Automatic Detection of Invasive Ductal Carcinoma (Breast Cancer) in Histopathology Images using Deep Learning
2025
Invasive Ductal Carcinoma (IDC) is the most common type of breast cancer, accounting for 70 -80% of total breast cancer cases.The traditional method of detecting IDC breast cancer is time -consuming and prone to human error, as doctors manually recommend a cancer diagnosis based on their expertise.Pathologists examine IDC using a microscope to analyze hematoxylin and eosin (H&E) stained slides, which is very time-consuming and prone to human error.Today, digital technology uses deep learning (DL) models to quickly and reliably search and analyze IDC images.These models analyze H^E -stained tissue slides and mainly use public datasets such as The Cancer Genome Atlas (TCGA) and BreakHis.This study explores the application of deep learning techniques to predict IDC using histopathological tissue slice images.The proposed solution achieved an accuracy of 92%, a sensitivity of 89%, and a specificity of 94%.The results of this study show that DL models can provide reliable and interpretable predictions that can assist pathologists in clinical decision-making.