New Strategy to Hyperspectral Image Segmentation Using Principal Components Analysis
摘要
Imaging exams are fundamental in the treatment of various diseases. Through them, it is possible to obtain faster, more accurate and safer diagnoses. Infrared spectroscopy exams help to differentiate healthy tissue from pathological tissue, identifying their characteristics, but this generates a large amount of data that requires a lot of time and computational capacity to process. Thus, this work intends to optimize the pre-processing of micro-FTIR images for cancer diagnosis, using k-means clustering and Principal Component Analysis (PCA).