Multi-scale network MRI pancreas contour positioning method based on shape constraint

Abstract

The invention discloses a multi-scale network MRI pancreas contour positioning method based on shape constraint, and mainly solves the problem of difficulty in pancreas image segmentation under the conditions of low MRI image contrast and unbalanced samples in the prior art. According to the technical scheme, the method comprises the steps of (1) generating a training set and an annotation set; (2) pre-training a U-net network; (3) constructing a multi-scale network; (4) training a shape constraint network; (5) constructing a shape-constrained multi-scale network; (6) training a shape-constrained multi-scale network; and (7) segmenting a pancreas region in the MRI image. According to the method, the shape information of the pancreas image is utilized, the boundary and region information iscombined for image segmentation, the pancreas region in the MRI image can be well positioned, the method has the advantage of high segmentation precision, and the method can be used for automaticallypositioning and segmenting the pancreas tissue contour in the human abdomen MRI image.

Description

technical field [0001] The invention belongs to the technical field of image processing, and further relates to a shape-constrained multi-scale network MRI (Magnetic Resonance Imaging) pancreas contour positioning method in the technical field of image segmentation. The invention can be used for automatic positioning and segmentation of the pancreas tissue outline in the MRI image of the human abdomen. Background technique [0002] At present, the automatic segmentation technology of pancreas in MRI images is mainly realized by the segmentation algorithm based on multi-organ atlas, the segmentation algorithm based on shape model and the segmentation algorithm based on neural network. Multi-organ atlas-based algorithms use atlases of multiple abdominal organs, employ image registration for image alignment, and rely on previously generated atlases to predict the boundaries of the pancreas. Shape model-based algorithms achieve segmentation by updating the pancreas-labeled prob...

AI Technical Summary

Problems solved by technology

The disadvantage of this method is that the two constructed convolutional neural network models (CNN) are only used for pancreas detection and boundary segmentation, and the local features of the MRI pancreas image to be segmented are not considered during the network training process. There are often discontinuities in the segmentation results, and it is easy to divide the pancreas area in the MRI image into other areas, which affects the segmentation accuracy of the pancreas area in the MRI image

The disadvantage of this method is that when compressing the original image to train a Q-net model to calculate the approximate position of the pancreas, the trained model is sensitive to the color and texture information of the MRI image, ignoring the shape information of the pancreas in the MRI image, resulting in The segmentation results of the image do not accurately delineate the edges of the pancreas region in the MRI image

Images