A Multimodal Deep Learning Model for Preoperative Risk Prediction of Follicular Thyroid Carcinoma

Follicular thyroid carcinoma (FTC) is the second most common type of thyroid cancer and is highly aggressive, with a tendency to hematogenous metastasis. A definite diagnosis of FTC requires pathological examination after complete excision of the mass, and preoperative diagnosis of FTC is a challenge for both surgeons and imaging physicians. In this study, we aim to develop a multimodal deep learning model that combines grey scale ultrasound images, color doppler ultrasound images, and patient clinical data to predict the risk of FTC. This retrospective study include a dataset of 323 patients who underwent surgery. We develop and compare different models, including single modal, bimodal, and multi-modal models. The multimodal model performs the best, with an area under the curve (AUC) of 0.97. The results of the study demonstrate that the deep learning multimodal fusion method using grey scale ultrasound images, color doppler ultrasound images, and patient clinical data achieves better prediction performance.