Background
We designed a deep convolutional neural network (CNN) to diagnose thyroid malignancy on ultrasound (US) and compared the diagnostic performance of CNN with that of experienced radiologists.
Methods
Between May 2012 and February 2015, 589 thyroid nodules in 519 patients were diagnosed as benign or malignant by surgical excision. Experienced radiologists retrospectively reviewed the US of the thyroid nodules in a test set. CNNs were trained and tested using retrospective data of 439 and 150 US images, respectively. Diagnostic performances were compared between the two groups.
Results
Of the 589 thyroid nodules, 396 were malignant and 193 were benign. The area under the curve (AUC) for diagnosing thyroid malignancy was 0.805‐0.860 for radiologists. The AUCs for diagnosing thyroid malignancy for the three CNNs were 0.845, 0.835, and 0.850. There was no significant difference in AUC between radiologists and CNNs.
Conclusions
CNNs showed comparable diagnostic performance compared to experienced radiologists in differentiating thyroid malignancy on US.
Ultrasonography patterns by the 2015 ATA guidelines can provide risk stratification for nodules with AUS cytology but not for ones with FLUS cytology. For nodules with AUS/FLUS cytology with the very low suspicion pattern of the ATA guidelines, follow-up US might be recommended instead of repeat FNA.
There were no significant associations between all histogram parameters on elastography and known poor prognostic factors such as extrathyroidal extension, lymph node metastasis, and high TNM stage in patients with PTMCs.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.