Deep convolutional neural network for the diagnosis of thyroid nodules on ultrasound

• Published in: Head & neck Vol. 41; no. 4; pp. 885 - 891
• Main Authors: Ko, Su Yeon, Lee, Ji Hye, Yoon, Jung Hyun, Na, Hyesun, Hong, Eunhye, Han, Kyunghwa, Jung, Inkyung, Kim, Eun‐Kyung, Moon, Hee Jung, Park, Vivian Y., Lee, Eunjung, Kwak, Jin Young
• Format: Journal Article
• Language: English
• Published: Hoboken, USA John Wiley & Sons, Inc 01.04.2019; Wiley Subscription Services, Inc
• Subjects: Benign; convolutional neural network (CNN); deep learning; Head and neck; Malignancy; Neural networks; Nodules; Thyroid; Thyroid cancer; Thyroid gland; thyroid nodule; Ultrasonic imaging; Ultrasound; deep learning; thyroid nodule; thyroid cancer; convolutional neural network (CNN); ultrasound
• DOI: 10.1002/hed.25415
• ISSN: 1043-3074; 1097-0347

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.