用压缩数据训练3D脑肿瘤MRI生成模型，效果几乎无损。
MRIComp4Flow: Compression of 3D Brain MRI for Training Multi-Modal Generative Models
- 用JPEG2000压缩3D脑MRI，保持生成模型训练所需细节。
- 20:1压缩比下，合成图像质量与原始数据无显著差异（PSNR差<1dB）。
- 适合想在普通设备上训练大模型的研究者，降低存储成本。
大规模多模态MRI数据集带来巨大的存储和读写开销，限制了在常规硬件上训练3D生成模型。尽管有损压缩被证明对判别性分割网络有效，但其对需学习完整数据分布的生成模型的影响尚未明确。本文研究标准图像编码器能否有效压缩语义丰富的脑肿瘤MRI，同时保留训练和部署3D MRI生成模型所需的保真度。每个3D体积使用JPEG2000或近无损的JPEG-LS进行压缩。随后，在压缩数据上训练一个以BraTS图像序列（T1n, T1c, T2, T2f）为条件的波浪流匹配模型，并在验证集上评估性能。在20:1压缩比下，合成质量与未压缩数据训练的模型在预设范围内无显著差异（ΔPSNR <1 dB，ΔSSIM <0.02；配对等效性检验p=[[p]]）：平均PSNR为27.3 dB vs. 27.0 dB，平均SSIM为0.95 vs. 0.96（跨模态）。结果表明，JPEG2000压缩是实现可扩展3D MRI生成建模且不降低合成质量的实用方案。代码已开源：https://github.com/lisafis/MRIComp4Flow。
原文摘要 · Abstract (English)
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 ($Δ$PSNR $<1$,dB, $Δ$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 .
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。