Detection and classification of breast lesions using multiple information on contrast-enhanced mammography by a multiprocess deep-learning system: A multicenter study

Yuqian Chen; Zhen Hua; Fan Lin; Tiantian Zheng; Heng Zhou; Shijie Zhang; Jing Gao; Zhongyi Wang; Huafei Shao; Wenjuan Li; Fengjie Liu; Simin Wang; Yan Zhang; Feng Zhao; Hao Liu; Haizhu Xie; Heng Ma; Haicheng Zhang; Ning Mao

doi:10.21147/j.issn.1000-9604.2023.04.07

Detection and classification of breast lesions using multiple information on contrast-enhanced mammography by a multiprocess deep-learning system: A multicenter study

Chin J Cancer Res. 2023 Aug 30;35(4):408-423. doi: 10.21147/j.issn.1000-9604.2023.04.07.

Authors

Yuqian Chen¹, Zhen Hua¹, Fan Lin², Tiantian Zheng³, Heng Zhou¹, Shijie Zhang², Jing Gao², Zhongyi Wang², Huafei Shao², Wenjuan Li², Fengjie Liu², Simin Wang⁴, Yan Zhang⁵, Feng Zhao⁶, Hao Liu⁷, Haizhu Xie², Heng Ma², Haicheng Zhang^{2

8}, Ning Mao^{2

8}

Affiliations

¹ School of Information and Electronic Engineering, Shandong Technology and Business University, Yantai 264005, China.
² Department of Radiology, Yantai Yuhuangding Hospital, Affiliated Hospital of Qingdao University, Yantai 264000, China.
³ School of Medical Imaging, Binzhou Medical University, Yantai 264003, China.
⁴ Department of Radiology, Fudan University Cancer Center, Shanghai 200433; China.
⁵ Department of Radiology, Guangdong Maternal and Child Health Hospital, Guangzhou 510010, China.
⁶ School of Computer Science and Technology, Shandong Technology and Business University, Yantai 264005, China.
⁷ Yizhun Medical AI Co. Ltd., Beijing 100080, China.
⁸ Big Data and Artificial Intelligence Laboratory, Yantai Yuhuangding Hospital, Affiliated Hospital of Qingdao University, Yantai 264000, China.

PMID: 37691895
PMCID: PMC10485921
DOI: 10.21147/j.issn.1000-9604.2023.04.07

Abstract

Objective: Accurate detection and classification of breast lesions in early stage is crucial to timely formulate effective treatments for patients. We aim to develop a fully automatic system to detect and classify breast lesions using multiple contrast-enhanced mammography (CEM) images.

Methods: In this study, a total of 1,903 females who underwent CEM examination from three hospitals were enrolled as the training set, internal testing set, pooled external testing set and prospective testing set. Here we developed a CEM-based multiprocess detection and classification system (MDCS) to perform the task of detection and classification of breast lesions. In this system, we introduced an innovative auxiliary feature fusion (AFF) algorithm that could intelligently incorporates multiple types of information from CEM images. The average free-response receiver operating characteristic score (AFROC-Score) was presented to validate system's detection performance, and the performance of classification was evaluated by area under the receiver operating characteristic curve (AUC). Furthermore, we assessed the diagnostic value of MDCS through visual analysis of disputed cases, comparing its performance and efficiency with that of radiologists and exploring whether it could augment radiologists' performance.

Results: On the pooled external and prospective testing sets, MDCS always maintained a high standalone performance, with AFROC-Scores of 0.953 and 0.963 for detection task, and AUCs for classification were 0.909 [95% confidence interval (95% CI): 0.822-0.996] and 0.912 (95% CI: 0.840-0.985), respectively. It also achieved higher sensitivity than all senior radiologists and higher specificity than all junior radiologists on pooled external and prospective testing sets. Moreover, MDCS performed superior diagnostic efficiency with an average reading time of 5 seconds, compared to the radiologists' average reading time of 3.2 min. The average performance of all radiologists was also improved to varying degrees with MDCS assistance.

Conclusions: MDCS demonstrated excellent performance in the detection and classification of breast lesions, and greatly enhanced the overall performance of radiologists.

Keywords: Deep learning; breast lesions; classification; contrast-enhanced mammography; detection.