Cell image segmentation method based on Mask contour

Abstract

The invention discloses a cell image segmentation method based on a Mask contour. The method comprises the following steps of 1, making a data set; 2, cell feature extraction, which comprises the following steps: 2.1, constructing a feature extraction network; 2.2, performing feature multi-scale fusion; 3, establishinga multi-task branch network, mainly establishing a classification branch network, a segmentation branch network and a Center branch network, and respectively sending the fused features into the multi-task branch network for further operation; 4, generating a target Mask contour:generating the Mask contour of an initial target through deformable convolution and a Graham algorithm; and 5, carrying out segmentation Mask contour refinement on the cell image. According to the cell image segmentation method based on the Mask contour provided by the invention, the complexity of an image segmentation task is reduced, the image segmentation processing time is shortened, and the performance is improved.

Description

technical field [0001] The invention belongs to the field of computer vision and discloses a cell image segmentation method based on Mask outline. Specifically, the segmentation of cell images is realized through the convolutional neural network in deep learning, that is, firstly use the feature extraction network ResNet and FPN to extract and multi-scale fusion the features of the cell, and then use the deformable convolutional network and the Craham algorithm to generate the Mask of the target Contour, and finally the segmentation of the cell image is realized by refining the Mask contour. Background technique [0002] Research at the molecular and cellular level is an important step in the development of new drugs. Especially in recent years, the incidence of cancer and other cellular diseases has been increasing year by year. In our country, more than one million people are diagnosed with cancer every year, and a large number of patients die from cancer. Therefore, the ...

AI Technical Summary

Problems solved by technology

[0004] In order to solve the problems of high complexity and slow processing time in the cell image segmentation of the existing deep learning algorithm, the present invention provides a cell image segmentation method that uses the network to generate a Mask contour for the target and refines the contour

Images