Feasibility of using AI to auto-catch responsible frames in ultrasound screening for breast cancer diagnosis
Jing Chen,
Yitao Jiang,
Keen Yang,
Xiuqin Ye,
Chen Cui,
Siyuan Shi,
Huaiyu Wu,
Hongtian Tian,
Di Song,
Jincao Yao,
Liping Wang,
Sijing Huang,
Jinfeng Xu,
Dong Xu,
Fajin Dong
Affiliations
Jing Chen
Department of Ultrasound, Shenzhen People's Hospital (The Second Clinical School of Medicine, Jinan University; The First Affiliated Hospital of Southern University of Science and Technology), Shenzhen, Guangdong 518020, China
Yitao Jiang
Research and Development Department, Microport Prophecy, Shanghai 201203, China
Keen Yang
Department of Ultrasound, Shenzhen People's Hospital (The Second Clinical School of Medicine, Jinan University; The First Affiliated Hospital of Southern University of Science and Technology), Shenzhen, Guangdong 518020, China
Xiuqin Ye
Department of Ultrasound, Shenzhen People's Hospital (The Second Clinical School of Medicine, Jinan University; The First Affiliated Hospital of Southern University of Science and Technology), Shenzhen, Guangdong 518020, China
Chen Cui
Research and Development Department, Illuminate, LLC, Shenzhen, Guangdong 518000, China
Siyuan Shi
Research and Development Department, Illuminate, LLC, Shenzhen, Guangdong 518000, China
Huaiyu Wu
Department of Ultrasound, Shenzhen People's Hospital (The Second Clinical School of Medicine, Jinan University; The First Affiliated Hospital of Southern University of Science and Technology), Shenzhen, Guangdong 518020, China
Hongtian Tian
Department of Ultrasound, Shenzhen People's Hospital (The Second Clinical School of Medicine, Jinan University; The First Affiliated Hospital of Southern University of Science and Technology), Shenzhen, Guangdong 518020, China
Di Song
Department of Ultrasound, Shenzhen People's Hospital (The Second Clinical School of Medicine, Jinan University; The First Affiliated Hospital of Southern University of Science and Technology), Shenzhen, Guangdong 518020, China
Jincao Yao
The Cancer Hospital of the University of Chinese Academy of Sciences (Zhejiang Cancer Hospital), Institute of Basic Medicine and Cancer (IBMC), Chinese Academy of Sciences, Hangzhou, Zhejiang 310022, China
Liping Wang
The Cancer Hospital of the University of Chinese Academy of Sciences (Zhejiang Cancer Hospital), Institute of Basic Medicine and Cancer (IBMC), Chinese Academy of Sciences, Hangzhou, Zhejiang 310022, China
Sijing Huang
Department of Ultrasound, Shenzhen People's Hospital (The Second Clinical School of Medicine, Jinan University; The First Affiliated Hospital of Southern University of Science and Technology), Shenzhen, Guangdong 518020, China
Jinfeng Xu
Department of Ultrasound, Shenzhen People's Hospital (The Second Clinical School of Medicine, Jinan University; The First Affiliated Hospital of Southern University of Science and Technology), Shenzhen, Guangdong 518020, China; Corresponding author
Dong Xu
The Cancer Hospital of the University of Chinese Academy of Sciences (Zhejiang Cancer Hospital), Institute of Basic Medicine and Cancer (IBMC), Chinese Academy of Sciences, Hangzhou, Zhejiang 310022, China; Corresponding author
Fajin Dong
Department of Ultrasound, Shenzhen People's Hospital (The Second Clinical School of Medicine, Jinan University; The First Affiliated Hospital of Southern University of Science and Technology), Shenzhen, Guangdong 518020, China; Corresponding author
Summary: The research of AI-assisted breast diagnosis has primarily been based on static images. It is unclear whether it represents the best diagnosis image.To explore the method of capturing complementary responsible frames from breast ultrasound screening by using artificial intelligence. We used feature entropy breast network (FEBrNet) to select responsible frames from breast ultrasound screenings and compared the diagnostic performance of AI models based on FEBrNet-recommended frames, physician-selected frames, 5-frame interval-selected frames, all frames of video, as well as that of ultrasound and mammography specialists. The AUROC of AI model based on FEBrNet-recommended frames outperformed other frame set based AI models, as well as ultrasound and mammography physicians, indicating that FEBrNet can reach level of medical specialists in frame selection.FEBrNet model can extract video responsible frames for breast nodule diagnosis, whose performance is equivalent to the doctors selected responsible frames.
