MRIComp4Flow: Compression of 3D Brain MRI for Training Multi-Modal Generative Models

A new study finds that JPEG2000 compression at a 20:1 ratio preserves the quality of 3D brain MRI generative models, with synthesis quality statistically equivalent to uncompressed training (mean PSNR 27.3 dB vs. 27.0 dB, mean SSIM 0.95 vs. 0.96). The research, led by authors of the MRIComp4Flow codebase, demonstrates that lossy compression can reduce storage and I/O costs for large-scale multi-modal MRI datasets without degrading generative model performance. The code is available at https://github.com/lisafis/MRIComp4Flow.

arXiv:2608.10291v1 Announce Type: new Abstract: Large-scale multi-modal MRI datasets impose substantial storage and I/O costs, limiting the training of 3D generative models on commodity infrastructure. While lossy compression is known to preserve accuracy for discriminative segmentation networks, its effect on generative models, which must learn the full data distribution rather than a decision boundary, is unexplored. We study whether standard image codecs can effectively compress semantically rich brain tumor MRI while preserving the fidelity required to train and deploy a 3D MRI generative model. Each 3D volume is compressed with JPEG2000 or a near-lossless JPEG-LS pipeline. Next, a Wavelet Flow Matching model, conditioned on BraTS image sequences T1n, T1c, T2, T2f , is trained on compressed data, and the resulting models are evaluated on the validation set. At a 20:1 compression ratio, synthesis quality is statistically equivalent to a model trained on uncompressed data within a pre-specified margin $\Delta$PSNR $<1$,dB, $\Delta$SSIM $<0.02$; paired TOST $p= p $ : mean PSNR is 27.3,dB vs. 27.0,dB and mean SSIM is 0.95 vs. 0.96 across modalities. Our results indicate that JPEG2000 compression is a practical step toward scalable 3D MRI generative modeling without degrading synthesis quality. The codebase is available at https://github.com/lisafis/MRIComp4Flow .