Answers are grounded in this paper and cite their sources.
Interpreting thyroid ultrasound images is a tedious task and is prone to interobserver variability. This study proposes a computer-aided diagnosis system (CAD) for thyroid nodule risk classification and management recommendations based on the American College of Radiology (ACR) Thyroid Imaging Reporting and Data System (TIRADS), which uses a deep learning framework to increase diagnostic accuracy and reliability. In this retrospective analysis, 2450 thyroid ultrasound images with 3250 nodules were acquired from 1037 patients from 2018 to 2020 at a single institution. Our proposed automated method has four main steps: preprocessing and image augmentation, nodule detection, nodule classification on the basis of ACR-TIRADS, and risk-level stratification and treatment management. We trained different state-of-the-art pretrained convolutional neural networks (CNNs) to choose the best architecture in the detection and classification stage. We compared the performance of our method with that of three experienced radiologists. The comparison results show that the Faster R-CNN ResNet-101 has better performance in the detection stage and that the fine-tuned Xception model achieves 0.98 % accuracy, 0.99 % AUC, 0.967 % precision, and 0.912 % recall when it is selected as the backbone of the classification stage. The results demonstrated that the performance of our algorithm was better than that of the three radiologists, with a mean kappa value of 0.85 % for the five ACR-TIRADS categories compared with the gold standard. This study, in addition to generating a valuable database of thyroid US images, demonstrates that our method can effectively improve the performance of thyroid nodule assessment and can assist radiologists as an adjunctive clinical tool to improve efficiency, reliability, and diagnostic performance in clinical practice. • Developing a deep learning CAD system for risk stratification and treatment management of thyroid nodules. • Using a single DL network for the multi-label classification. • Automatic detection of multi-nodules from ultrasound thyroid images. • Automatic removal of all calipers and patient information from the images. • 0.98 % accuracy and 0.99 % AUC that can increase diagnosis accuracy, decrease observer variation and unnecessary FNA.
No takes yet. Share an insight, caveat, or question.
Sharifi et al. (2025) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: