Revolutionizing Brain Tumor Imaging: Generating Synthetic 3D FA Maps from T1-Weighted MRI using CycleGAN Models
This work addresses a domain-specific problem for neuroimaging and clinical workflows by providing an AI-driven alternative to reduce the need for additional scans, though it is incremental as it applies an existing method to new data.
The paper tackled the spatial misalignment between FA maps and tractography atlases in neuroimaging by proposing a CycleGAN-based approach to generate synthetic 3D FA maps from T1-weighted MRI scans, achieving high fidelity as measured by SSIM and PSNR, with robust performance in tumour regions.
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.