Regulating Anatomy-Aware Rewards via Trajectory-Integral Feedback for Volumetric Computed Tomography Analysis

• URL: http://arxiv.org/abs/2605.20277v1
• Date: Tue, 19 May 2026 04:33:27 GMT
• Title: Regulating Anatomy-Aware Rewards via Trajectory-Integral Feedback for Volumetric Computed Tomography Analysis
• Abstract summary: We introduce textbfClinical Abnormality Benchmarking Substrate (CABS), a structured system that decomposes radiology reports into verifiable clinical semantic units.<n>We propose textbfTrajectory-Integral FeedbackO (TIF-GRPO), a novel framework integrating control-theoretic principles into policy optimization.
• Score: 30.439440028190944
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Medical vision-language models (VLMs) have rapidly advanced as general-purpose multimodal assistants, yet their deployment in 3D Computed Tomography (CT) analysis remains constrained by a persistent mismatch between optimization objectives and clinical rigor. Current Reinforcement Learning (RL) paradigms still rely on lexical proxy signals that induce ``\textit{Evaluation Hallucinations}'', where models optimize linguistic fluency rather than factual clinical correctness, leading to diagnostically critical errors. To bridge this gap, we introduce the \textbf{Clinical Abnormality Benchmarking Substrate (CABS)}, a structured system that decomposes radiology reports into verifiable clinical semantic units. Using CABS, we identify a ``\textit{Mechanistic Divergence}'' in standard RL, where surface-similarity rewards drive policy gradients to bypass medical facts. We therefore propose \textbf{Trajectory-Integral Feedback GRPO (TIF-GRPO)}, a novel framework integrating control-theoretic principles into policy optimization. By formulating clinical reasoning as a pseudo-temporal trajectory for anomaly discovery, TIF-GRPO regulates anatomy-aware rewards via an integral feedback loop that penalizes persistent omissions as cumulative state errors and suppresses hallucinations as excessive control effort. Experiments on 3D CT benchmarks demonstrate that our approach significantly enhances abnormality detection and clinical faithfulness, establishing a new paradigm for fine-grained regulation in medical VLMs. Our project is available at \href{https://github.com/ZJU4HealthCare/TIF-GRPO}{GitHub}.

Related papers

• Concept-Grounded Reasoning with Prompt-Driven Localization for Interpretable Structured Report Generation [66.62662330558906]
  CORAL is a multimodal framework that integrates spatial grounding and concept-level supervision into a unified reasoning process.<n>CORAL employs a prompt-driven medical segmentation model to localize lesions and predicts multi-class clinical attributes through a Concept Bottleneck module.<n>Experiments on BUS-CoT and IU X-ray datasets demonstrate consistent improvements in diagnostic accuracy, concept consistency, and report quality over strong general-purpose and medical MLLMs.
  arXiv  Detail & Related papers  (2026-09-14T10:21:23Z)
• Analyzing and Improving Fine-grained Preference Optimization in Medical LVLMs [53.697403481143404]
  Large Vision-Language Models (LVLMs) have achieved strong performance across medical imaging tasks.<n>But they remain prone to factual inconsistencies, poor visual grounding, and misalignment with clinically meaningful feedback.
  arXiv  Detail & Related papers  (2026-06-10T18:35:36Z)
• CA-GCL: Cross-Anatomy Global-Local Contrastive Learning for Robust 3D Medical Image Understanding [10.148965935742543]
  Fine-grained Vision-Language Pre-training demonstrates significant potential in 3D medical image understanding.<n>Existing paradigms often suffer from severe representation collapse in the textual embedding space.<n>This distributional degeneracy renders the model hypersensitive to prompt variations, hindering reliable clinical deployment.<n>We propose a novel Cross-Anatomy Global-Local Contrastive Learning framework (CA-GCL) to address these challenges.
  arXiv  Detail & Related papers  (2026-05-13T13:54:27Z)
• KEPIL: Knowledge-Enhanced Prompt-Image Learning for Prompt-Robust Disease Detection [6.447908430647854]
  radiological findings are long-tailed in practice, leaving some conditions underrepresented and making zero-shot inference essential.<n>We present textitKEPIL, a prompt-robust framework that integrates curated medical knowledge to stabilize zero-shot generalization.
  arXiv  Detail & Related papers  (2026-05-09T19:29:01Z)
• Graph-Augmented Topological Internalization with Dual-Stream Classifiers for Medical Report Generation [3.3887144970801555]
  We propose a Graph-Augmented Dual-Stream Medical Report Generation with Topological Internalization, GDMRG.<n>Our framework introduces a Topological Knowledge Internalization module, TKI, which generates an explicit parameterized weight matrix based on global disease co-occurrence priors.<n>Experiments on the MIMIC-CXR dataset demonstrate that GDMRG achieves competitive clinical efficacy, CE, while maintaining natural language fluency.
  arXiv  Detail & Related papers  (2026-05-04T09:17:27Z)
• MedScribe: Clinically Grounded CT Reporting through Agentic Workflows [13.40306812882295]
  Vision-language models (VLMs) have shown potential for automated radiology report generation.<n>We introduce MedScribe, a hypothesis-driven framework that reformulates report generation as an iterative evidence acquisition process.
  arXiv  Detail & Related papers  (2026-05-03T08:32:40Z)
• Clinical Cognition Alignment for Gastrointestinal Diagnosis with Multimodal LLMs [63.535652574541764]
  Multimodal Large Language Models (MLLMs) have demonstrated remarkable potential in medical image analysis.<n>Their application in gastrointestinal endoscopy is currently hindered by two critical limitations.<n>We propose a novel Clinical-Cognitive-Aligned (CogAlign) framework to address these challenges.
  arXiv  Detail & Related papers  (2026-03-21T07:47:37Z)
• Anatomy of a Lie: A Multi-Stage Diagnostic Framework for Tracing Hallucinations in Vision-Language Models [62.932580559941414]
  Vision-Language Models (VLMs) frequently "hallucinate" - generate plausible yet factually incorrect statements.<n>We propose a new paradigm for diagnosing hallucinations, recasting them from static output errors into dynamic pathologies of a model's computational cognition.
  arXiv  Detail & Related papers  (2026-03-16T17:20:38Z)
• SPEGC: Continual Test-Time Adaptation via Semantic-Prompt-Enhanced Graph Clustering for Medical Image Segmentation [12.0982298854338]
  Continual Test-Time Adaptation (CTTA) aims to enable pre-trained models to adapt to continuously changing unlabeled domains.<n>We propose a CTTA via Semantic-Prompt-Enhanced Graph Clustering (SPEGC) for medical image segmentation.
  arXiv  Detail & Related papers  (2026-03-12T03:22:43Z)
• Suppressing Prior-Comparison Hallucinations in Radiology Report Generation via Semantically Decoupled Latent Steering [94.37535002230504]
  We develop a training-free, inference-time control framework termed Semantically Decoupled Latent Steering.<n>Our approach constructs a semantic-free intervention vector via large language model (LLM)-driven semantic decomposition.<n>We show that our approach significantly reduces the probability of historical hallucinations.
  arXiv  Detail & Related papers  (2026-02-27T04:49:01Z)
• Benchmarking Egocentric Clinical Intent Understanding Capability for Medical Multimodal Large Language Models [48.95516224614331]
  We introduce MedGaze-Bench, the first benchmark leveraging clinician gaze as a Cognitive Cursor to assess intent understanding across surgery, emergency simulation, and diagnostic interpretation.<n>Our benchmark addresses three fundamental challenges: visual homogeneity of anatomical structures, strict temporal-causal dependencies in clinical, and implicit adherence to safety protocols.
  arXiv  Detail & Related papers  (2026-01-11T02:20:40Z)
• Physically-Grounded Manifold Projection Model for Generalizable Metal Artifact Reduction in Dental CBCT [20.637726557566793]
  Metal artifacts in Dental CBCT severely obscure anatomical structures.<n>Current deep learning for Metal Artifact Reduction (MAR) faces limitations.<n>Denoising Diffusion Models (DDPMs) offer realism but rely on slow, iterative sampling.
  arXiv  Detail & Related papers  (2025-12-30T14:36:26Z)
• MIRNet: Integrating Constrained Graph-Based Reasoning with Pre-training for Diagnostic Medical Imaging [67.74482877175797]
  MIRNet is a novel framework that integrates self-supervised pre-training with constrained graph-based reasoning.<n>We introduce TongueAtlas-4K, a benchmark comprising 4,000 images annotated with 22 diagnostic labels.
  arXiv  Detail & Related papers  (2025-11-13T06:30:41Z)
• Self-Supervised Anatomical Consistency Learning for Vision-Grounded Medical Report Generation [61.350584471060756]
  Vision-grounded medical report generation aims to produce clinically accurate descriptions of medical images.<n>We propose Self-Supervised Anatomical Consistency Learning (SS-ACL) to align generated reports with corresponding anatomical regions.<n>SS-ACL constructs a hierarchical anatomical graph inspired by the invariant top-down inclusion structure of human anatomy.
  arXiv  Detail & Related papers  (2025-09-30T08:59:06Z)
• AGIR: Assessing 3D Gait Impairment with Reasoning based on LLMs [0.0]
  gait impairment plays an important role in early diagnosis, disease monitoring, and treatment evaluation for neurodegenerative diseases.<n>Recent deep learning-based approaches have consistently improved classification accuracies, but they often lack interpretability.<n>We introduce AGIR, a novel pipeline consisting of a pre-trained VQ-VAE motion tokenizer and a Large Language Model (LLM) fine-tuned over pairs of motion tokens.
  arXiv  Detail & Related papers  (2025-03-23T17:12:16Z)

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.