Papers
arxiv:2508.12900

CTFlow: Video-Inspired Latent Flow Matching for 3D CT Synthesis

Published on Aug 18, 2025
Authors:
,
,
,

Abstract

A 0.5B latent flow matching transformer generates whole CT volumes from clinical reports using an autoregressive slice sequence approach with improved coherence and alignment.

Generative modelling of entire CT volumes conditioned on clinical reports has the potential to accelerate research through data augmentation, privacy-preserving synthesis and reducing regulator-constraints on patient data while preserving diagnostic signals. With the recent release of CT-RATE, a large-scale collection of 3D CT volumes paired with their respective clinical reports, training large text-conditioned CT volume generation models has become achievable. In this work, we introduce CTFlow, a 0.5B latent flow matching transformer model, conditioned on clinical reports. We leverage the A-VAE from FLUX to define our latent space, and rely on the CT-Clip text encoder to encode the clinical reports. To generate consistent whole CT volumes while keeping the memory constraints tractable, we rely on a custom autoregressive approach, where the model predicts the first sequence of slices of the volume from text-only, and then relies on the previously generated sequence of slices and the text, to predict the following sequence. We evaluate our results against state-of-the-art generative CT model, and demonstrate the superiority of our approach in terms of temporal coherence, image diversity and text-image alignment, with FID, FVD, IS scores and CLIP score.

Community

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2508.12900
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 1

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2508.12900 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2508.12900 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.