Background: A computer-aided diagnosis (CAD) system was recently introduced for the characterization and interpretation of the US features of thyroid nodules.
Purpose: To determine whether a CAD system for the evaluation of thyroid nodules is non-inferior to radiologists with different levels of experience.
Materials and methods: Institutional review board approval and informed consent were obtained for this prospective non-inferiority study. Patients with thyroid nodules with a decisive diagnosis, whether benign or malignant, were consecutively enrolled from November 2017 to September 2018. Three radiologists with different levels of experience (1 month, 4 year, and 7 years) in thyroid ultrasound reviewed the thyroid ultrasound with and without the use of a CAD system. Statistical analyses included non-inferiority testing of the diagnostic accuracy for malignant thyroid nodules between the CAD system and the three radiologists with a non-inferiority margin of 10%, comparison of the diagnostic performance, and the added value of the CAD system on the radiologists.
Results: A total of 197 patients (165 patients with a benign nodule [84.8%] and 25 patients with a malignant nodule [15.2%]) were included in the study cohort. The diagnostic accuracy of the CAD system was non-inferior to that of the radiologists with less experience (1 month and 4 year) on thyroid US, whereas it was inferior to that of the experienced radiologist (7 years). The sensitivity and negative predictive value of the CAD system were significantly higher than those of the less-experienced radiologists, whereas no significant difference was found with the experienced radiologist. A conjunctive combination of grayscale US and the CAD system significantly improved sensitivity and negative predictive value, although specificity and positive predictive value deteriorated for the less-experienced radiologists.
Conclusion: The CAD system may offer support for decision-making in the diagnosis of malignant thyroid nodules for operators who have less experience in thyroid US.