Does artificial intelligence aid in the detection of different types of breast cancer?

Abstract Background On mammography many cancers may be missed even in retrospect either due to the breast density, small size of tumor or subtle signs cancer that are imperceptible. We aimed compare sensitivity artificial intelligence (AI) digital detection different types cancer. Also, AI picking up morphologies namely mass, pathological calcifications, asymmetry, and distortion was assessed. Tissue biopsy pathology were used as standard reference. The study included 123 female patients with 134 proved carcinoma. All underwent mammogram (DM) examination scanned algorithm. Results achieved higher than detecting malignant lesions. 96.6%, false negative rate 3.4%, while 87.3% 12.7%. Our showed performed better ductal carcinoma situ invasive lobular (100% 96.6%) vs (88.9% 82.2%) respectively. more sensitive detect presented suspicious mass 95.2% 75%, calcifications 100% 86.5% asymmetry 84.6%, mammography. Conclusions potential values overcome mammographic limitations those challenging morphology carcinoma, situ, tubular micropapillary