Breast cancer is one of the most common cancers in the world, especially among women. Breast tumor segmentation is a key step in the identification and localization of the breast tumor region, which has important clinical significance. Inspired by the swin-transformer model with powerful global modeling ability, we propose a semantic segmentation framework named Swin-Net for breast ultrasound images, which combines Transformer and Convolutional Neural Networks (CNNs) to effectively improve the accuracy of breast ultrasound segmentation. Firstly, our model utilizes a swin-transformer encoder with stronger learning ability, which can extract features of images more precisely. In addition, two new modules are introduced in our method, including the feature refinement and enhancement module (RLM) and the hierarchical multi-scale feature fusion module (HFM), given that the influence of ultrasonic image acquisition methods and the characteristics of tumor lesions is difficult to capture. Among them, the RLM module is used to further refine and enhance the feature map learned by the transformer encoder. The HFM module is used to process multi-scale high-level semantic features and low-level details, so as to achieve effective cross-layer feature fusion, suppress noise, and improve model segmentation performance. Experimental results show that Swin-Net performs significantly better than the most advanced methods on the two public benchmark datasets. In particular, it achieves an absolute improvement of 1.4–1.8% on Dice. Additionally, we provide a new dataset of breast ultrasound images on which we test the effect of our model, further demonstrating the validity of our method. In summary, the proposed Swin-Net framework makes significant advancements in breast ultrasound image segmentation, providing valuable exploration for research and applications in this domain.

Background: The performance in evaluating thyroid nodules on ultrasound varies across different risk stratification systems, leading to inconsistency and uncertainty regarding diagnostic sensitivity, specificity, and accuracy.Objective: Comparing diagnostic performance of detecting thyroid cancer among distinct ultrasound risk stratification systems proposed in the last five years.Evidence acquisition: Systematic search was conducted on PubMed, EMBASE, and Web of Science databases to find relevant research up to December 8, 2022, whose study contents contained elucidation of diagnostic performance of any one of the above ultrasound risk stratification systems (European Thyroid Imaging Reporting and Data System[Eu-TIRADS]; American College of Radiology TIRADS [ACR TIRADS]; Chinese version of TIRADS [C-TIRADS]; Computer-aided diagnosis system based on deep learning [S-Detect]). Based on golden diagnostic standard in histopathology and cytology, single meta-analysis was performed to obtain the optimal cut-off value for each system, and then network meta-analysis was conducted on the best risk stratification category in each system.Evidence synthesis: This network meta-analysis included 88 studies with a total of 59,304 nodules. The most accurate risk category thresholds were TR5 for Eu-TIRADS, TR5 for ACR TIRADS, TR4b and above for C-TIRADS, and possible malignancy for S-Detect. At the best thresholds, sensitivity of these systems ranged from 68% to 82% and specificity ranged from 71% to 81%. It identified the highest sensitivity for C-TIRADS TR4b and the highest specificity for ACR TIRADS TR5. However, sensitivity for ACR TIRADS TR5 was the lowest. The diagnostic odds ratio (DOR) and area under curve (AUC) were ranked first in C-TIRADS.Conclusion: Among four ultrasound risk stratification options, this systemic review preliminarily proved that C-TIRADS possessed favorable diagnostic performance for thyroid nodules.Systematic review registration: https://www.crd.york.ac.uk/prospero, CRD42022382818.

Objective: Conventional cervical lymph node dissection often leaves large surgical scars, which seriously compromises the postoperative aesthetic effect and can affect the quality of life of patients. In this study, the safety and feasibility of robotic-assisted endoscopic thyroidectomy with central neck dissection (CND) and lateral neck dissection (LND) via a combined transoral and breast approach are discussed in detail. Materials and methods: A retrospective analysis was made of the data of 26 patients with stage cN1b papillary thyroid carcinoma who were admitted to the Thyroid Surgery Department of the Hunan Cancer Hospital from March 2021 to September 2022 and who underwent robotic-assisted endoscopic thyroidectomy with LND via a combined transoral and breast approach. The demographic data, surgical indicators, postoperative data, and the postoperative complication rate of the patients were analyzed, and the learning curve was analyzed by cumulative summation. Results: All the patients underwent endoscopic surgery without any conversion to open surgery. The mean operation time was 313.7±50.3 min and the mean number of total positive/retrieved lymph nodes was 11.2±8.1/36.8±13.7. Two patients developed temporary laryngeal recurrent nerve palsy and three patients developed temporary hypoparathyroidism, all of whom recovered within 3 months postoperatively. No tumor recurrence occurred during follow-ups that ranged from 6 to 24 months. The mean postoperative quality of life (QOL) score was 189.1±118.2, test results ranging from 0 to 1300 with a lower score indicating a higher QOL, and the aesthetic satisfaction score was 4.2±0.7, test scores ranging from 0 to 5 with higher scores indicate higher satisfaction. The turning point of the learning curve was in the 11th case. Conclusions: The robotic-assisted endoscopic thyroidectomy with CND and LND via a combined transoral and breast approach is safe and feasible, and the improved cosmetic effect is remarkable, which is conducive to improving the postoperative QOL of patients. It provides a new surgical option for patients.

We developed a continuous learning system (CLS) based on deep learning and optimization and ensemble approach, and conducted a retrospective data simulated prospective study using ultrasound images of breast masses for precise diagnoses. We extracted 629 breast masses and 2235 images from 561 cases in the institution to train the model in six stages to diagnose benign and malignant tumors, pathological types, and diseases. We randomly selected 180 out of 3098 cases from two external institutions. The CLS was tested with seven independent datasets and compared with 21 physicians, and the system’s diagnostic ability exceeded 20 physicians by training stage six. The optimal integrated method we developed is expected accurately diagnose breast masses. This method can also be extended to the intelligent diagnosis of masses in other organs. Overall, our findings have potential value in further promoting the application of AI diagnosis in precision medicine.

Neuromyelitis optica spectrum disorder (NMOSD) is an inflammatory demyelinating disease of the central nervous system. However, whether and how cortical changes occur in NMOSD with normal-appearing brain tissue, or whether any cortical changes correlate with clinical characteristics, is not completely clear. The current study recruited 43 patients with NMOSD who had normal-appearing brain tissue and 45 healthy controls matched for age, sex, and educational background from December 2020 to February 2022. A surface-based morphological analysis of high-resolution T1-weighted structural magnetic resonance images was used to calculate the cortical thickness, sulcal depth, and gyrification index. Analysis showed that cortical thickness in the bilateral rostral middle frontal gyrus and left superior frontal gyrus was lower in the patients with NMOSD than in the control participants. Subgroup analysis of the patients with NMOSD indicated that compared with those who did not have any optic neuritis episodes, those who did have such episodes exhibited noticeably thinner cortex in the bilateral cuneus, superior parietal cortex, and pericalcarine cortex. Correlation analysis indicated that cortical thickness in the bilateral rostral middle frontal gyrus was positively correlated with scores on the Digit Symbol Substitution Test and negatively correlated with scores on the Trail Making Test and the Expanded Disability Status Scale. These results are evidence that cortical thinning of the bilateral regional frontal cortex occurs in patients with NMOSD who have normal-appearing brain tissue, and that the degree of thinning is correlated with clinical disability and cognitive function. These findings will help improve our understanding of the imaging characteristics in NMOSD and their potential clinical significance.