# Visually-Guided Controllable Medical Image Generation via Fine-Grained Semantic Disentanglement

arXiv: https://arxiv.org/abs/2603.10519 · HTML: https://mlsanity.com/paper/2603.10519/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 21 references that are in the map.
- First posted on arXiv 11 Mar 2026.

## Builds on (most cited first, 16 of 16)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [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)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [Publicly Available Clinical BERT Embeddings](https://mlsanity.com/paper/1904.03323/) (2019)
- [PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis](https://mlsanity.com/paper/2310.00426/) (2023)
- [Kvasir-SEG: A Segmented Polyp Dataset](https://mlsanity.com/paper/1911.07069/) (2019)
- [MAISI: Medical AI for Synthetic Imaging](https://mlsanity.com/paper/2409.11169/) (2024)
- [Anatomical Invariance Modeling and Semantic Alignment for Self-supervised Learning in 3D Medical Image Analysis](https://mlsanity.com/paper/2302.05615/) (2023)
- [MedSegFactory: Text-Guided Generation of Medical Image-Mask Pairs](https://mlsanity.com/paper/2504.06897/) (2025)
- [Medical Image Synthesis via Fine-Grained Image-Text Alignment and Anatomy-Pathology Prompting](https://mlsanity.com/paper/2403.06835/) (2024)
- [Med-Art: Diffusion Transformer for 2D Medical Text-to-Image Generation](https://mlsanity.com/paper/2506.20449/) (2025)
- [VAP-Diffusion: Enriching Descriptions with MLLMs for Enhanced Medical Image Generation](https://mlsanity.com/paper/2506.23641/) (2025)

## Abstract (arXiv)

Medical image synthesis is crucial for alleviating data scarcity and privacy constraints. However, fine-tuning general text-to-image (T2I) models remains challenging, mainly due to the significant modality gap between complex visual details and abstract clinical text. In addition, semantic entanglement persists, where coarse-grained text embeddings blur the boundary between anatomical structures and imaging styles, thus weakening controllability during generation. To address this, we propose a Visually-Guided Text Disentanglement framework. We introduce a cross-modal latent alignment mechanism that leverages visual priors to explicitly disentangle unstructured text into independent semantic representations. Subsequently, a Hybrid Feature Fusion Module (HFFM) injects these features into a Diffusion Transformer (DiT) through separated channels, enabling fine-grained structural control. Experimental results in three datasets demonstrate that our method outperforms existing approaches in terms of generation quality and significantly improves performance on downstream classification tasks. The source code is available at https://github.com/hx111/VG-MedGen.