Using Deep Convolutional Neural Networks for Enhanced Ultrasonographic Image Diagnosis of Differentiated Thyroid Cancer
Wai-Kin Chan,
Jui-Hung Sun,
Miaw-Jene Liou,
Yan-Rong Li,
Wei-Yu Chou,
Feng-Hsuan Liu,
Szu-Tah Chen,
Syu-Jyun Peng
Affiliations
Wai-Kin Chan
Division of Endocrinology and Metabolism, Department of Internal Medicine, Chang Gung Memorial Hospital, College of Medicine, Chang Gung University, Taoyuan 33302, Taiwan
Jui-Hung Sun
Division of Endocrinology and Metabolism, Department of Internal Medicine, Chang Gung Memorial Hospital, College of Medicine, Chang Gung University, Taoyuan 33302, Taiwan
Miaw-Jene Liou
Division of Endocrinology and Metabolism, Department of Internal Medicine, Chang Gung Memorial Hospital, College of Medicine, Chang Gung University, Taoyuan 33302, Taiwan
Yan-Rong Li
Division of Endocrinology and Metabolism, Department of Internal Medicine, Chang Gung Memorial Hospital, College of Medicine, Chang Gung University, Taoyuan 33302, Taiwan
Wei-Yu Chou
Division of Endocrinology and Metabolism, Department of Internal Medicine, Chang Gung Memorial Hospital, College of Medicine, Chang Gung University, Taoyuan 33302, Taiwan
Feng-Hsuan Liu
Division of Endocrinology and Metabolism, Department of Internal Medicine, Chang Gung Memorial Hospital, College of Medicine, Chang Gung University, Taoyuan 33302, Taiwan
Szu-Tah Chen
Division of Endocrinology and Metabolism, Department of Internal Medicine, Chang Gung Memorial Hospital, College of Medicine, Chang Gung University, Taoyuan 33302, Taiwan
Syu-Jyun Peng
Professional Master Program in Artificial Intelligence in Medicine, College of Medicine, Taipei Medical University, Taipei 10675, Taiwan
Differentiated thyroid cancer (DTC) from follicular epithelial cells is the most common form of thyroid cancer. Beyond the common papillary thyroid carcinoma (PTC), there are a number of rare but difficult-to-diagnose pathological classifications, such as follicular thyroid carcinoma (FTC). We employed deep convolutional neural networks (CNNs) to facilitate the clinical diagnosis of differentiated thyroid cancers. An image dataset with thyroid ultrasound images of 421 DTCs and 391 benign patients was collected. Three CNNs (InceptionV3, ResNet101, and VGG19) were retrained and tested after undergoing transfer learning to classify malignant and benign thyroid tumors. The enrolled cases were classified as PTC, FTC, follicular variant of PTC (FVPTC), Hürthle cell carcinoma (HCC), or benign. The accuracy of the CNNs was as follows: InceptionV3 (76.5%), ResNet101 (77.6%), and VGG19 (76.1%). The sensitivity was as follows: InceptionV3 (83.7%), ResNet101 (72.5%), and VGG19 (66.2%). The specificity was as follows: InceptionV3 (83.7%), ResNet101 (81.4%), and VGG19 (76.9%). The area under the curve was as follows: Incep-tionV3 (0.82), ResNet101 (0.83), and VGG19 (0.83). A comparison between performance of physicians and CNNs was assessed and showed significantly better outcomes in the latter. Our results demonstrate that retrained deep CNNs can enhance diagnostic accuracy in most DTCs, including follicular cancers.
