Enhancing Performance of Breast Ultrasound in Opportunistic Screening Women by a Deep Learning-Based System: A Multicenter Prospective Study
Chenyang Zhao, Mengsu Xiao, Li Ma, Xinhua Ye, Jing Deng, Ligang Cui, Fajin Guo, Min Wu, Baoming Luo, Qin Chen, Chen Wu, Jun Guo, Qian Li, Qing Zhang, Jianchu Li, Yuxin Jiang, Qingli Zhu
Abstract
Purpose To validate the feasibility of S-Detect, an ultrasound computer-aided diagnosis (CAD) system using deep learning, in enhancing the diagnostic performance of breast ultrasound (US) for patients with opportunistic screening-detected breast lesions. Methods Nine medical centers throughout China participated in this prospective study. Asymptomatic patients with US-detected breast masses were enrolled and received conventional US, S-Detect, and strain elastography subsequently. The final pathological results are referred to as the gold standard for classifying breast mass. The diagnostic performances of the three methods and the combination of S-Detect and elastography were evaluated and compared, including sensitivity, specificity, and area under the receiver operating characteristics (AUC) curve. We also compared the diagnostic performances of S-Detect among different study sites. Results A total of 757 patients were enrolled, including 460 benign and 297 malignant cases. S-Detect exhibited significantly higher AUC and specificity than conventional US (AUC, S-Detect 0.83 [0.80–0.85] vs. US 0.74 [0.70–0.77], p < 0.0001; specificity, S-Detect 74.35% [70.10%–78.28%] vs. US 54.13% [51.42%–60.29%], p < 0.0001), with no decrease in sensitivity. In comparison to that of S-Detect alone, the AUC value significantly was enhanced after combining elastography and S-Detect (0.87 [0.84–0.90]), without compromising specificity (73.93% [68.60%–78.78%]). Significant differences in the S-Detect’s performance were also observed across different study sites (AUC of S-Detect in Groups 1–4: 0.89 [0.84–0.93], 0.84 [0.77–0.89], 0.85 [0.76–0.92], 0.75 [0.69–0.80]; p [1 vs. 4] < 0.0001, p [2 vs. 4] = 0.0165, p [3 vs. 4] = 0.0157). Conclusions Compared with the conventional US, S-Detect presented higher overall accuracy and specificity. After S-Detect and strain elastography were combined, the performance could be further enhanced. The performances of S-Detect also varied among different centers.