Forecasting Intrathecal Tracer Enhancement from Pre-Contrast Brain MRI: Direct Regression versus Flow Matching
On the map: Diffusion models → Medical imaging and segmentation
Abstract (arXiv)
Intrathecal contrast-enhanced MRI tracks how a cerebrospinal-fluid tracer spreads through the brain, but requires repeated scans over 24--48,h. Forecasting enhancement from a pre-contrast scan could one day help select patients for intrathecal drug treatment and plan their dose. We ask how much of the enhancement at a given time can be predicted from the pre-contrast scan and the elapsed time alone. Training on 104 patients, we compared direct image-to-image regression (I2I) with conditional flow matching (CFM) using the same 3D U-Net and protocol, and tested on 23 held-out patients and 51 external patients with normal pressure hydrocephalus. All models were measured against simply copying the pre-contrast scan. I2I removed about 60% of this copying error internally and 25% externally, outperformed CFM on both test sets (mean absolute error 0.036 vs. 0.058 and 0.056 vs. 0.063), and predicted each volume in a single forward pass, whereas CFM ran its network ten times. CFM uncertainty located errors but was poorly calibrated. Much of tracer enhancement is thus predictable from anatomy and timing, and direct regression is the more accurate and cheaper choice at this data scale.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models. Builds on 20 of its 37 references that are in the map. First posted on arXiv 17 Sep 2026.
Builds on
20 of 37 references.
Closest ancestors · 3
Same direction, newest first
- 2025Temporal Flow Matching for Learning Spatio-Temporal Trajectories in 4D Longitudinal Medical Imaging29 Aug
- 2024Enhancing Spatiotemporal Disease Progression Models via Latent Diffusion and Prior Knowledge6 May
- 2022SADM: Sequence-Aware Diffusion Model for Longitudinal Medical Image Generation16 Dec
Other references · 17
- 2020Denoising Diffusion Probabilistic Modelscited by 20,851
- 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
- 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
- 2022Flow Matching for Generative Modelingcited by 5,426
- 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
- 2017FiLM: Visual Reasoning with a General Conditioning Layercited by 2,286
- 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,170
- 2018Group Normalizationcited by 1,514
- 20163D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotationcited by 1,471
- 2023Improving and generalizing flow-based generative models with minibatch optimal transportcited by 835
- 2022MONAI: An open-source framework for deep learning in healthcarecited by 438
- 2023Inversion by Direct Iteration: An Alternative to Denoising Diffusion for Image Restorationcited by 164
5 more
- 2019FastSurfer -- A fast and accurate deep learning based neuroimaging pipelinecited by 110
- 2022Investigating molecular transport in the human brain from MRI with physics-informed neural networkscited by 24
- 2019Degenerative Adversarial NeuroImage Nets: Generating Images that Mimic Disease Progressioncited by 21
- 2024ImageFlowNet: Forecasting Multiscale Image-Level Trajectories of Disease Progression with Irregularly-Sampled Longitudinal Medical Imagescited by 19
- 2026Beyond Random Partitioning: Unsupervised Spatio-Temporal Stratification for Cohort Balancing in Longitudinal Medical Imagingcited by 1
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025Synthesizing Accurate and Realistic T1-weighted Contrast-Enhanced MR Images using Posterior-Mean Rectified Flow
- 2026Rectified flow-based prediction of post-treatment brain MRI from pre-radiotherapy priors for patients with glioma
- 2024Conditional Generative Models for Contrast-Enhanced Synthesis of T1w and T1 Maps in Brain MRI
- 2024Towards Learning Contrast Kinetics with Multi-Condition Latent Diffusion Models
- 2026Contrast-X: A Multi-Modal Contrast Image Synthesis Benchmark and Universal Modality Flow Matching
- 2024CAVM: Conditional Autoregressive Vision Model for Contrast-Enhanced Brain Tumor MRI Synthesis
- 2023Diffusion Models for Contrast Harmonization of Magnetic Resonance Images
- 2025Comparing Conditional Diffusion Models for Synthesizing Contrast-Enhanced Breast MRI from Pre-Contrast Images