AUTHOR=Yang Jingya , Shi Xiaoli , Wang Bing , Qiu Wenjing , Tian Geng , Wang Xudong , Wang Peizhen , Yang Jiasheng 

TITLE=Ultrasound Image Classification of Thyroid Nodules Based on Deep Learning

JOURNAL=Frontiers in Oncology

VOLUME=Volume 12 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2022.905955

DOI=10.3389/fonc.2022.905955

ISSN=2234-943X

ABSTRACT=A thyroid nodule, which is defined as abnormal growth of thyroid cells, indicates excessive iodine intake, thyroid degeneration, inflammation and other diseases. Although thyroid nodules are always non-malignant, the malignancy likelihood of a thyroid nodule grows steadily every year. In order to reduce the burden on doctors and avoid unnecessary fine needle aspiration (FNA) and surgical resection, various studies have been done to diagnose thyroid nodule through deep-learning based image recognition analysis. In this study, to predict the benign and malignant thyroid nodules accurately, a novel deep learning framework is proposed. 508 ultrasound images were collected from the Third Hospital of Hebei Medical University in China for model training and validation. First, a ResNet18 model, pre-trained on ImageNet, was trained by ultrasound images dataset, and a random sampling of training dataset was applied ten times to avoid accidental errors. The results show that our model has a good performance, the average area under curve (AUC) of ten times is 0.997, the average accuracy is 0.984, the average recall is 0.978, the average precision is 0.939 and the average F1 score is 0.957. Second, Gradient-weighted Class Activation Mapping (Grad-CAM) was proposed to highlight sensitive regions in an ultrasound image during the learning process. Grad-CAM is able to extract the sensitive regions and analyze their shape features. Based on the results, there are obvious differences between benign and malignant thyroid nodules, therefore, shape features of the sensitive regions are helpful in diagnosis to a great extent. Overall, the proposed model demonstrated the feasibility of employing deep learning and ultrasound images to estimate benign and malignant thyroid nodules.