# From Alignment to Synthesis: Contrastive Volumetric Grounding for Text-to-CT Generation

arXiv: https://arxiv.org/abs/2506.00633 · HTML: https://mlsanity.com/paper/2506.00633/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models.
- Builds on 31 of its 47 references that are in the map.
- First posted on arXiv 31 May 2025.

## Placed in

- Diffusion models / [Medical imaging and segmentation](https://mlsanity.com/diffusion/medical-imaging-and-segmentation/)

## Builds on (most cited first, 30 of 31)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [Contrastive Learning with Hard Negative Samples](https://mlsanity.com/paper/2010.04592/) (2020)
- [BiomedCLIP: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs](https://mlsanity.com/paper/2303.00915/) (2023)
- [ClinicalBERT: Modeling Clinical Notes and Predicting Hospital Readmission](https://mlsanity.com/paper/1904.05342/) (2019)
- [Hard Negative Mixing for Contrastive Learning](https://mlsanity.com/paper/2010.01028/) (2020)
- [Making the Most of Text Semantics to Improve Biomedical Vision--Language Processing](https://mlsanity.com/paper/2204.09817/) (2022)
- [Med3D: Transfer Learning for 3D Medical Image Analysis](https://mlsanity.com/paper/1904.00625/) (2019)
- [Diffusion Models for Medical Image Analysis: A Comprehensive Survey](https://mlsanity.com/paper/2211.07804/) (2022)
- [Brain Imaging Generation with Latent Diffusion Models](https://mlsanity.com/paper/2209.07162/) (2022)
- [Generalist Foundation Models from a Multimodal Dataset for 3D Computed Tomography](https://mlsanity.com/paper/2403.17834/) (2024)
- [MAISI: Medical AI for Synthetic Imaging](https://mlsanity.com/paper/2409.11169/) (2024)
- [CXR-CLIP: Toward Large Scale Chest X-ray Language-Image Pre-training](https://mlsanity.com/paper/2310.13292/) (2023)
- [Machine-Learning-Based Multiple Abnormality Prediction with Large-Scale Chest Computed Tomography Volumes](https://mlsanity.com/paper/2002.04752/) (2020)
- [GenerateCT: Text-Conditional Generation of 3D Chest CT Volumes](https://mlsanity.com/paper/2305.16037/) (2023)
- [Hierarchical Amortized Training for Memory-efficient High Resolution 3D GAN](https://mlsanity.com/paper/2008.01910/) (2020)
- [MedSyn: Text-guided Anatomy-aware Synthesis of High-Fidelity 3D CT Images](https://mlsanity.com/paper/2310.03559/) (2023)
- [Text encoders bottleneck compositionality in contrastive vision-language models](https://mlsanity.com/paper/2305.14897/) (2023)
- [A Flexible 2.5D Medical Image Segmentation Approach with In-Slice and Cross-Slice Attention](https://mlsanity.com/paper/2405.00130/) (2024)
- [XGeM: A Multi-Prompt Foundation Model for Multimodal Medical Data Generation](https://mlsanity.com/paper/2501.04614/) (2025)

## Built on by (most cited first, 6 of 6)

- [Radiology Report Conditional 3D CT Generation with Multi Encoder Latent diffusion Model](https://mlsanity.com/paper/2509.14780/) (2025)
- [Retrieval-Augmented Anatomical Guidance for Text-to-CT Generation](https://mlsanity.com/paper/2603.08305/) (2026)
- [No Caption, No Problem: Caption-Free Membership Inference via Model-Fitted Embeddings](https://mlsanity.com/paper/2602.22689/) (2026)
- [CTForensics: A Comprehensive Dataset and Method for AI-Generated CT Image Detection](https://mlsanity.com/paper/2603.01878/) (2026)
- [MedSyn2: Flexible Control of 3D CT Generation via Text and Semantically-Defined Segmentation Prompts](https://mlsanity.com/paper/2606.00967/) (2026)
- [Evidence-Based Text-Conditioned 3D CT Synthesis for Ovarian Cancer](https://mlsanity.com/paper/2606.28980/) (2026)

## Abstract (arXiv)

Generating semantically controllable 3D CT volumes from radiology reports requires more than a rich text encoder, it requires vision-language alignment grounded in volumetric space. Existing Text-to-CT approaches condition generation on encoders pretrained with language only or 2D vision-language objectives, providing conditioning signals that are linguistically expressive but volumetrically blind. We argue this is a structural limitation: the quality of 3D vision-language alignment, not the richness of the text encoder, is the primary bottleneck for semantic controllability in volumetric diffusion models. To address this, we propose a generation-oriented 3D-CLIP encoder trained with structured hard negatives that operate exclusively at the text level. This design increases contrastive difficulty without any additional 3D memory cost, overcoming the small-batch constraints inherent to volumetric encoders. The resulting encoder conditions a fully end-to-end latent diffusion model that operates directly in 3D latent space, eliminating the spatial artifacts and cross-slice inconsistencies introduced by super-resolution pipelines. Through systematic ablations, we establish a clear empirical link between grounding quality and downstream generative controllability. Evaluated on CT-RATE across 18 pathological conditions, our method achieves state-of-the-art performance on both image fidelity and factual correctness, while requiring less inference time and GPU memory than all competing methods. Code is at https://github.com/danielemolino/Text2CT.