Detection of tumor-infiltrating lymphocytes in Breast Histopathological cancer images using deep learning
G K Shruthi, Ravikumar Pushpa · 2025
Breast cancer constitutes 12% of all newly diagnosed cases globally, making it the most predominant type of cancer as a whole. Histopathology images, among all the medical image modalities, maintain the cancer&s;s path and provide richer phenotypic relevant information. The patient&s;s immune system is progressively predictable as a critical feature in defining the suitable treatment. Tumor-infiltrating lymphocytes (TILs), immune cells found within tumors, are emerging as key biomarkers in breast cancer. Histopathology, like radiology, is a visually-focused medical field where pathologists analyze stained tissue sections to make diagnostic decisions. Immunotherapy is a newer approach where stromal tumor-infiltrating lymphocytes (sTILs) are used to target and kill tumor cells. Several deep learning models, including convolutional neural networks (CNNs), have been used to detect cancer cells and segment breast cancer slides. The proposed method uses a deep learning-based method to compute the Tumor-Infiltrating Lymphocytes (TILs) score from breast cancer histopathological images using U-Net for segmentation and ResNet for classification.