Channel boosting based detection and segmentation for cancer analysis in histopathological images
Published in 2022 19th International Bhurban Conference on Applied Sciences and Technology (IBCAST), 2022
The human immune system plays a vital role in cancer prevention, with Tumor Infiltrating Lymphocytes (TILs) serving as key indicators of cancer prognosis. Manual counting of TILs under a microscope is labor-intensive, subjective, and time-consuming. To address this, we propose an automated diagnostic system called PVTCB-Lymph-Det. This system incorporates channel boosting with a Pyramid Vision Transformer and CBAM-enhanced ResNet-50 for effective feature extraction. It tackles the challenges posed by lymphocyte morphological variations, clustering, and artifacts. The model achieves an F-score of 88.92% for lymphocyte detection. PVTCB-Lymph-Det shows promise in assisting pathologists with accurate and efficient diagnosis.
Recommended citation: M. L. Ali, Z. Rauf, A. R. Khan and A. Khan, "Channel boosting based detection and segmentation for cancer analysis in histopathological images," 2022 19th International Bhurban Conference on Applied Sciences and Technology (IBCAST), Islamabad, Pakistan, 2022, pp. 1-6, doi: 10.1109/IBCAST54850.2022.9990330.
Download Paper