Zhao Chenyang, Xiao Mengsu, Ma Li, Ye Xinhua, Deng Jing, Cui Ligang, Guo Fajin, Wu Min, Luo Baoming, Chen Qin, Chen Wu, Guo Jun, Li Qian, Zhang Qing, Li Jianchu, Jiang Yuxin, Zhu Qingli
Department of Ultrasound, Chinese Academy of Medical Sciences and Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China.
Department of Ultrasound, First Affiliated Hospital, Nanjing Medical University, Nanjing, China.
Front Oncol. 2022 Feb 10;12:804632. doi: 10.3389/fonc.2022.804632. eCollection 2022.
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.
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.
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], < 0.0001; specificity, S-Detect 74.35% [70.10%-78.28%] vs. US 54.13% [51.42%-60.29%], < 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]; [1 vs. 4] < 0.0001, [2 vs. 4] = 0.0165, [3 vs. 4] = 0.0157).
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.
验证S-Detect（一种使用深度学习的超声计算机辅助诊断（CAD）系统）在提高机会性筛查发现的乳腺病变患者的乳腺超声（US）诊断性能方面的可行性。
中国九个医疗中心参与了这项前瞻性研究。纳入超声检查发现乳腺肿块的无症状患者，随后接受常规超声、S-Detect和应变弹性成像检查。最终病理结果作为乳腺肿块分类的金标准。评估并比较了三种方法以及S-Detect与弹性成像联合检查的诊断性能，包括敏感性、特异性和受试者工作特征（AUC）曲线下面积。我们还比较了不同研究地点S-Detect的诊断性能。
共纳入757例患者，其中良性460例，恶性297例。S-Detect的AUC和特异性显著高于常规超声（AUC，S-Detect为0.83[0.80-0.85]，超声为0.74[0.70-0.77]，<0.0001；特异性，S-Detect为74.35%[70.10%-78.28%]，超声为54.13%[51.42%-60.29%]，<0.0001），敏感性无下降。与单独使用S-Detect相比，弹性成像与S-Detect联合后AUC值显著提高（0.87[0.84-0.90]），且特异性未受影响（73.93%[68.60%-78.78%]）。不同研究地点的S-Detect性能也存在显著差异（第1-4组S-Detect的AUC：0.89[0.84-0.93]，0.84[0.77-0.89]，0.85[0.76-0.92]，0.75[0.69-0.80]；[1与4比较]<0.0001，[2与4比较]=0.0165，[3与4比较]=0.0157）。
与传统超声相比，S-Detect具有更高的总体准确性和特异性。S-Detect与应变弹性成像联合后，性能可进一步提高。不同中心的S-Detect性能也有所不同。
