Optimizing breast lesions diagnosis and decision-making with a deep learning fusion model integrating ultrasound and mammography: a dual-center retrospective study.
Authors
Affiliations (11)
Affiliations (11)
- Department of Ultrasound, Nanfang Hospital, Southern Medical University, Guangzhou, 510515, China.
- School of Biomedical Engineering, Southern Medical University, Guangzhou, 510515, Guangdong, China.
- Department of Imaging, Zengcheng Branch of Nanfang Hospital, Southern Medical University, Guangzhou, 510515, China.
- Department of Radiology, Nanfang Hospital, Southern Medical University, Guangzhou, 510515, China.
- Department of Ultrasound, First People's Hospital of Foshan, Foshan, 510515, Guangdong, China.
- Department of Medical Imaging, Nanfang Hospital, Southern Medical University, Guangzhou, 510515, Guangdong, China.
- Department of Ultrasound, Ruijin Hospital, Shanghai Jiaotong University School of Medicine, Shanghai, 200025, China.
- Shenzhen Key Laboratory for Drug Addiction and Medication Safety, Department of Ultrasound, Institute of Ultrasonic Medicine, Peking University Shenzhen Hospital, Shenzhen Peking University-The Hong Kong University of Science and Technology Medical Center, Shenzhen, 518036, China.
- Department of Medical Imaging, Nanfang Hospital, Southern Medical University, Guangzhou, 510515, Guangdong, China. [email protected].
- School of Biomedical Engineering, Southern Medical University, Guangzhou, 510515, Guangdong, China. [email protected].
- Department of Ultrasound, Nanfang Hospital, Southern Medical University, Guangzhou, 510515, China. [email protected].
Abstract
This study aimed to develop a BI-RADS network (DL-UM) via integrating ultrasound (US) and mammography (MG) images and explore its performance in improving breast lesion diagnosis and management when collaborating with radiologists, particularly in cases with discordant US and MG Breast Imaging Reporting and Data System (BI-RADS) classifications. We retrospectively collected image data from 1283 women with breast lesions who underwent both US and MG within one month at two medical centres and categorised them into concordant and discordant BI-RADS classification subgroups. We developed a DL-UM network via integrating US and MG images, and DL networks using US (DL-U) or MG (DL-M) alone, respectively. The performance of DL-UM network for breast lesion diagnosis was evaluated using ROC curves and compared to DL-U and DL-M networks in the external testing dataset. The diagnostic performance of radiologists with different levels of experience under the assistance of DL-UM network was also evaluated. In the external testing dataset, DL-UM outperformed DL-M in sensitivity (0.962 vs. 0.833, P = 0.016) and DL-U in specificity (0.667 vs. 0.526, P = 0.030), respectively. In the discordant BI-RADS classification subgroup, DL-UM achieved an AUC of 0.910. The diagnostic performance of four radiologists improved when collaborating with the DL-UM network, with AUCs increased from 0.674-0.772 to 0.889-0.910, specificities from 52.1%-75.0 to 81.3-87.5% and reducing unnecessary biopsies by 16.1%-24.6%, particularly for junior radiologists. Meanwhile, DL-UM outputs and heatmaps enhanced radiologists' trust and improved interobserver agreement between US and MG, with weighted kappa increased from 0.048 to 0.713 (P < 0.05). The DL-UM network, integrating complementary US and MG features, assisted radiologists in improving breast lesion diagnosis and management, potentially reducing unnecessary biopsies.