Automatic Detection System to Identify Invasive Ductal Carcinoma by Predicting Bloom Richardson Grading from Histopathological Images

After skin cancer, the most common type of cancer is breast among world population. Breast leading cause cancer-induced mortality women. frequently diagnosed by using biopsies in which tissue removed from and studied under a microscope. The results these are based on qualifications experience pathologist who diagnoses abnormal cell With emergence advancements fields image processing artificial intelligence, there an area interest developing deep learning model to improve enhance quality accuracy diagnosis. This study proposed that automatically analyses multiclass classification hematoxylin eosin-stained histological images invasive ductal carcinoma (IDC) discriminating IDC into grades such as G-1, G-2, G-3. methodology focused detect adopting Sequential Convolutional Neural Network Two-Dimensional (CNN2D). We used DataBiox, public dataset taken internet source consisting 922 images. evaluate result dividing 80% 20% training testing data, respectively. As pre-trained CNN model, sequential yields 92.81%. Our accurately classifies multi-class specifically IDC. It ready be tested with more diverse massive database future.