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

• URL: http://arxiv.org/abs/2508.12900v1
• Date: Mon, 18 Aug 2025 12:58:21 GMT
• Title: CTFlow: Video-Inspired Latent Flow Matching for 3D CT Synthesis
• Authors: Jiayi Wang, Hadrien Reynaud, Franciskus Xaverius Erick, Bernhard Kainz,
• Abstract summary: We introduce CTFlow, a latent flow matching transformer model conditioned on clinical reports.<n>We use the A-VAE from FLUX to define our latent space, and rely on the CT-Clip text encoder to encode the clinical reports.<n>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.
• Score: 7.57931364659531
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• CT-Flow: Orchestrating CT Interpretation Workflow with Model Context Protocol Servers [14.499713300688555]
  Most existing approaches for 3D CT analysis largely rely on static, single-pass inference.<n>By leveraging the Model Context Protocol (MCP), CT-Flow shifts from closed-box inference to an open, tool-aware paradigm.<n>Built upon this, CT-Flow functions as a clinical orchestrator capable of decomposing complex natural language queries into automated tool-use sequences.
  arXiv  Detail & Related papers  (2026-02-23T07:19:30Z)
• BridgeSplat: Bidirectionally Coupled CT and Non-Rigid Gaussian Splatting for Deformable Intraoperative Surgical Navigation [69.14180476971602]
  We introduce BridgeSplat, a novel approach for deformable surgical navigation.<n>Our method rigs 3D Gaussians to a CT mesh, enabling joint optimization of Gaussian parameters and mesh deformation.<n>We demonstrate BridgeSplat's effectiveness on visceral pig surgeries and synthetic data of a human liver under simulation.
  arXiv  Detail & Related papers  (2025-09-23T01:09:36Z)
• Radiology Report Conditional 3D CT Generation with Multi Encoder Latent diffusion Model [0.830525411228399]
  Report2CT is a conditional diffusion framework for synthesizing 3D chest CT volumes directly from free text radiology reports.<n>Report2CT generates anatomically consistent CT volumes with excellent visual quality and text image alignment.
  arXiv  Detail & Related papers  (2025-09-18T09:32:23Z)
• Recurrent Visual Feature Extraction and Stereo Attentions for CT Report Generation [18.113659670915474]
  We propose a large language model (LLM) based CTRG method with recurrent visual feature extraction and stereo attentions for hierarchical feature modeling.<n>Specifically, we use a vision Transformer to recurrently process each slice in a CT volume, and employ a set of attentions over the encoded slices from different perspectives to obtain important visual information.<n>Experiment results and further analysis on the benchmark M3D-Cap dataset show that our method outperforms strong baseline models.
  arXiv  Detail & Related papers  (2025-06-24T14:29:06Z)
• Text-to-CT Generation via 3D Latent Diffusion Model with Contrastive Vision-Language Pretraining [0.8714814768600079]
  We introduce a novel architecture for Text-to-CT generation that combines a latent diffusion model with a 3D contrastive vision-language pretraining scheme.<n>Our method offers a scalable and controllable solution for synthesizing clinically meaningful CT volumes from text.
  arXiv  Detail & Related papers  (2025-05-31T16:41:55Z)
• 3D-CT-GPT: Generating 3D Radiology Reports through Integration of Large Vision-Language Models [51.855377054763345]
  This paper introduces 3D-CT-GPT, a Visual Question Answering (VQA)-based medical visual language model for generating radiology reports from 3D CT scans. Experiments on both public and private datasets demonstrate that 3D-CT-GPT significantly outperforms existing methods in terms of report accuracy and quality.
  arXiv  Detail & Related papers  (2024-09-28T12:31:07Z)
• RadGenome-Chest CT: A Grounded Vision-Language Dataset for Chest CT Analysis [56.57177181778517]
  RadGenome-Chest CT is a large-scale, region-guided 3D chest CT interpretation dataset based on CT-RATE. We leverage the latest powerful universal segmentation and large language models to extend the original datasets.
  arXiv  Detail & Related papers  (2024-04-25T17:11:37Z)
• CT-GLIP: 3D Grounded Language-Image Pretraining with CT Scans and Radiology Reports for Full-Body Scenarios [53.94122089629544]
  We introduce CT-GLIP (Grounded Language-Image Pretraining with CT scans), a novel method that constructs organ-level image-text pairs to enhance multimodal contrastive learning. Our method, trained on a multimodal CT dataset comprising 44,011 organ-level vision-text pairs from 17,702 patients across 104 organs, demonstrates it can identify organs and abnormalities in a zero-shot manner using natural languages.
  arXiv  Detail & Related papers  (2024-04-23T17:59:01Z)
• GuideGen: A Text-Guided Framework for Full-torso Anatomy and CT Volume Generation [1.138481191622247]
  GuideGen is a controllable framework that generates anatomical masks and corresponding CT volumes for the entire torso-from chest to pelvis-based on free-form text prompts. Our approach includes three core components: a text-conditional semantic synthesizer for creating realistic full-torso anatomies; a contrast-aware autoencoder for detailed, high-fidelity feature extraction across varying contrast levels; and a latent feature generator that ensures alignment between CT images, anatomical semantics and input prompts.
  arXiv  Detail & Related papers  (2024-03-12T02:09:39Z)
• GenerateCT: Text-Conditional Generation of 3D Chest CT Volumes [2.410738584733268]
  GenerateCT is the first approach to generating 3D medical imaging conditioned on free-form medical text prompts. We benchmarked GenerateCT against cutting-edge methods, demonstrating its superiority across all key metrics. GenerateCT enables the scaling of synthetic training datasets to arbitrary sizes.
  arXiv  Detail & Related papers  (2023-05-25T13:16:39Z)
• Incremental Cross-view Mutual Distillation for Self-supervised Medical CT Synthesis [88.39466012709205]
  This paper builds a novel medical slice to increase the between-slice resolution. Considering that the ground-truth intermediate medical slices are always absent in clinical practice, we introduce the incremental cross-view mutual distillation strategy. Our method outperforms state-of-the-art algorithms by clear margins.
  arXiv  Detail & Related papers  (2021-12-20T03:38:37Z)
• Efficient Learning and Decoding of the Continuous-Time Hidden Markov Model for Disease Progression Modeling [119.50438407358862]
  We present the first complete characterization of efficient EM-based learning methods for CT-HMM models. We show that EM-based learning consists of two challenges: the estimation of posterior state probabilities and the computation of end-state conditioned statistics. We demonstrate the use of CT-HMMs with more than 100 states to visualize and predict disease progression using a glaucoma dataset and an Alzheimer's disease dataset.
  arXiv  Detail & Related papers  (2021-10-26T20:06:05Z)
• CyTran: A Cycle-Consistent Transformer with Multi-Level Consistency for Non-Contrast to Contrast CT Translation [56.622832383316215]
  We propose a novel approach to translate unpaired contrast computed tomography (CT) scans to non-contrast CT scans. Our approach is based on cycle-consistent generative adversarial convolutional transformers, for short, CyTran. Our empirical results show that CyTran outperforms all competing methods.
  arXiv  Detail & Related papers  (2021-10-12T23:25:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.