Deep learning-based breast cancer detection using VGG-NiN architecture

Breast cancer is a steadily growing disease that provides elevated mortality than other types for global women. The survival rate of this type can be uplifted through appropriate screening and diagnosis where the role early detection breast significant. In regard, design Computer-Aided Diagnosis (CAD) with improved reliability always in demand earlier detection. work proposed VGG-NiN architecture integrating pretrained CNN VGG-16 together spatial pyramid pooling (SPP) layer network-in-network (NiN). above-said layers are stacked to classify severities minimum parameters speed up model convergence training process. For this, utilized INbreast dataset digital mammogram inputs. obtained experimental results reveal robustness method as compared state-of-the-art CAD techniques.