A robust and efficient AI assistant for breast tumor segmentation from DCE-MRI via a spatial-temporal framework

Jiadong Zhang; Zhiming Cui; Zhenwei Shi; Yingjia Jiang; Zhiliang Zhang; Xiaoting Dai; Zhenlu Yang; Yuning Gu; Lei Zhou; Chu Han; Xiaomei Huang; Chenglu Ke; Suyun Li; Zeyan Xu; Fei Gao; Luping Zhou; Rongpin Wang; Jun Liu; Jiayin Zhang; Zhongxiang Ding; Kun Sun; Zhenhui Li; Zaiyi Liu; Dinggang Shen

doi:10.1016/j.patter.2023.100826

A robust and efficient AI assistant for breast tumor segmentation from DCE-MRI via a spatial-temporal framework

Patterns (N Y). 2023 Aug 16;4(9):100826. doi: 10.1016/j.patter.2023.100826. eCollection 2023 Sep 8.

Authors

Jiadong Zhang¹, Zhiming Cui¹, Zhenwei Shi², Yingjia Jiang³, Zhiliang Zhang⁴, Xiaoting Dai⁵, Zhenlu Yang⁶, Yuning Gu¹, Lei Zhou⁷, Chu Han², Xiaomei Huang⁸, Chenglu Ke², Suyun Li², Zeyan Xu², Fei Gao¹, Luping Zhou⁹, Rongpin Wang⁶, Jun Liu³, Jiayin Zhang⁵, Zhongxiang Ding¹⁰, Kun Sun¹¹, Zhenhui Li¹², Zaiyi Liu², Dinggang Shen^{1

13

14}

Affiliations

¹ School of Biomedical Engineering, ShanghaiTech University, Shanghai 201210, China.
² Department of Radiology, Guangdong Provincial People's Hospital, Guangdong 510080, China.
³ Department of Radiology, The Second Xiangya Hospital, Central South University, Hunan 410011, China.
⁴ School of Medical Imaging, Hangzhou Medical College, Zhejiang 310059, China.
⁵ Department of Radiology, Shanghai General Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai 200080, China.
⁶ Department of Radiology, Guizhou Provincial People's Hospital, Guizhou 550002, China.
⁷ School of Health Science and Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China.
⁸ Department of Medical Imaging, Nanfang Hospital, Southern Medical University, Guangzhou 510515, China.
⁹ School of Electrical and Information Engineering, The University of Sydney, Sydney, NSW 2006, Australia.
¹⁰ Department of Radiology, Key Laboratory of Clinical Cancer Pharmacology and Toxicology Research of Zhejiang Province, Hangzhou 310003, China.
¹¹ Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai 200025, China.
¹² Department of Radiology, The Third Affiliated Hospital of Kunming Medical University, Kunming 650118, China.
¹³ Shanghai United Imaging Intelligence Co., Ltd., Shanghai 200230, China.
¹⁴ Shanghai Clinical Research and Trial Center, Shanghai 200052, China.

Abstract

Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) allows screening, follow up, and diagnosis for breast tumor with high sensitivity. Accurate tumor segmentation from DCE-MRI can provide crucial information of tumor location and shape, which significantly influences the downstream clinical decisions. In this paper, we aim to develop an artificial intelligence (AI) assistant to automatically segment breast tumors by capturing dynamic changes in multi-phase DCE-MRI with a spatial-temporal framework. The main advantages of our AI assistant include (1) robustness, i.e., our model can handle MR data with different phase numbers and imaging intervals, as demonstrated on a large-scale dataset from seven medical centers, and (2) efficiency, i.e., our AI assistant significantly reduces the time required for manual annotation by a factor of 20, while maintaining accuracy comparable to that of physicians. More importantly, as the fundamental step to build an AI-assisted breast cancer diagnosis system, our AI assistant will promote the application of AI in more clinical diagnostic practices regarding breast cancer.