Application of Deep-learning and Ultrasound Elastography in Opportunistic Screening of Breast Cancer

A Multi-center Study of Deep Learning Diagnosis and Ultrasound Elastography in Opportunistic Screening of Breast Cancer

As the most common cancer expected to occur all over the world, breast cancer still faces with the unsatisfied diagnostic accuracy in US imaging. S-detect is a sophisticated CAD system for breast US imaging based on deep learning algorithms. E-breast is a software installed in US machines which automatically reveals tumor elastographic features. This multi-center study intends to further validate the diagnostic efficiency of S-detect and E-breast in opportunistic breast cancer screening populations in China. Our hypothesis is that S-detect and E-breast can increase the diagnostic accuracy and specificity as compared to routinely US examinations by doctors.

Inclusion Criteria:

• Female over 18 years of age;
• Had breast lesions detected by ultrasound.
• No clinical symptoms such as nipple discharge, while breast lesions were not palpable.
• Received breast surgery within one week of ultrasound examination.
• Agreed to participant in this study and signed informed consent.

Exclusion Criteria:

• Patients who had received a biopsy of breast lesion before the ultrasound examination.
• Patients who were pregnant or lactating.
• Patients who were undergoing neoadjuvant treatment.