School of Management, Hefei University of Technology, Hefei 230009, Anhui, People's Republic of China.
Key Laboratory of Process Optimization and Intelligent Decision-making, Ministry of Education, Hefei 230009, Anhui, People's Republic of China.
Phys Med Biol. 2024 Oct 24;69(21). doi: 10.1088/1361-6560/ad869f.
Ultrasound is the primary screening test for breast cancer. However, providing an interpretable auxiliary diagnosis of breast lesions is a challenging task. This study aims to develop an interpretable auxiliary diagnostic method to enhance usability in human-machine collaborative diagnosis.To address this issue, this study proposes the deep multi-stage reasoning method (DMSRM), which provides individual and overall breast imaging-reporting and data system (BI-RADS) assessment categories for breast lesions. In the first stage of the DMSRM, the individual BI-RADS assessment network (IBRANet) is designed to capture lesion features from breast ultrasound images. IBRANet performs individual BI-RADS assessments of breast lesions using ultrasound images, focusing on specific features such as margin, contour, echogenicity, calcification, and vascularity. In the second stage, evidence reasoning (ER) is employed to achieve uncertain information fusion and reach an overall BI-RADS assessment of the breast lesions.To evaluate the performance of DMSRM at each stage, two test sets are utilized: the first for individual BI-RADS assessment, containing 4322 ultrasound images; the second for overall BI-RADS assessment, containing 175 sets of ultrasound image pairs. In the individual BI-RADS assessment of margin, contour, echogenicity, calcification, and vascularity, IBRANet achieves accuracies of 0.9491, 0.9466, 0.9293, 0.9234, and 0.9625, respectively. In the overall BI-RADS assessment of lesions, the ER achieves an accuracy of 0.8502. Compared to independent diagnosis, the human-machine collaborative diagnosis results of three radiologists show increases in positive predictive value by 0.0158, 0.0427, and 0.0401, in sensitivity by 0.0400, 0.0600 and 0.0434, and in area under the curve by 0.0344, 0.0468, and 0.0255.This study proposes a DMSRM that enhances the transparency of the diagnostic reasoning process. Results indicate that DMSRM exhibits robust BI-RADS assessment capabilities and provides an interpretable reasoning process that better suits clinical needs.
超声是乳腺癌的主要筛查手段。然而，为乳腺病变提供可解释的辅助诊断是一项具有挑战性的任务。本研究旨在开发一种可解释的辅助诊断方法，以提高人机协作诊断的可用性。
为了解决这个问题，本研究提出了深度多阶段推理方法（DMSRM），它为乳腺病变提供了个体和整体乳腺影像报告和数据系统（BI-RADS）评估类别。在 DMSRM 的第一阶段，设计了个体 BI-RADS 评估网络（IBRANet），用于从乳腺超声图像中捕获病变特征。IBRANet 使用超声图像对乳腺病变进行个体 BI-RADS 评估，重点关注边缘、轮廓、回声、钙化和血管等特定特征。在第二阶段，采用证据推理（ER）实现不确定信息融合，得出乳腺病变的整体 BI-RADS 评估。
为了评估 DMSRM 在每个阶段的性能，使用了两个测试集：第一个用于个体 BI-RADS 评估，包含 4322 张超声图像；第二个用于整体 BI-RADS 评估，包含 175 对超声图像。在边缘、轮廓、回声、钙化和血管的个体 BI-RADS 评估中，IBRANet 的准确率分别为 0.9491、0.9466、0.9293、0.9234 和 0.9625。在病变的整体 BI-RADS 评估中，ER 的准确率为 0.8502。与独立诊断相比，三位放射科医生的人机协作诊断结果显示，阳性预测值分别增加了 0.0158、0.0427 和 0.0401，灵敏度分别增加了 0.0400、0.0600 和 0.0434，曲线下面积分别增加了 0.0344、0.0468 和 0.0255。
本研究提出了一种 DMSRM，增强了诊断推理过程的透明度。结果表明，DMSRM 具有强大的 BI-RADS 评估能力，并提供了一种更适合临床需求的可解释推理过程。
