GANet-Seg: Adversarial Learning for Brain Tumor Segmentation with Hybrid Generative Models

TL;DR

This paper presents GANet-Seg, a novel brain tumor segmentation framework that combines pre-trained GANs with U-Net architectures, utilizing adversarial learning and synthetic data augmentation to improve accuracy and robustness in clinical MRI analysis.

Contribution

It introduces a hybrid generative model approach for brain tumor segmentation that reduces reliance on fully annotated datasets and enhances segmentation performance.

Findings

Achieved higher lesion-wise Dice scores than baseline methods.

Demonstrated robustness with synthetic image augmentation.

Outperformed existing methods in sensitivity and accuracy on BraTS dataset.

Abstract

This work introduces a novel framework for brain tumor segmentation leveraging pre-trained GANs and Unet architectures. By combining a global anomaly detection module with a refined mask generation network, the proposed model accurately identifies tumor-sensitive regions and iteratively enhances segmentation precision using adversarial loss constraints. Multi-modal MRI data and synthetic image augmentation are employed to improve robustness and address the challenge of limited annotated datasets. Experimental results on the BraTS dataset demonstrate the effectiveness of the approach, achieving high sensitivity and accuracy in both lesion-wise Dice and HD95 metrics than the baseline. This scalable method minimizes the dependency on fully annotated data, paving the way for practical real-world applications in clinical settings.