Enhancing Fine-Grained Spatial Grounding in 3D CT Report Generation via Discriminative Guidance

• URL: http://arxiv.org/abs/2604.10437v1
• Date: Sun, 12 Apr 2026 03:25:41 GMT
• Title: Enhancing Fine-Grained Spatial Grounding in 3D CT Report Generation via Discriminative Guidance
• Abstract summary: Vision--language models (VLMs) for radiology report generation (RRG) can produce long-form chest CT reports from volumetric scans.<n>Existing methods face two key limitations: (i) training supervision is often coarse, aligning a whole CT volume with a full free-text report without explicit alignment for fine-grained attributes or pathology locations.<n>We propose emphDiscrimi Cue-Prompting with Prompt Dropout (DCP-PD), a plug-and-play framework that distills fine-grained cues from free-text reports and uses them to guide report generation.
• Score: 16.566888073449714
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Vision--language models (VLMs) for radiology report generation (RRG) can produce long-form chest CT reports from volumetric scans and show strong potential to improve radiology workflow efficiency and consistency. However, existing methods face two key limitations: (i) training supervision is often coarse, aligning a whole CT volume with a full free-text report without explicit alignment for fine-grained attributes or pathology locations; and (ii) evaluation is typically holistic (lexical overlap, entity matching, or LLM-as-a-judge scores) and not diagnostic for spatial grounding. We propose \emph{Discriminative Cue-Prompting with Prompt Dropout (DCP-PD)}, a plug-and-play framework that distills fine-grained cues from free-text reports and uses them to guide report generation while mitigating shortcut reliance via prompt dropout. DCP-PD achieves state-of-the-art performance on CT-RATE, improving macro F1 from $=0.501$ to $0.603$ (20% relative), and substantially boosts out-of-distribution performance on Rad-ChestCT from F1 $=0.266$ to $0.503$ (89% relative). Finally, we introduce a hierarchical, location-aware question-set protocol (presence $\rightarrow$ laterality $\rightarrow$ lobe) to directly assess pathology-location grounding, showing that fine-grained spatial localization remains challenging even for models that score highly on current benchmarks.

Related papers

• Bridging Vision Foundation Model Priors with CLIP for Spatial-aware Few-shot Anomaly Detection in Medical Images [48.646448077284276]
  We propose Spatial-FAD, a framework for effective few-shot medical anomaly detection.<n>It improves lesion localization by combining VFM spatial priors with CLIP semantics.<n>Our method achieves an average improvement of over 11.4% in Dice score and 1.8% in AUC.
  arXiv  Detail & Related papers  (2026-09-11T05:21:01Z)
• Synergistic Perception-Reasoning Governance: Grounding Medical MLLMs with Verifiable Anatomical Evidence [45.78409219344429]
  Multimodal large language models (MLLMs) show strong promise for clinical VQA and radiology report generation, yet inference-time hallucinations undermine trustworthy use.<n>We propose a holistic, training-free evidence-injection framework that systematically mitigates hallucinations through dual-side evidence injection.<n>We conduct systematic evaluations on 2 tasks and 5 datasets using textttLLaVA-1.5-7B, texttLLaVA-Med-1.5-7B, texttQwen3-VL-8B/32B, and textttInternVL
  arXiv  Detail & Related papers  (2026-06-30T08:07:25Z)
• SA-CycleGAN-2.5D: Self-Attention CycleGAN with Tri-Planar Context for Multi-Site MRI Harmonization [3.5109108807229403]
  We propose SA-CycleGAN-2.5D, a domain adaptation framework motivated by the $HH$-divergence bound of Ben-David et al.<n>By bridging 2D efficiency and 3D consistency, our framework yields voxel-level harmonized images that preserve tumor pathophysiology.
  arXiv  Detail & Related papers  (2026-03-17T23:49:46Z)
• PathGLS: Evaluating Pathology Vision-Language Models without Ground Truth through Multi-Dimensional Consistency [22.13541624406203]
  Vision-Language Models (VLMs) offer significant potential in computational pathology by enabling interpretable image analysis, automated reporting, and scalable decision support.<n>To address this gap, we propose PathGLS, a novel reference-free evaluation framework that assesses pathology VLMs across three dimensions.<n> Experiments on Quilt-1M, TCGA, REG2025, PathMMU and TCGA-Sarcoma datasets demonstrate the superiority of PathGLS.
  arXiv  Detail & Related papers  (2026-03-17T04:25:55Z)
• Beyond the Embedding Bottleneck: Adaptive Retrieval-Augmented 3D CT Report Generation [10.885951167009694]
  3D CT embeddings encode discriminative pathology signals, yet exhibit severe dimensional concentration.<n>We propose textbfAdaRAG-CT, an adaptive augmentation framework that compensates for this visual bottleneck.<n>AdaRAG-CT achieves state-of-the-art clinical efficacy, improving Clinical F1 from 0.420 (CT-Agent) to 0.480 (+6 points)
  arXiv  Detail & Related papers  (2026-03-16T18:56:14Z)
• Using Unsupervised Domain Adaptation Semantic Segmentation for Pulmonary Embolism Detection in Computed Tomography Pulmonary Angiogram (CTPA) Images [0.0]
  unsupervised domain adaptation (UDA) framework is proposed, utilizing a Transformer backbone and a Mean-Teacher architecture for cross-center semantic segmentation.<n>The primary focus is placed on enhancing pseudo-label reliability by learning deep structural information within the feature space.<n> Experimental validation conducted on cross-center datasets (FUMPE and CAD-PE) demonstrates significant performance gains.
  arXiv  Detail & Related papers  (2026-02-23T14:33:24Z)
• $μ^2$Tokenizer: Differentiable Multi-Scale Multi-Modal Tokenizer for Radiology Report Generation [9.947108972979155]
  We propose $mu2$LLM, a $underlinetextbfmu$ltiscale $underlinetextbfmu$ltimodal large language models for radiology report generation tasks.<n>The novel $mu2$Tokenizer, as an intermediate layer, integrates multi-modal features from the multiscale visual tokenizer and the text tokenizer.<n>For prompt engineering, we introduce a five-stage, LLM-driven pipeline that converts routine CT reports into paired visual-question-answer triples and citation-linked reasoning narratives.
  arXiv  Detail & Related papers  (2025-06-30T23:14:49Z)
• Cross-Modal Causal Intervention for Medical Report Generation [107.76649943399168]
  Radiology Report Generation (RRG) is essential for computer-aided diagnosis and medication guidance.<n> generating accurate lesion descriptions remains challenging due to spurious correlations from visual-linguistic biases.<n>We propose a two-stage framework named CrossModal Causal Representation Learning (CMCRL)<n> Experiments on IU-Xray and MIMIC-CXR show that our CMCRL pipeline significantly outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-03-16T07:23:55Z)
• Radiomics-Guided Global-Local Transformer for Weakly Supervised Pathology Localization in Chest X-Rays [65.88435151891369]
  Radiomics-Guided Transformer (RGT) fuses textitglobal image information with textitlocal knowledge-guided radiomics information. RGT consists of an image Transformer branch, a radiomics Transformer branch, and fusion layers that aggregate image and radiomic information.
  arXiv  Detail & Related papers  (2022-07-10T06:32:56Z)
• Generalizing electrocardiogram delineation: training convolutional neural networks with synthetic data augmentation [63.51064808536065]
  Existing databases for ECG delineation are small, being insufficient in size and in the array of pathological conditions they represent. This article delves has two main contributions. First, a pseudo-synthetic data generation algorithm was developed, based in probabilistically composing ECG traces given "pools" of fundamental segments, as cropped from the original databases, and a set of rules for their arrangement into coherent synthetic traces. Second, two novel segmentation-based loss functions have been developed, which attempt at enforcing the prediction of an exact number of independent structures and at producing closer segmentation boundaries by focusing on a reduced number of samples.
  arXiv  Detail & Related papers  (2021-11-25T10:11:41Z)
• COVI-AgentSim: an Agent-based Model for Evaluating Methods of Digital Contact Tracing [68.68882022019272]
  COVI-AgentSim is an agent-based compartmental simulator based on virology, disease progression, social contact networks, and mobility patterns. We use COVI-AgentSim to perform cost-adjusted analyses comparing no DCT to: 1) standard binary contact tracing (BCT) that assigns binary recommendations based on binary test results; and 2) a rule-based method for feature-based contact tracing (FCT) that assigns a graded level of recommendation based on diverse individual features.
  arXiv  Detail & Related papers  (2020-10-30T00:47:01Z)

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.