Su Yeon Ko1, Ji Hye Lee2, Jung Hyun Yoon2, Hyesun Na3, Eunhye Hong3, Kyunghwa Han4, Inkyung Jung5, Eun-Kyung Kim2, Hee Jung Moon2, Vivian Y Park2, Eunjung Lee3, Jin Young Kwak2. 1. Department of Radiology, Jeju National University Hospital, Jeju National School of Medicine, Jeju, Korea. 2. Department of Radiology, Severance Hospital, Research Institute of Radiological Science, Yonsei University College of Medicine, Seoul, Korea. 3. Department of Computational Science and Engineering, Yonsei University, Seoul, Korea. 4. Department of Radiology, Research Institute of Radiological Science, Center for Clinical Imaging Data Science, Seoul, Korea. 5. Department of Biostatistics and Medical Informatics, Yonsei University College of Medicine, Seoul, Korea.
Abstract
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.
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.
Authors: Dario Tumino; Giorgio Grani; Marta Di Stefano; Maria Di Mauro; Maria Scutari; Teresa Rago; Laura Fugazzola; Maria Grazia Castagna; Fabio Maino Journal: Front Endocrinol (Lausanne) Date: 2020-01-23 Impact factor: 5.555