A medical image processing method and device thereof

Abstract

The invention discloses a medical image processing method and device. The method comprises the steps of providing a medical segmentation image, and filling the medical segmentation image. The method is characterized by further comprising the steps of extracting any region of interest, and dividing the region of interest into a first region, a second region and a third region; calculating the feature value Ti of any pixel i in the third region by adopting a first judgment method; and performing secondary judgment on the feature value Ti of any pixel i in the third region to obtain a filled segmentation image. By adopting the method and the device, the non-closed boundary and internal seriously vacant discrete points of the segmentation image can be effectively filled, the boundary can be flexibly adjusted, different smooth filling effects are achieved, the filling accuracy and the robustness are improved, and different diagnosis requirements are met.

Description

technical field [0001] The invention relates to the field of medical information processing, in particular to a medical image processing method and device thereof. Background technique [0002] Medical image reconstruction is to convert a two-dimensional medical image sequence into a three-dimensional image and display it on the screen through computer graphics, digital image processing technology, computer visualization, and human-computer interaction technologies, and provide interactive processing methods for users as needed. Theory, methods and techniques. [0003] In order to accurately distinguish between target tissue and normal tissue in medical images, medical images need to be segmented. Image segmentation is an indispensable means of extracting quantitative information of target tissues in medical images. It is a key step from image processing to image analysis. The accuracy of image segmentation affects the accuracy of image reconstruction, which is crucial to t...

AI Technical Summary

Problems solved by technology

The limitations of this type of method are: 1) Masks with severe internal defects are likely to cause excessive expansion, resulting in a large difference between the final result and the actual required result; 2) It is necessary to judge the strength of expansion and corrosion in advance, only applicable in a relatively simple processing environment

The limitations of this method are: the calculation time is relatively long, more complex logic is required when filling multiple separate masks, and the sensitivity of the parameters is relatively strong, and the parameters need to be adjusted separately for different application scenarios

The limitations of this method are: 1) the radius parameter of the rolling ball needs to be predefined, and there will be problems of over-smoothing or insufficient filling when dealing with masks with different sizes of boundary defects; 2) when filling multiple separate masks and Compared with literature 2, it requires more complex logic, and the sensitivity of parameters is strong

The parameters are not robust to different application scenarios

Images