Noninvasive Deep Learning System for Preoperative Diagnosis of Follicular-Like Thyroid Neoplasms Using Ultrasound Images: A Multicenter, Retrospective Study.
Authors
Affiliations (12)
Affiliations (12)
- Department of Radiology, The First Affiliated Hospital of Jinan University, Guangzhou, Guangdong, China.
- Department of Ultrasound, The First Affiliated Hospital of Kunming Medical University, Kunming, Yunnan, China.
- Department of Ultrasound, Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou, Guangdong, China.
- Department of Medicine Ultrasonics, Nanfang Hospital, Southern Medical University, Guangzhou.
- Department of Ultrasound, The First Affiliated Hospital of Guangzhou University of Chinese Medicine, Guangzhou, Guangdong, China.
- Department of Breast and Thyroid Surgery, The Second Affiliated Hospital of Guilin Medical University, Guilin, Guangxi, China.
- Department of Anesthesiology, The First People's Hospital of Yunnan Province, Kunming, Yunnan, China.
- Department of Radiology, Guangzhou Women and Children's Medical Center, Guangzhou Medical University, Guangzhou, Guangdong, China.
- Department of Pathology, The People's Hospital of Wenshan Prefecture, Wenshan, Yunnan, China.
- Department of Ultrasound, The Affiliated Hospital of Guangdong Medical University, Zhanjiang, Guangdong, China.
- Department of Ultrasound, Zhuhai Clinical Medical College of Jinan University (Zhuhai People's Hospital), Zhuhai, Guangdong, China.
- Medical AI Lab, The First Hospital of Hebei Medical University, Hebei Medical University; Hebei Provincial Engineering Research Center for AI-Based Cancer Treatment Decision-Making, The First Hospital of Hebei Medical University; Department of Oncology, The First Hospital of Hebei Medical University, Hebei Medical University, Shijiazhuang, Hebei, China.
Abstract
To propose a deep learning (DL) system for the preoperative diagnosis of follicular-like thyroid neoplasms (FNs) using routine ultrasound images. 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. 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. 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). 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.