Chromosome image instance segmentation method and device based on improved Mask RCNN

Abstract

The invention discloses a chromosome image instance segmentation method and device based on an improved Mask RCNN. The method comprises the steps of obtaining each first ROI formed by feature information of each scale in a chromosome image and each corresponding first axis alignment bounding box; correcting the first rotary bounding box in each first ROI to obtain each second rotary bounding box to form a rotary bounding box set; performing NMS operation on the second rotary bounding box according to the angle weighted IOU of the second rotary bounding box and the rotary bounding box set to obtain a final axis alignment bounding box of the first ROI; and according to the final ROI axis alignment bounding box and the corresponding feature information, obtaining a second ROI, inputting the second ROI into a Mask branch, and obtaining a chromosome image segmentation mask. Compared with the prior art, the obtained first ROI is subjected to the NMS operation combined with the angle weightedIOU, so that the problems of excessive inhibition of cross overlapping chromosomes, mutual interference of overlapping monomers during mask regression and the like are solved, and the segmentation effect of the chromosome image is improved.

Description

technical field [0001] The present application relates to the technical field of chromosome karyotype analysis, in particular to a method and device for segmenting chromosome image instances based on improved Mask RCNN. Background technique [0002] Chromosomal karyotype analysis technology refers to the process of pairing, numbering, comparative analysis and diagnosing mutations of chromosomes in the metaphase of biological cell division according to certain regulations according to their inherent number and morphological structure characteristics by means of microscopic banding technology. Including specimen collection, cell culture, chromosome harvesting, chromosome specimen preparation, chromosome staining and banding, microphotography, chromosome image segmentation, chromosome image classification, karyotype map generation, analysis and diagnosis, etc. Wherein, the chromosome image segmentation refers to performing image segmentation on each chromosome target instance f...

AI Technical Summary

Problems solved by technology

Compared with the traditional method, Mask RCNN has greatly improved the baseline level on the general image segmentation dataset, but in the chromosome image segmentation task, due to serious occlusion problems such as chromosome target adhesion and overlap, non-maximum suppression may occur During the (NMS) process, there are problems such as excessive suppression of cross-overlapping chromosomes, and mutual interference of overlapping monomers during mask regression, which makes the segmentation effect of chromosome images still not ideal.

Images