A brain tumor MRI image semantic segmentation method

Abstract

The application discloses a brain tumor MRI image semantic segmentation method, and belongs to the technical field of medical image processing and computer-aided diagnosis. The application solves the problem of low segmentation precision based on the existing brain tumor MRI image semantic segmentation technology. The application proposes a semantic segmentation model combining the U-Net architecture with the LWD module, the MFDF module and various filters. The LWD module can keep as much information as possible in the down-sampling process. The MFDF module constructs a new directional gradient feature extraction operator and combines different direction operators by using double-channel filtering, so that the constructed multi-direction filter can extract low-frequency and high-frequency feature direction information respectively. The MFDF module transmits the detail features from the encoding module to the corresponding decoding module, thereby recovering the spatial information including the feature boundary and texture and improving the segmentation precision of the model. The application has good adaptability to the randomness of the shape, size and boundary of the brain tumor. The method can be applied to brain tumor MRI image segmentation.

Images