Segmentation of MRI tumors and pelvic anatomy via cGAN-synthesized data and attention-enhanced U-Net

Open Webpage

Mudassar Ali, Haoji Hu, Tong Wu, Maryam Mansoor, Qiong Luo, Weizeng Zheng, Neng Jin

Published: 2025, Last Modified: 02 Aug 2025Pattern Recognit. Lett. 2025EveryoneRevisionsBibTeXCC BY-SA 4.0
Abstract: Highlights•Pioneering cGAN-based technique revolutionizes MRI tumor segmentation accuracy.•Patch discriminator integration crafts ultra-realistic synthetic MRI datasets.•Attention-augmented U-Net model dramatically boosts feature-focused segmentation.•Synthetic data innovation bridges the gap of limited annotated medical imagery.•Achieves unprecedented precision in brain, liver, and pelvic MRI segmentation tasks.