Classification of optimal brain tissue using dynamic region growing and fuzzy min-max neural network in brain magnetic resonance images

Abstract

On an MRI scan of the brain, the boundary between endocrine tissues is highly convoluted and irregular. Outdated segmentation algorithms face a severe test. Machine learning as a new sort of learning Here, researchers categorize normal and abnormal tissue using the fuzzy min-max neural network approach, which helps classify normal and abnormal tissues such as GM, CSF, WM, OCS, and OSS. This classification helps to explain the fuzzy min-max neural network method. Osseous Spongy Substance, SCALP, and Osseous Compact Substance are all MRI-classified as aberrant tissue in these tissues. Denoising and improving images can be accomplished using the Gabor filtering technique. Using the filtering method, the tumour component will be accurately identified during the segmentation operation. A dynamically changed region growing approach may be applied to a picture by modifying the Modified Region Growing method's two thresholds. This helps to raise Modified Region Growing's upper and lower bounds. Once the Region Growth is accomplished, the edges may be observed using the Modified Region Growing segmented image's Edge Detection approach. After removing the texture, an entropy-based method may be used to abstract the colour information. After the Dynamic Modified Region Growing phase findings have been merged with those from the texture feature generation phase, a distance comparison within regions is performed to combine comparable areas in the region merging phase. After tissues have been identified, a Fuzzy Min-Max Neural Network may be utilised to categorise them.