Deep learning radiomics for non-invasive diagnosis of benign and malignant thyroid nodules using ultrasound images

Abstract

Background: The differential diagnosis of benign and malignant thyroid nodules from ultrasound (US) images remained challengeable in clinical practice. We aimed to develop and validate a highly automatic and objective diagnostic model named deep learning Radiomics of thyroid (DLRT) for the differential diagnosis of benign and malignant thyroid nodules from US images. Methods: We retrospectively enrolled US images and corresponding fine-needle aspiration biopsies from 1645 thyroid nodules. A basic convolutional neural network (CNN) model, a transfer learning model, and a newly designed model named deep learning Radiomics of thyroid (DLRT) were used for the investigation. Their diagnostic accuracy was further compared with human observers (one senior and one junior US radiologist). Results: AUCs of DLRT were 0.96 (95% confidence interval [CI]: 0.94-0.98) and 0.95 (95% confidence interval [CI]: 0.93-0.97) in the training and validation cohort, respectively, for the differential diagnosis of benign and malignant thyroid nodules, which were significantly better than other deep learning models (P < 0.05) and human observers (P < 0.05). Conclusions: DLRT shows the best overall performance comparing with other deep learning models and human observers. It holds great promise for improving the differential diagnosis of benign and malignant thyroid nodules.

Ähnliche Arbeiten