Revolutionizing Brain Tumor Imaging: Generating Synthetic 3D FA Maps from T1-Weighted MRI using CycleGAN Models

TL;DR

This paper introduces a CycleGAN-based method to generate synthetic FA maps from T1-weighted MRI scans, improving neuroimaging analysis by addressing spatial misalignment issues, especially in tumor regions.

Contribution

It is the first to apply CycleGAN models for generating FA maps from T1-weighted MRI in both healthy and tumor-affected tissues, enabling unpaired data training.

Findings

High fidelity FA maps generated with strong SSIM and PSNR scores.

Robust performance in tumor regions demonstrated by evaluation metrics.

Potential to streamline clinical workflows by reducing additional scans.

Abstract

Fractional anisotropy (FA) and directionally encoded colour (DEC) maps are essential for evaluating white matter integrity and structural connectivity in neuroimaging. However, the spatial misalignment between FA maps and tractography atlases hinders their effective integration into predictive models. To address this issue, we propose a CycleGAN based approach for generating FA maps directly from T1-weighted MRI scans, representing the first application of this technique to both healthy and tumour-affected tissues. Our model, trained on unpaired data, produces high fidelity maps, which have been rigorously evaluated using Structural Similarity Index (SSIM) and Peak Signal-to-Noise Ratio (PSNR), demonstrating particularly robust performance in tumour regions. Radiological assessments further underscore the model's potential to enhance clinical workflows by providing an AI-driven alternative that reduces the necessity for additional scans.