Cell image segmentation method based on deep learning

Abstract

The invention discloses a cell image segmentation method based on deep learning, and belongs to the field of image processing. The method specifically comprises the following steps: segmenting cells in test tube holes by using an improved Mask R-CNN (Region-Convolutional Neural Network), obtaining cell images, establishing a digital image data set, fusing feature learning into a model establishing process, and accurately detecting and segmenting the cells in the test tube holes. A quick, low-cost and accurate automatic detection technology is realized, and the detection efficiency can be improved.

Description

technical field [0001] The invention belongs to the field of image processing, and in particular relates to a cell image segmentation method based on deep learning. Background technique [0002] In medical image processing, it is often necessary to segment the cells in the image from the background to analyze changes in their outlines and internal structures, thereby providing a basis for medical identification. Traditional cell image segmentation needs to be done manually, but when the number of cells in the image is large, the manual segmentation method often cannot meet the application requirements in terms of efficiency. Therefore, in recent years, with the continuous development of artificial intelligence, machine learning technology has been gradually introduced into cell image segmentation. This is the inevitable result of the development of both theory and technology, and has extremely promising application prospects. [0003] Machine learning is usually implemented...

AI Technical Summary

Problems solved by technology

[0006] However, compared with other medical images, cell images have higher complexity, and the direct use of Mask R-CNN often has problems of insufficient precision and low accuracy.

Images