Generate to Ground: Multimodal Text Conditioning Boosts Phrase Grounding in Medical Vision-Language Models

• URL: http://arxiv.org/abs/2507.12236v1
• Date: Wed, 16 Jul 2025 13:48:32 GMT
• Title: Generate to Ground: Multimodal Text Conditioning Boosts Phrase Grounding in Medical Vision-Language Models
• Authors: Felix Nützel, Mischa Dombrowski, Bernhard Kainz,
• Abstract summary: We show that generative text-to-image diffusion models can achieve superior zero-shot phrase grounding performance.<n>Results establish generative approaches as a more effective paradigm for phrase grounding in the medical imaging domain.
• Score: 6.408114351192012
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Phrase grounding, i.e., mapping natural language phrases to specific image regions, holds significant potential for disease localization in medical imaging through clinical reports. While current state-of-the-art methods rely on discriminative, self-supervised contrastive models, we demonstrate that generative text-to-image diffusion models, leveraging cross-attention maps, can achieve superior zero-shot phrase grounding performance. Contrary to prior assumptions, we show that fine-tuning diffusion models with a frozen, domain-specific language model, such as CXR-BERT, substantially outperforms domain-agnostic counterparts. This setup achieves remarkable improvements, with mIoU scores doubling those of current discriminative methods. These findings highlight the underexplored potential of generative models for phrase grounding tasks. To further enhance performance, we introduce Bimodal Bias Merging (BBM), a novel post-processing technique that aligns text and image biases to identify regions of high certainty. BBM refines cross-attention maps, achieving even greater localization accuracy. Our results establish generative approaches as a more effective paradigm for phrase grounding in the medical imaging domain, paving the way for more robust and interpretable applications in clinical practice. The source code and model weights are available at https://github.com/Felix-012/generate_to_ground.

Related papers

• Anatomy-Grounded Weakly Supervised Prompt Tuning for Chest X-ray Latent Diffusion Models [8.94567513238762]
  We show that a standard text-conditioned Latent Diffusion Model has not learned to align clinically relevant information in free-text radiology reports with the corresponding areas of the given scan.<n>We propose a fine-tuning framework to improve multi-modal alignment in a pre-trained model such that it can be efficiently repurposed for downstream tasks such as phrase grounding.
  arXiv  Detail & Related papers  (2025-06-12T12:19:18Z)
• Zero-Shot Medical Phrase Grounding with Off-the-shelf Diffusion Models [12.264115733611058]
  The task of performing localization with textual guidance is commonly referred to as phrase grounding.<n>We use a publicly available Foundation Model, namely the Latent Diffusion Model, to perform this challenging task.<n>Results on a popular chest X-ray benchmark indicate that our method is competitive with SOTA on different types of pathology.
  arXiv  Detail & Related papers  (2024-04-19T14:43:48Z)
• Uncertainty-aware Medical Diagnostic Phrase Identification and Grounding [72.18719355481052]
  We introduce a novel task called Medical Report Grounding (MRG)<n>MRG aims to directly identify diagnostic phrases and their corresponding grounding boxes from medical reports in an end-to-end manner.<n>We propose uMedGround, a robust and reliable framework that leverages a multimodal large language model to predict diagnostic phrases.
  arXiv  Detail & Related papers  (2024-04-10T07:41:35Z)
• On the Multi-modal Vulnerability of Diffusion Models [56.08923332178462]
  We propose MMP-Attack to manipulate the generation results of diffusion models by appending a specific suffix to the original prompt.<n>Our goal is to induce diffusion models to generate a specific object while simultaneously eliminating the original object.
  arXiv  Detail & Related papers  (2024-02-02T12:39:49Z)
• R&B: Region and Boundary Aware Zero-shot Grounded Text-to-image Generation [74.5598315066249]
  We probe into zero-shot grounded T2I generation with diffusion models. We propose a Region and Boundary (R&B) aware cross-attention guidance approach.
  arXiv  Detail & Related papers  (2023-10-13T05:48:42Z)
• DiffDis: Empowering Generative Diffusion Model with Cross-Modal Discrimination Capability [75.9781362556431]
  We propose DiffDis to unify the cross-modal generative and discriminative pretraining into one single framework under the diffusion process. We show that DiffDis outperforms single-task models on both the image generation and the image-text discriminative tasks.
  arXiv  Detail & Related papers  (2023-08-18T05:03:48Z)
• Discffusion: Discriminative Diffusion Models as Few-shot Vision and Language Learners [88.07317175639226]
  We propose a novel approach, Discriminative Stable Diffusion (DSD), which turns pre-trained text-to-image diffusion models into few-shot discriminative learners. Our approach mainly uses the cross-attention score of a Stable Diffusion model to capture the mutual influence between visual and textual information.
  arXiv  Detail & Related papers  (2023-05-18T05:41:36Z)
• Zero-shot Medical Image Translation via Frequency-Guided Diffusion Models [9.15810015583615]
  We propose a frequency-guided diffusion model (FGDM) that employs frequency-domain filters to guide the diffusion model for structure-preserving image translation. Based on its design, FGDM allows zero-shot learning, as it can be trained solely on the data from the target domain, and used directly for source-to-target domain translation. FGDM outperformed the state-of-the-art methods (GAN-based, VAE-based, and diffusion-based) in metrics of Frechet Inception Distance (FID), Peak Signal-to-Noise Ratio (PSNR), and Structural Similarity
  arXiv  Detail & Related papers  (2023-04-05T20:47:40Z)
• Learning to Exploit Temporal Structure for Biomedical Vision-Language Processing [53.89917396428747]
  Self-supervised learning in vision-language processing exploits semantic alignment between imaging and text modalities. We explicitly account for prior images and reports when available during both training and fine-tuning. Our approach, named BioViL-T, uses a CNN-Transformer hybrid multi-image encoder trained jointly with a text model.
  arXiv  Detail & Related papers  (2023-01-11T16:35:33Z)
• RoentGen: Vision-Language Foundation Model for Chest X-ray Generation [7.618389245539657]
  We develop a strategy to overcome the large natural-medical distributional shift by adapting a pre-trained latent diffusion model on a corpus of publicly available chest x-rays. We investigate the model's ability to generate high-fidelity, diverse synthetic CXR conditioned on text prompts. We present evidence that the resulting model (RoentGen) is able to create visually convincing, diverse synthetic CXR images.
  arXiv  Detail & Related papers  (2022-11-23T06:58:09Z)
• Adapting Pretrained Vision-Language Foundational Models to Medical Imaging Domains [3.8137985834223502]
  Building generative models for medical images that faithfully depict clinical context may help alleviate the paucity of healthcare datasets. We explore the sub-components of the Stable Diffusion pipeline to fine-tune the model to generate medical images. Our best-performing model improves upon the stable diffusion baseline and can be conditioned to insert a realistic-looking abnormality on a synthetic radiology image.
  arXiv  Detail & Related papers  (2022-10-09T01:43:08Z)

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.