Follicle ultrasonic processing method and system based on level set image segmentation

Abstract

The invention provides a follicle ultrasonic processing method and system based on level set image segmentation, and the method comprises the steps: carrying out the image enhancement of a follicle ultrasonic image through preprocessing, and obtaining a high-quality preprocessing image; dividing the preprocessed image into a plurality of regions according to the gray scale distribution characteristics of the ultrasonic image, respectively calculating the region threshold of each region, and carrying out the gray scale adaptive segmentation of each region based on the region threshold; carryingout secondary segmentation on the pre-segmentation region by adopting level set image segmentation, and enhancing the difference between a follicle region and a non-follicle region in the pre-segmentation region to obtain a suspected follicle region; and partitioning the suspected follicle region based on a decision tree and a bagging algorithm, extracting an independent complete follicle area inthe suspected follicle area, and performing follicle quality scoring evaluation. The problems of strong subjectivity, few quantitative indexes and the like in ultrasonic follicle monitoring are solved; automatic segmentation of follicle ultrasonic images is achieved, the diagnosis process is optimized, the diagnosis quality is improved and the labor intensity of medical workers is relieved.

Description

technical field [0001] The present invention relates to the fields of image enhancement, image noise reduction and image segmentation, in particular, to a method and system for ultrasonic treatment of follicles based on level set image segmentation, especially to image noise reduction and adaptive histogram based on bilateral filtering Image processing method of ultrasound images of follicles with enhancement, pre-segmentation based on gray adaptive threshold and secondary segmentation based on level set method-CV model, and digital quantitative evaluation of follicle quality by least square method. Background technique [0002] Medical image segmentation is a development process from completely relying on manual segmentation to realizing semi-manual and semi-automatic segmentation, and then slowly moving towards fully automatic segmentation. Early medical image segmentation relied on manual segmentation to delineate the desired region boundaries on the image. Semi-automati...

AI Technical Summary

Problems solved by technology

[0004] However, the current research on follicle ultrasound image processing is still relatively lacking. Compared with other medical ultrasound images, follicle ultrasound images have small target areas and inconsistent numbers. And the shape is different, it is difficult to directly apply other ultrasonic image processing methods

Images