Bone scanning image hotspot segmentation method and system, medium and equipment

Abstract

The invention provides a bone scanning image hotspot segmentation method and system, a medium and equipment. The method comprises the steps: S1, obtaining a four-dimensional position feature vector; S2, combining the four-dimensional position feature, the 33-dimensional texture feature and the one-dimensional neighborhood contrast feature into an artificial feature of the bone scanning image; S3,constructing a 38-dimensional feature; S4, training a small block level classifier by using MIL to obtain a probability distribution diagram of the hot spots, and obtaining an initial contour similarto the segmentation target through threshold segmentation; and S5, obtaining a bone scanning image hotspot segmentation result by using level set evolution, and obtaining bone scanning image hotspot segmentation result information. The CGAN can be utilized to calculate the position features, and the position features, the texture features and the contrast features are combined into the artificialfeatures of the bone scanning image.

Description

technical field [0001] The present invention relates to the field of medical image segmentation, in particular, to a bone scan image hotspot segmentation method, system, medium and equipment, especially a bone scan image hotspot segmentation method based on conditional generative adversarial network and multi-instance learning. Background technique [0002] Hotspot segmentation of bone scan images is an essential means for clinical diagnosis of tumors and related bone diseases caused by them. When detected, the tumor was much brighter than other areas in the image and was called a "hot spot" in the study. In recent years, with the advancement of computer technology, the research on hot spot segmentation of bone scan images has achieved great development. [0003] In 2004, Yin et al. used local maxima to segment potential hotspots; in 2007, Huang et al. segmented bone scan images into 23 human body regions, and then established a linear regression analysis model through the ...

AI Technical Summary

Problems solved by technology

There is still room for improvement in the effect of bone scan image processing in this patent

Images