Hip joint X-ray image segmentation method and system based on local vision clue

Abstract

The invention relates to a hip joint X-ray image segmentation method and system based on a local vision clue. The method comprises the following steps: preprocessing the image data in the data set; learning a first-layer convolution block feature of the standard U-net network; obtaining a rough label by using a Sobel operator; extracting a local visual clue LVC through the first convolution blockfeature and the rough label; combining LVC with an S-loss loss function to guide a U-net network to output a preliminary segmentation result graph; utilizing LVC to generate LVC local visual guidance,outputting a sampling offset field with the preliminary segmentation result image through a deformable spatial transformation network, and resampling the preliminary segmentation result image to obtain a final segmentation result of the image. According to the method, the problem that a supervised learning model is easily influenced by label noise in the medical image segmentation process is solved, and the complexity of medical image label generation is reduced.

Description

technical field [0001] The invention belongs to the technical field of deep learning and computer vision. Specifically, it relates to a weakly supervised hip image segmentation method based on local visual cues to automatically correct semantic segmentation errors. Background technique [0002] Convolutional neural networks have achieved very good results in the field of computer vision and are excellent image feature extractors for various image tasks. However, computerized tomography CT images, magnetic resonance imaging MRI images, and X-ray (X-ray) images in the medical field are very different from natural images due to the difficulty in data labeling and small amount of data, which leads to convolutional neural networks. It cannot be well applied to medical images. [0003] In the medical field of hip dysplasia, the screening of developmental dysplasia of the hip (DDH) mainly relies on the doctor's geometric angle calculation and observation. For hip joint segmentat...

AI Technical Summary

Problems solved by technology

However, the classic full convolution segmentation algorithm requires a large amount of accurate data annotation, and the data annotation resources are very limited in the medical field.

Images