AUTHOR=Hou Yiqing , Chen Chao , Zhang Lu , Zhou Wei , Lu Qinyang , Jia Xiaohong , Zhang Jingwen , Guo Cen , Qin Yuxiang , Zhu Lifeng , Zuo Ming , Xiao Jing , Huang Lingyun , Zhan Weiwei 

TITLE=Using Deep Neural Network to Diagnose Thyroid Nodules on Ultrasound in Patients With Hashimoto’s Thyroiditis

JOURNAL=Frontiers in Oncology

VOLUME=Volume 11 - 2021

YEAR=2021

URL=https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2021.614172

DOI=10.3389/fonc.2021.614172

ISSN=2234-943X

ABSTRACT=Objective: The aim of this study is to develop a model using Deep Neural Network (DNN) to diagnose thyroid nodules in patients with Hashimoto’s Thyroiditis. 
Methods: In this retrospective study, we included 2932 patients with thyroid nodules who underwent thyroid ultrasonogram in our hospital from January 2017 to August 2019. 80%of them were included as training set and 20% as test set. Nodules suspected for malignancy underwent FNA or surgery for pathological results. Two DNN models were trained to diagnose thyroid nodules and we chose the one with better performance. The features of nodules as well as parenchyma around nodules will be learned by the model to achieve better performance under diffused parenchyma. 10-fold cross-validation and an independent test set were used to evaluate the performance of the algorithm. The performance of model was compared with 3 groups of radiologists with clinical experience of <5 years, 5-10 years, >10 years respectively.
Results: In total, 9127 images were collected from 2932 patients with 7301 images for training set and 1806 for test set. 56% of the patients enrolled had Hashimoto’s Thyroiditis. The model achieved an AUC of 0.924 for distinguishing malignant and benign nodules in the test set. It showed similar performance under diffused thyroid parenchyma and normal parenchyma with sensitivity of 0.881 versus 0.871(p=0.938) and specificity of 0.846 versus 0.822(p=0.178). In patients with HT, the model achieved an AUC of 0.924 for differentiate malignant and benign nodules which was significantly higher than the three groups of radiologists (AUC=0.824, 0.857, 0.863 respectively, p<0.05).
Conclusion: The model showed high performance in diagnosing thyroid nodules under both normal and diffused parenchyma. In patients with Hashimoto’s Thyroiditis, the model showed a better performance compared to radiologists with various years of experience.