A deep learning-based framework for the malignancy analysis of thyroid lesions in contrast-enhanced ultrasound videos.
Authors
Affiliations (5)
Affiliations (5)
- School of Computer Science and Engineering, Hubei Key Laboratory of Intelligent Robot, Wuhan Institute of Technology, Wuhan, 430200, China.
- Faculty of Applied Science and Engineering, University of Toronto, Toronto, M5S 3G4, Canada.
- Department of Ultrasound, Seventh Medical Center, Chinese PLA General Hospital, Beijing, 10010, China.
- Department of Medical Ultrasound, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, China. Electronic address: [email protected].
- School of Computer Science and Engineering, Hubei Key Laboratory of Intelligent Robot, Wuhan Institute of Technology, Wuhan, 430200, China; Xinjiang Key Laboratory of Artificial Intelligence Assisted Imaging Diagnosis, Kashi, 844000, China. Electronic address: [email protected].
Abstract
Contrast-enhanced ultrasound (CEUS) is widely used for evaluating thyroid nodule malignancy, but conventional time-intensity curve (TIC) analysis is labor-intensive and operator-dependent. This study proposes LSTAC, an automated framework for nodule segmentation and TIC analysis in CEUS videos. LSTAC integrates an improved YOLOv5-based segmentation network with a peak intensity frame (PIF) extraction algorithm to enable automatic nodule localization, TIC generation, and PIF identification. The framework was trained using CEUS data from 623 patients collected across three hospitals and evaluated on both internal and external validation cohorts. LSTAC achieved 3-10× higher efficiency than VueBox in PIF extraction while maintaining strong temporal accuracy (0.94, 0.77, 0.79) and structural similarity (SSIM: 0.80, 0.60, 0.67). In malignancy prediction based on PIF features, LSTAC outperformed VueBox in two of three validation sets, with AUCs of 0.8279 vs. 0.8226 and 0.8000 vs. 0.7000. LSTAC provides an efficient and accurate solution for automated CEUS analysis, reducing manual workload and improving consistency in thyroid nodule assessment, with potential for clinical application.