The study presents a novel 1D deep learning tool, CaReNet-V1, for breast cancer subtype evaluation and biochemical content evaluation using micro-FTIR hyperspectral images. The tool effectively classified cancer and adjacent tissue, as well as HER2 and TNBC subtypes, with some difficulty for LA and LB. The model also enabled the evaluation of the most contributing wavenumbers to the predictions, providing a direct relationship with the biochemical content. This approach could potentially enhance breast cancer biopsies assessment and provide additional information to the pathology report.
Publication date: 24 Oct 2023
Project Page: Not provided
Paper: https://arxiv.org/pdf/2310.15094
