Conditional Generative Diffusion Deep Learning for Accelerated Diffusion Tensor and Kurtosis Imaging

Purpose The purpose of this study was to develop DiffDL, a generative diffusion probabilistic model designed to produce high-quality diffusion tensor imaging (DTI) and diffusion kurtosis imaging (DKI) metrics from a reduced set of diffusion-weighted images (DWIs). This model addresses the challenge of prolonged data acquisition times in diffusion MRI while preserving metric accuracy. Methods DiffDL was trained using data from the Human Connectome Project, including 300 training/validation subjects and 50 testing subjects. High-quality DTI and DKI metrics were generated using many DWIs and combined with subsets of DWIs to form training pairs. A UNet architecture was used for denoising, trained over 500 epochs with a linear noise schedule. Performance was evaluated against conventional DTI/DKI modeling and a reference UNet model using normalized mean absolute error (NMAE), peak signal-to-noise ratio (PSNR), and Pearson correlation coefficient (PCC). Results DiffDL showed significant improvements in the quality and accuracy of fractional anisotropy (FA) and mean diffusivity (MD) maps compared to conventional methods and the baseline UNet model. For DKI metrics, DiffDL outperformed conventional DKI modeling and the UNet model across various acceleration scenarios. Quantitative analysis demonstrated superior NMAE, PSNR, and PCC values for DiffDL, capturing the full dynamic range of DTI and DKI metrics. The generative nature of DiffDL allowed for multiple predictions, enabling uncertainty quantification and enhancing performance. Conclusion The DiffDL framework demonstrated the potential to significantly reduce data acquisition times in diffusion MRI while maintaining high metric quality. Future research should focus on optimizing computational demands and validating the model with clinical cohorts and standard MRI scanners.