Biomedical Optics Express · 2019 · 31 citations · 25 references
MedicineOncologyPathologyComputer VisionHistopathologySurgical PathologyCancer DetectionCancer DiagnosisComputer-aided DiagnosisHyperspectral ImagingPancreatic CancerTumor DetectionHyperspectral AnalysisHyperspectral Imagery AnalysisImage-based Tumor DetectionPancreatic Cancer DetectionPathology Image AnalysisSupport Vector ClassificationSupport Vector Machine ClassificationTissue Microarray Analysis
Hyperspectral imaging (HSI) provides more detailed information than red-green-blue (RGB) imaging, and therefore has potential applications in computer-aided pathological diagnosis. This study aimed to develop a pattern recognition method based on HSI, called hyperspectral analysis of pathological slides based on stain spectrum (HAPSS), to detect cancers in hematoxylin and eosin-stained pathological slides of pancreatic tumors. The samples, comprising hyperspectral cubes of 420-750 nm, were harvested for HSI and tissue microarray (TMA) analysis. As a result of conducting HAPSS experiments with a support vector machine (SVM) classifier, we obtained maximal accuracy of 94%, a 14% improvement over the widely used RGB images. Thus, HAPSS is a suitable method to automatically detect tumors in pathological slides of the pancreas.
25
Leo Breiman · Machine Learning · 2001 · 126.2K citations · Full text
Hematoxylin and Eosin Staining of Tissue and Cell Sections
Andrew H. Fischer, Kenneth A. Jacobson, Jack Rose et al. · Cold Spring Harbor Protocols · 2008 · 2.1K citations
Imaging Spectrometry for Earth Remote Sensing
Alexander Goetz, Gregg Vane, Jerry E. Solomon et al. · Science · 1985 · 1.9K citations