Automated Diganosis Pipeline for Breast Cancer Metastasis Assessment

This research aims to develop an AI-guided automated pipeline for assessing breast cancer metastases in distant and axillary lymph nodes using affordable digital images of H&E-stained biopsy specimens. Traditional imaging methods (e.g., MRI, CT, PET-CT) often fail to detect early metastases and depend heavily on expert interpretation. While biopsy-based assessment is more accurate, it is underutilized in low-resource settings like Bangladesh and other developing countries due to its labor-intensive nature. Our system captures biopsy images using a camera-mounted microscope, identifies tumor regions using a transformer model, and classifies metastases using a graph neural network (GNN). The pipeline delivers fast, accurate, and cost-effective results, helping pathologists make informed decisions. This research directly supports the UN Sustainable Development Goals (SDGs), including Good Health and Well-being (SDG 3), Industry and Innovation (SDG 9), Reduced Inequalities (SDG 10), and Gender Equality (SDG 5).