A novel biomedical image automatic segmentation method based on a U-net network structure

Abstract

The invention belongs to the technical field of image processing and computer vision, and relates to a novel biomedical image automatic segmentation method based on a U-net network structure, including dividing a biomedical data set into a training set and a test set, and normalizing the test set and augmented test set; inputting the images of the training set into the improved U-net network model, and generating a classification probability map by output image passing through a softmax layer; calculating the error between classification probability diagram and gold standard by a centralized loss function, and obtaining the weight parameters of network model by a gradient backpropagation method; entering the images in the test set into the improved U-net network model, and outputting the image to generate a classification probability map through the softmax layer; according to the class probability in the classification probability graph, obtaining the segmentation result graph of theimage. The invention solves the problems that simple samples in the image segmentation process contribute too much to the loss function to learn difficult samples well.

Description

technical field [0001] The invention belongs to the technical field of image processing and computer vision, and in particular relates to a new method for automatically segmenting biomedical images based on a U-net network structure. Background technique [0002] Medical image segmentation is of great significance to 3D positioning, 3D visualization, surgical planning and computer-aided diagnosis, and is one of the hot research fields of image processing and analysis. The methods are divided into manual segmentation, semi-automatic segmentation and automatic segmentation. The manual segmentation method is very time-consuming, and depends on subjective factors such as the knowledge and experience of clinical experts, has poor repeatability, and cannot fully meet the real-time clinical needs. The semi-automatic segmentation method adopts human-computer interaction, which improves the segmentation speed to a certain extent, but still depends on the observer, which limits its a...

AI Technical Summary

Problems solved by technology

[0005] In addition, biomedical images often have the problem of unbalanced distribution of positive and negative samples, and similar samples are also difficult. For example, samples in the edge area of ​​​​the target are more difficult to segment than in the central area.

These two problems will cause the loss function to converge to a bad position, resulting in a reduction in the generalization ability of the model

The focal loss function (Focal loss) was originally applied in the dense target detection task to solve the serious imbalance of samples generated by the Anchor mechanism, the excessive contribution of simple samples to the loss function, and the inability to learn difficult samples well.

Images