An automatic segmentation method of serialize visual human body slice images

Abstract

The invention discloses an automatic segmentation method of serialized visible human body slice images. The method comprises the following steps: S1, selecting a serialized image of a color organ slice image; S2, segmenting the foreground region and the background region of the image by using the minimum cutting algorithm based on the optimized energy function; S3, extracting a seed point image ofa foreground region in the image based on an etching algorithm; S4, extracting a skeleton image of a background region in the image based on a thinning algorithm; S5, segmenting the second image of the serialized image according to the seed point of the foreground region and the skeleton of the background region. This method combines interactive segmentation and serialized automatic segmentation,reduces the robustness of segmentation affected by the complexity of medical images, and also greatly saves the segmentation time. The method has very important practical significance in the segmentation and extraction of human organs, quantitative analysis of human tissues and their pathological regions and other medical fields.

Description

technical field [0001] The invention relates to the technical field of image segmentation, in particular to a method for automatic segmentation of serialized visible human body slice images. Background technique [0002] In recent years, the research on visible human has deepened day by day, making it possible to use the visible human dataset and apply it to practical research. Manually extracting the desired tissues or organs during the 3D redrawing process of the dataset consumes a lot of manpower. Traditional image automatic segmentation algorithms cannot quickly and accurately segment different human tissues with very similar colors. The serialized automatic segmentation method based on spectral analysis and skeleton graffiti can identify the subtle color differences between tissues, and quickly, accurately and effectively separate the human tissues and organs required for research from the huge data set. Provide a reliable source of data for future medical research. ...

AI Technical Summary

Problems solved by technology

However, in this process, technicians need to repeatedly search for the best marked area, and depending on the implementer, the obtained segmentation results are also uneven.

The seed point of the first image is particularly important, which may directly affect the subsequent results, and the extraction of the region of interest in the image has a lot of interference. If the non-interest region has similar pixels to the region of interest, it can also be extracted. Therefore, the subsequent seed point There is a certain error in the transmission

Images