Automated diagnosis and management of follicular thyroid nodules based on the devised small-datasets interpretable foreground optimization network deep learning: A multicenter diagnostic study.

Abstract

Currently, follicular thyroid carcinoma (FTC) has relatively low incidence with a lack of effective preoperative diagnostic means. To reduce the need for diagnostic invasive procedures and to address information deficiencies inherent in a small-dataset, we utilized interpretable foreground optimization network deep learning to develop a reliable preoperative FTC detection system. In this study, a deep learning model (FThyNet) was established using preoperative ultrasound images. Data on patients in training and internal validation cohort (n=432) were obtained from XXX Hospital, China. Data on patients in external validation cohort (n=71) were obtained from four other clinical centers. We evaluated the predictive performance of FThyNet and its ability to generalize across multiple external centers and compared the results yielded with assessments from physicians directly predicting FTC outcomes. In addition, the influence of texture information around the nodule edge on the prediction results was evaluated. FThyNet had a consistently high accuracy in predicting FTC with area under the receiver operating characteristic curve (AUC) of (89.0% [95% CI 87.0-90.9]). Particularly, the AUC for grossly invasive-FTC reached 90.3%, which was significantly higher than that of the radiologists (56.1% [95% CI 51.8-60.3]). The parametric visualization study found that those nodules with blurred edges and relatively distorted surrounding textures were more likely to have FTC. Furthermore, edge texture information played an important role in FTC prediction with an AUC of (68.3% [95% CI 61.5-75.5]), and highly invasive malignancies had the highest texture complexity. FThyNet could effectively predict FTC, provide explanations consistent with pathological knowledge, and improve clinical understanding of the disease.