Method and Apparatus for Segmentation Algorithm Evaluation Based on Anatomical Priors

Abstract

The present invention provides a method and device for evaluating a segmentation algorithm based on anatomical prior, the method comprising: performing shape processing on the relative position information of the center point coordinates of each segmentation target area according to an active shape model algorithm and a Platts analysis method, Obtain the processed shape; according to the training sample set data, calculate the mean value of the processed shape, the eigenvalue of the covariance matrix and the eigenvector value of the covariance matrix; according to the mean value of the processed shape, the characteristics of the covariance matrix vector value, the shape coefficient value is obtained; according to the shape coefficient value and the eigenvalue of the covariance matrix, the relative position stability of the total segmentation target region is obtained; according to the segmentation deviation value of each segmentation target region, each segmentation target region is obtained The unique prior of ; according to the stable prior of the relative position of the total segmentation target area and the unique prior of each segmentation target area, the training model is obtained, and the current segmentation algorithm is evaluated.

Description

technical field [0001] The present invention relates to the field of medical imaging, in particular, to a method and device for evaluating segmentation algorithms based on anatomical priors. Background technique [0002] Medical image analysis methods based on deep learning models have received more and more attention. In order to achieve good analysis results, it is necessary to label a large amount of data for model training and testing. Since high-quality medical data annotation requires doctors to have rich experience, it is very important to select the most informative data for annotation by evaluating the effect of existing models when annotation resources are limited. [0003] The existing segmentation algorithm evaluation methods are mainly divided into two categories. One is to calculate the evaluation index value directly based on the difference between the segmentation result and the annotation when there is an annotation, but this method is obviously not suitab...

AI Technical Summary

Problems solved by technology

There are two problems in doing this. One is that the training time is long, which makes the iterative update of the model slow; the other is that a large number of features need to be manually designed, but the anatomical prior information of the task itself is not fully utilized.

Images