System and image segmentation method for colorectal cancer microsatellite instability prediction

The invention belongs to the technical field of medical image processing, and particularly relates to a system for colorectal cancer microsatellite instability prediction and an image segmentation method. The segmentation method comprises the following steps: reading a multi-resolution image from original full-view slice image data, removing the background of a high-resolution image by using a low-resolution image, and then segmenting the high-resolution image to obtain a plurality of blocks; calculating image entropies of all blocks obtained in the step 1; screening the blocks according to the image entropy, and discarding the blocks with the too low image entropy, so as to obtain an Entropy-mask formed by the remaining blocks; and multiplying the Entropy-mask by a high-resolution image to obtain an effective area after segmentation. The invention also provides a system for predicting the instability of the microsatellite through a machine learning model trained by weak supervised learning by using the segme