Overlapping cervical cell image segmentation method

Abstract

The present invention discloses an overlapping cervical cell segmentation method. The method comprises a method for improving local adaptive nucleus segmentation and an overlapping cytoplasmic segmentation method. The local adaptive segmentation method comprises: solving a sub-image to obtain a gradient histogram, eliminating a block effect by using an equal interval interpolation method, and using the mathematical morphology to suppress image noise, so that the nuclear region can be completely and accurately segmented without omission. The overlapping cell segmentation method comprises: extracting overlapping cytoplasmic parts, performing watershed segmentation on the overlapping cytoplasmic parts, and using the similarity criterion to perform region merging. According to the overlappingcervical cell segmentation method disclosed by the present invention, the problems that the segmentation algorithm is inaccurate in segmentation and easily causes over-segmentation and under-segmentation are solved, the complete cell contour can be extracted, overlapping of cell edges caused by the excessive edge width can be avoided, the complexity of late merging can be reduced, a clearer and more complete cytoplasmic contour can be obtained, and the method is of great significance for cell image classification and pathological detection.

Description

technical field [0001] The invention relates to the technical field of medical image processing, in particular to a method for segmenting overlapping cervical cell images. Background technique [0002] Cervical cancer is one of the common malignant tumors. Although cervical cancer has a high morbidity and mortality rate, early detection and treatment can effectively reduce the risk of death. Therefore, accurate and efficient early detection of cervical cancer cells can help save more women's lives. The quality of cervical cell image segmentation also has a very important impact on the accuracy of the final detection results. An ideal cell image segmentation result will not only reduce the complexity of the subsequent classifier design, but also help to improve the accuracy of the final detection. [0003] At present, there are many cell image segmentation algorithms, which are mainly divided into two categories: cell segmentation algorithms based on region information and ...

AI Technical Summary

Problems solved by technology

The automatic cell segmentation method that can automatically segment the region of interest without manual intervention is the ultimate goal of all segmentation methods. However, automatic segmentation methods usually have high structural complexity, and are not effective in segmenting cell images with complex backgrounds and blurred cell edges. not as expected

Images