Seeing the Trees for the Forest: Rethinking Weakly-Supervised Medical Visual Grounding

• URL: http://arxiv.org/abs/2505.15123v1
• Date: Wed, 21 May 2025 05:16:45 GMT
• Title: Seeing the Trees for the Forest: Rethinking Weakly-Supervised Medical Visual Grounding
• Authors: Ta Duc Huy, Duy Anh Huynh, Yutong Xie, Yuankai Qi, Qi Chen, Phi Le Nguyen, Sen Kim Tran, Son Lam Phung, Anton van den Hengel, Zhibin Liao, Minh-Son To, Johan W. Verjans, Vu Minh Hieu Phan,
• Abstract summary: Current models struggle to associate textual descriptions with disease regions due to inefficient attention mechanisms and a lack of fine-grained token representations.<n>We introduce Disease-Aware Prompting (DAP), which uses the explainability map of a VLM to identify the appropriate image features.<n>DAP improves visual grounding accuracy by 20.74% compared to state-of-the-art methods across three major chest X-ray datasets.
• Score: 50.483761005446
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Visual grounding (VG) is the capability to identify the specific regions in an image associated with a particular text description. In medical imaging, VG enhances interpretability by highlighting relevant pathological features corresponding to textual descriptions, improving model transparency and trustworthiness for wider adoption of deep learning models in clinical practice. Current models struggle to associate textual descriptions with disease regions due to inefficient attention mechanisms and a lack of fine-grained token representations. In this paper, we empirically demonstrate two key observations. First, current VLMs assign high norms to background tokens, diverting the model's attention from regions of disease. Second, the global tokens used for cross-modal learning are not representative of local disease tokens. This hampers identifying correlations between the text and disease tokens. To address this, we introduce simple, yet effective Disease-Aware Prompting (DAP) process, which uses the explainability map of a VLM to identify the appropriate image features. This simple strategy amplifies disease-relevant regions while suppressing background interference. Without any additional pixel-level annotations, DAP improves visual grounding accuracy by 20.74% compared to state-of-the-art methods across three major chest X-ray datasets.

Related papers

• From Gaze to Insight: Bridging Human Visual Attention and Vision Language Model Explanation for Weakly-Supervised Medical Image Segmentation [46.99748372216857]
  Vision-language models (VLMs) provide semantic context through textual descriptions but lack explanation precision required.<n>We propose a teacher-student framework that integrates both gaze and language supervision, leveraging their complementary strengths.<n>Our method achieves Dice scores of 80.78%, 80.53%, and 84.22%, respectively, improving 3-5% over gaze baselines without increasing the annotation burden.
  arXiv  Detail & Related papers  (2025-04-15T16:32:15Z)
• Activating Associative Disease-Aware Vision Token Memory for LLM-Based X-ray Report Generation [54.631356899598956]
  We propose a novel associative memory-enhanced X-ray report generation model that effectively mimics the process of professional doctors writing medical reports.<n>We employ a visual Hopfield network to establish memory associations for disease-related tokens, and a report Hopfield network to retrieve report memory information.
  arXiv  Detail & Related papers  (2025-01-07T01:19:48Z)
• See Detail Say Clear: Towards Brain CT Report Generation via Pathological Clue-driven Representation Learning [12.40415847810958]
  We introduce a Pathological Clue-driven Representation Learning (PCRL) model to build cross-modal representations based on pathological clues. Specifically, we construct pathological clues from perspectives of segmented regions, pathological entities, and report themes. To adapt the representations for the text generation task, we bridge the gap between representation learning and report generation by using a unified large language model (LLM) with task-tailored instructions.
  arXiv  Detail & Related papers  (2024-09-29T12:08:20Z)
• ViKL: A Mammography Interpretation Framework via Multimodal Aggregation of Visual-knowledge-linguistic Features [54.37042005469384]
  We announce MVKL, the first multimodal mammography dataset encompassing multi-view images, detailed manifestations and reports. Based on this dataset, we focus on the challanging task of unsupervised pretraining. We propose ViKL, a framework that synergizes Visual, Knowledge, and Linguistic features.
  arXiv  Detail & Related papers  (2024-09-24T05:01:23Z)
• Guided Context Gating: Learning to leverage salient lesions in retinal fundus images [1.8789068567093286]
  We propose a novel attention mechanism called Guided Context Gating. It integrates Context Formulation, Channel Correlation, and Guided Gating to learn global context, spatial correlations, and localized lesion context. Experiments on the Zenodo-DR-7 dataset reveal a substantial 2.63% accuracy boost over advanced attention mechanisms.
  arXiv  Detail & Related papers  (2024-06-19T00:42:35Z)
• Decomposing Disease Descriptions for Enhanced Pathology Detection: A Multi-Aspect Vision-Language Pre-training Framework [43.453943987647015]
  Medical vision language pre-training has emerged as a frontier of research, enabling zero-shot pathological recognition. Due to the complex semantics of biomedical texts, current methods struggle to align medical images with key pathological findings in unstructured reports. This is achieved by consulting a large language model and medical experts. Ours improves the accuracy of recent methods by up to 8.56% and 17.26% for seen and unseen categories, respectively.
  arXiv  Detail & Related papers  (2024-03-12T13:18:22Z)
• Class Attention to Regions of Lesion for Imbalanced Medical Image Recognition [59.28732531600606]
  We propose a framework named textbfClass textbfAttention to textbfREgions of the lesion (CARE) to handle data imbalance issues. The CARE framework needs bounding boxes to represent the lesion regions of rare diseases. Results show that the CARE variants with automated bounding box generation are comparable to the original CARE framework.
  arXiv  Detail & Related papers  (2023-07-19T15:19:02Z)
• 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)
• Multi-Granularity Cross-modal Alignment for Generalized Medical Visual Representation Learning [24.215619918283462]
  We present a novel framework for learning medical visual representations directly from paired radiology reports. Our framework harnesses the naturally exhibited semantic correspondences between medical image and radiology reports at three different levels.
  arXiv  Detail & Related papers  (2022-10-12T09:31:39Z)

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.