Noninvasive Deep Learning System for Preoperative Diagnosis of Follicular-Like Thyroid Neoplasms Using Ultrasound Images
Year: 2025
Type: article
Abstract: OBJECTIVE: To propose a deep learning (DL) system for the preoperative diagnosis of follicular-like thyroid neoplasms (FNs) using routine ultrasound images. SUMMARY BACKGROUND DATA: Preoperative diagnosis of malignancy in nodules suspicious for an FN remains challenging. Ultrasound, fine-needle aspiration cytology, and intraoperative frozen section pathology cannot unambiguously distinguish between benign and malignant FNs, leading to unnecessary biopsies and operations in benign nodules. METHODS: This multicenter, retrospective study included 3634 patients who underwent ultrasound and received a definite diagnosis of FN from 11 centers, comprising thyroid follicular adenoma (n=1748), follicular carcinoma (n=299), and follicular variant of papillary thyroid carcinoma (n=1587). Four DL models including Inception-v3, ResNet50, Inception-ResNet-v2, and DenseNet161 were constructed on a training set (n=2587, 6178 images) and were verified on an internal validation set (n=648, 1633 images) and an external validation set (n=399, 847 images). The diagnostic efficacy of the DL models was evaluated against the ACR TI-RADS regarding the area under the curve (AUC), sensitivity, specificity, and unnecessary biopsy rate. RESULTS: When externally validated, the four DL models yielded robust and comparable performance, with AUCs of 82.2%-85.2%, sensitivities of 69.6%-76.0%, and specificities of 84.1%-89.2%, which outperformed the ACR TI-RADS. Compared to ACR TI-RADS, the DL models showed a higher biopsy rate of malignancy (71.6% -79.9% vs 37.7%, P<0.001) and a significantly lower unnecessary FNAB rate (8.5% -12.8% vs 40.7%, P<0.001). CONCLUSION: This study provides a noninvasive DL tool for accurate preoperative diagnosis of FNs, showing better performance than ACR TI-RADS and reducing unnecessary invasive interventions.
Source: Annals of Surgery
Authors: Hui Shen, Yue Huang, Wenxiao Yan, Chifa Zhang, Ting Liang, Dan Yang, Xiaoxiao Feng, Shuyi Liu, Yu Wang, Weihan Cao, Ying Cheng, Hongyan Chen, Qiujie Ni, Fei Wang, Jingjing You, Zhe Jin, Wenle He, Jie Sun, Dexing Yang, Lijuan Liu, Boling Cao, Xiao Zhang, Yingjia Li, Shufang Pei, Shuixing Zhang, Bin Zhang
Institutions: First Affiliated Hospital of Jinan University, Kunming Medical University, First Affiliated Hospital of Kunming Medical University, Guangdong Academy of Medical Sciences, Guangdong Provincial People's Hospital, Southern Medical University, Nanfang Hospital, Guangzhou University of Chinese Medicine, First Affiliated Hospital of Guangzhou University of Chinese Medicine, Guilin Medical University, People’s Hospital of Wenshan Prefecture, First People's Hospital of Yunnan Province, The First Hospital of Kunming, Guangzhou Women and Children Medical Center, Guangzhou Medical University, Guangdong Medical College, Jinan University, Zhuhai People's Hospital, Hebei Medical University, First Affiliated Hospital of Hebei Medical University
Language: English
Subfield: Endocrinology, Diabetes and Metabolism
Field: Medicine
Domain: Health Sciences
Open Access status: hybrid
Award: G3794734302
OpenAlex ID: W4412523651