Exploration of Multi-Scale Image Fusion Systems in Intelligent Medical Image Analysis

The diagnosis of brain cancer relies heavily on medical imaging, with MRI serving as the primary tool. Precise segmentation of brain tumors in MRI scans is essential, and this project seeks to develop a specialized algorithm using the U-Net architecture for this purpose. The proposed approach integrates a residual network and a context information enhancement module, along with a void space convolution pooling pyramid to enable more sophisticated processing. The algorithm was validated using the brain glioma MRI image dataset from the Cancer Imaging Archives. A multi-scale segmentation technique, utilizing a weighted least squares filter, was employed to achieve a more accurate 3D reconstruction of brain tumors, thus improving the precision of the reconstruction. Experimental results show that the local texture features extracted by the algorithm closely match those obtained via laser scanning. By harnessing the U-Net method, the algorithm significantly increased accuracy, enhancing both the precision of image segmentation and the efficiency of image classification.