=0.37/0.33) when each was compared with the AI system. Notably, 95% CIs for these diagnostic indexes highlight the AI system\'s consistent performance across different settings.
UNASSIGNED: The findings advocate for the integration of AI into clinical settings to enhance the diagnostic accuracy of radiologists in assessing thyroid nodules. The AI system, designed as a supportive tool rather than a replacement, promises to revolutionize thyroid nodule diagnosis and management by providing a high level of diagnostic precision.