Human understandable thyroid ultrasound imaging AI report system - A bridge between AI and clinicians

Siqiong Yao; Pengcheng Shen; Tongwei Dai; Fang Dai; Yun Wang; Weituo Zhang; Hui Lu

doi:10.1016/j.isci.2023.106530

Human understandable thyroid ultrasound imaging AI report system - A bridge between AI and clinicians

iScience. 2023 Mar 31;26(4):106530. doi: 10.1016/j.isci.2023.106530. eCollection 2023 Apr 21.

Authors

Siqiong Yao¹, Pengcheng Shen¹, Tongwei Dai¹, Fang Dai¹, Yun Wang², Weituo Zhang³, Hui Lu^{1

4

5}

Affiliations

¹ Joint International Research Laboratory of Metabolic & Developmental Sciences, Department of Bioinformatics and Biostatistics, School of Life Sciences and Biotechnology, Shanghai Jiao Tong University, Shanghai, China.
² Department of Hepatobiliary pancreatic center, Xuzhou City Central Hospital, The Affiliated Hospital of the Southeast University Medical School (Xu zhou), The Tumor Research Institute of the Southeast University (Xu zhou), Xuzhou, Jiangsu, China.
³ Hong Qiao International Institute of Medicine, Shanghai Tong Ren Hospital and Clinical Research Institute, Shanghai Jiao Tong University School of Medicine, Shanghai, China.
⁴ SJTU-Yale Joint Center of Biostatistics and Data Science, National Center for Translational Medicine, Shanghai Jiao Tong University, Shanghai, China.
⁵ Shanghai Engineering Research Center for Big Data in Pediatric Precision Medicine, Center for Biomedical Informatics, Shanghai Children's Hospital, Shanghai, China.

Abstract

Artificial intelligence (AI) enables accurate diagnosis of thyroid cancer; however, the lack of explanation limits its application. In this study, we collected 10,021 ultrasound images from 8,079 patients across four independent institutions to develop and validate a human understandable AI report system named TiNet for thyroid cancer prediction. TiNet can extract thyroid nodule features such as texture, margin, echogenicity, shape, and location using a deep learning method conforming to the clinical diagnosis standard. Moreover, it offers excellent prediction performance (AUC 0.88) and provides quantitative explanations for the predictions. We conducted a reverse cognitive test in which clinicians matched the correct ultrasound images according to TiNet and clinical reports. The results indicated that TiNet reports (87.1% accuracy) were significantly easier to understand than clinical reports (81.6% accuracy; p < 0.001). TiNet can serve as a bridge between AI-based diagnosis and clinicians, enhancing human-AI cooperative medical decision-making.

Keywords: Artificial intelligence; Biotechnology; Radiation biology; Ultrasound technology.