Medical image classification labeling method and system and server

Abstract

The invention discloses a medical image classification labeling method and system, and a server, and belongs to the technical field of medical images. The method comprises the steps of obtaining an original medical image and sending the original medical image to a manual annotation terminal; obtaining a manual annotation image returned by the manual annotation terminal, and obtaining a pixel boundary of an annotation area through an edge extraction algorithm; processing the original medical image through a pre-trained full convolutional neural network model to obtain a feature map of which thesize is the size of the original medical image and the depth is the number of annotation types; at the pixel boundary, comparing the feature map with a manual annotation map; if the result of the pixel point on the manual annotation image is consistent with the result of the pixel point on the feature map, not correcting the pixel point; otherwise, selecting a plurality of pixel points around thepixel point on the feature map, and taking the category with the largest number in the plurality of pixel points as the category of the pixel point; and outputting the corrected feature map as a network annotation map.

Description

technical field [0001] The invention belongs to the technical field of medical image processing, and in particular relates to a method, system and server for classifying and labeling medical images. Background technique [0002] Advanced medical imaging technologies such as ultrasound imaging and magnetic resonance imaging technology have produced a large number of two-dimensional and three-dimensional medical images for medical diagnosis. judge. However, compared with conventional images, medical imaging has the characteristics of poor contrast and high noise, resulting in time-consuming diagnosis and error-prone problems. By pre-segmenting and labeling medical images, quantitatively separating the target area from the background area can not only reduce the workload and cost of medical experts in the process of disease diagnosis, but also reduce the error rate of the manual process, thereby improving Diagnostic efficiency and accuracy. [0003] At present, traditional i...

AI Technical Summary

Problems solved by technology

[0003] At present, traditional image segmentation methods based on threshold and edge detection are mostly used in the segmentation processing of medical images. These methods are easily affected by noise, and it is difficult to ensure the continuity and closure of segmentation edges.

Images