AUTHOR=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 

TITLE=Enhancing Performance of Breast Ultrasound in Opportunistic Screening Women by a Deep Learning-Based System: A Multicenter Prospective Study

JOURNAL=Frontiers in Oncology

VOLUME=Volume 12 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2022.804632

DOI=10.3389/fonc.2022.804632

ISSN=2234-943X

ABSTRACT=Abstract
Purpose To validate the feasibility of S-Detect, an ultrasound computer assistant diagnosis (CAD) system using deep learning, in enhancing 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 referred 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 operator characteristics curve (AUC). And 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 that of 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 with S-Detect alone, the AUC value significantly 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 Group 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 conventional US, S-Detect presented higher overall accuracy and specificity. After combining S-Detect and strain elastography, the performance could be further enhanced. The performances of S-Detect also varied among different centers.