DIGITAL PATHOLOGICAL IMAGE QUALITY CONTROL METHOD AND APPARATUS

摘要

The embodiments of the present application are applicable to image detection in the field of artificial intelligence. Disclosed is a digital pathological image quality control method, comprising: according to an image format of a digital pathological image, obtaining an image to be processed of a specified layer of the digital pathological image; inputting the image to be processed into a U-Net segmentation model to obtain a first abnormality probability matrix, corresponding to each pixel point, in the image to be processed, wherein the first abnormality probability matrix comprises a plurality of correlation values; according to a correlation value between each pixel point in the image to be processed and each quality control tag, determining a first quality control tag of each pixel point in the image to be processed; and according to the first quality control tag of each pixel point in the image to be processed, counting the number of pixel points, corresponding to N types of abnormality tags, in the image to be processed, and classifying the digital pathological image. Further correspondingly provided is a digital pathological image quality control apparatus. By means of the present application, quantitative unification of digital pathological image quality control standards can be realized, thereby improving the efficiency of quality control.