Brain tumor segmentation using particle swarm optimized histogram equalization and a VGG19 based U-Net
Nature
Read the full article
Researchers developed SPOHE-VGGNet, a brain tumor segmentation model combining a modified U-Net with VGG-19 and Particle Swarm Optimized Histogram Equalization to enhance MRI contrast and segmentation accuracy. Evaluated on Figshare and BraTS 2021 datasets, it achieved Dice scores above 0.94 across tumor types, improving over existing methods.
