DETECTION OF TISSUE REGIONS IN MICROSCOPE SLIDE IMAGES

摘要

According to one embodiment, the invention relates to a computer implemented method for detecting tissue samples in low resolution microscopic images comprising: obtaining an image of a microscopic tissue slide using at least one processor; segmenting the image with the processor into a plurality of regions using either (a) a maximum posterior marginal probability (MPM) process with a Gaussian Markov Random Field (GMRF), or (b) a maximum a posteriori (MAP) estimation with a discrete Markov Random Field (MRF); and classifying the plurality of regions into a background region and a tissue region to form a binary mask. The method may also comprise applying an active contour method to the binary mask to refine the tissue boundary. The invention also relates to a computer implemented system comprising a memory and a processor that is programmed to carry out the tissue detection method.