Fast and Label-Free Automated Detection of Microsatellite Status in Early Colon Cancer Using Artificial Intelligence Integrated Infrared Imaging

Dimensionality reduction for deep learning in infrared microscopy: a comparative computational survey

“…This finding, however, cannot be transferred to arbitrary settings: our results do not exclude that in other settings, e.g. when dealing with classifying or localizing cancer subtypes, 8,42,43 performance could suffer significantly under dimensionality reduction. The same holds for neural network topologies other than the CompSegNet investigated here, which could potentially be more or less sensitive to dimensionality reduction.…”

“…4,5 In an infrared microscopic image, the absorbance spectra at each pixel position represent fingerprints of the biochemical composition. As has been demonstrated in numerous studies, 3,[6][7][8] the highly resolved molecular information can be utilised to precisely localize different tissue components, 3 recognize tumor, 5 or distinguish different tumor subtypes 6,8 with high sensitivity and specificity.…”