Multimodal Deep Learning Model Based on Ultrasound and Cytological Images Predicts Risk Stratification of cN0 Papillary Thyroid Carcinoma.
Authors
Affiliations (5)
Affiliations (5)
- Department of Medical Ultrasound, Sichuan Provincial People's Hospital, School of Medicine, University of Electronic Science and Technology of China, Chengdu, China, 610000 (F.H.).
- Department of Chinese medicine, Sichuan Provincial People's Hospital, School of Medicine, University of Electronic Science and Technology of China, Chengdu, China, 610000 (S.C.).
- Department of Ultrasound, Beijing Anzhen Nanchong Hospital of Capital Medical University & Nanchong Central Hospital, Nanchong, Sichuan, China, 637000 (X.L.).
- Department of Pathology, Sichuan Provincial People's Hospital, School of Medicine, University of Electronic Science and Technology of China, Chengdu, China, 610000 (X.Y.).
- Department of Ultrasound, Chengdu Second People's Hospital, Chengdu, China, 610000 (X.Q.). Electronic address: [email protected].
Abstract
Accurately assessing the risk stratification of cN0 papillary thyroid carcinoma (PTC) preoperatively aids in making treatment decisions. We integrated preoperative ultrasound and cytological images of patients to develop and validate a multimodal deep learning (DL) model for non-invasive assessment of N0 PTC risk stratification before surgery. In this retrospective multicenter group study, we developed a comprehensive DL model based on ultrasound and cytological images. The model was trained and validated on 890 PTC patients undergoing thyroidectomy and lymph node dissection across five medical centers. The testing group included 107 patients from one medical center. We analyzed the model's performance, including the area under the receiver operating characteristic curve, accuracy, sensitivity, and specificity. The combined DL model demonstrated strong performance, with an area under the curve (AUC) of 0.922 (0.866-0.979) in the internal validation group and an AUC of 0.845 (0.794-0.895) in the testing group. The diagnostic performance of the combined DL model surpassed that of clinical models. Image region heatmaps assisted in interpreting the diagnosis of risk stratification. The multimodal DL model based on ultrasound and cytological images can accurately determine the risk stratification of N0 PTC and guide treatment decisions.