CARE-X: Towards Clinically Useful Radiology VLMs with Auxiliary Supervision, Reward-Aligned Learning, and Tool-Augmented Measurement

• URL: http://arxiv.org/abs/2608.03890v1
• Date: Tue, 04 Aug 2026 16:23:39 GMT
• Title: CARE-X: Towards Clinically Useful Radiology VLMs with Auxiliary Supervision, Reward-Aligned Learning, and Tool-Augmented Measurement
• Abstract summary: We introduce CARE-X, a chest X-ray Vision-Language Model (VLM) that unifies auxiliary discriminative supervision with reward-aligned generation.<n> CARE-X augments its generative backbone with focal-loss classification and composite-loss grounding heads, co-trained alongside the language-modeling objective.<n>The result is state-of-the-art performance on the majority of metrics across four report-generation benchmarks, 94.0% VQA accuracy on ReXVQA, and generative spatial decoding that reaches near parity with dedicated detection heads.
• Score: 3.586844533420584
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: A clinically useful chest X-ray system must go beyond fluent report generation: it should classify findings with tunable decision thresholds, localize them spatially, and derive the anatomical measurements upon which many diagnoses depend. Today's Vision-Language Models (VLMs) treat these as separate problems, if they address them at all, leaving a gap between what radiologists need and what generative models provide. We introduce CARE-X, a chest X-ray VLM that narrows this gap by unifying auxiliary discriminative supervision with reward-aligned generation. CARE-X augments its generative backbone with focal-loss classification and composite-loss grounding heads, co-trained alongside the language-modeling objective. This auxiliary supervision produces discriminative diagnostic predictions with tunable decision thresholds and precise spatial localization while also improving report quality, providing evidence that structured prediction and generation reinforce one another. Building on this foundation, Decoupled Clip and Dynamic Sampling Policy Optimization (DAPO) leverages task-specific reward signals for report generation, visual question answering (VQA), and spatial grounding, directly optimizing the clinical quality metrics that matter in practice. The result is state-of-the-art performance on the majority of metrics across four report-generation benchmarks, 94.0% VQA accuracy on ReXVQA (+6.0 pp over the next-best baseline), and generative spatial decoding that reaches near parity with dedicated detection heads. Separately, to address measurement-dependent diagnoses, we couple Qwen3-VL-4B-Instruct with native tool-calling capabilities for invoking deterministic measurement tools, while retaining full visual access to the image. This hybrid inference yields +43.6 pp average F1 over perception-only baselines across five measurement-dependent conditions.

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)
• A Modular Agent for Reliable and Auditable Spatial Relation Verification in CT Scans [7.8047270656196766]
  Modern vision-language models (VLMs) show promising performance on many medical imaging tasks.<n>We present a modular medical imaging agent for binary spatial relation verification in axial CT slices.<n>The best-performing hybrid configuration reaches 94.1% accuracy and 94.2% F1, outperforming direct Qwen2-VL prompting by 42.5 percentage points in accuracy.
  arXiv  Detail & Related papers  (2026-08-21T14:16:46Z)
• Beyond Fluency: A Clinical Benchmark and Anomaly-Enhanced Baseline for Spine MRI Report Generation [11.89113336167412]
  We benchmark state-of-the-art Vision-Language Models (VLMs) on lumbar spine MRI with a focus on diagnostic accuracy.<n>We propose an architecture-agnostic framework that augments VLM inputs with spatially localized, disc-level anomaly heatmaps.
  arXiv  Detail & Related papers  (2026-08-07T11:21:33Z)
• Disease-Centric Vision-Language Pretraining with Hybrid Visual Encoding for 3D Computed Tomography [75.7789001619107]
  Vision-language pre-training holds great promise for general-purpose medical AI.<n>We propose a tailored framework featuring three key components.<n>A diagnosis-aware prompt strategy employs real clinical phrases and aggregated disease prototypes to bridge the pre-training-inference gap.
  arXiv  Detail & Related papers  (2026-06-24T08:24:45Z)
• A Reasoning-Enabled Vision-Language Foundation Model for Chest X-ray Interpretation [48.23500302185585]
  We present CheXOne, a reasoning-enabled vision-language model for CXR interpretation.<n>CheXOne jointly generates diagnostic predictions and explicit, clinically grounded reasoning traces.<n>We show that CheXOne-drafted reports are comparable to or better than resident-written reports in 55% of cases.
  arXiv  Detail & Related papers  (2026-04-01T05:19:09Z)
• A DeepSeek-Powered AI System for Automated Chest Radiograph Interpretation in Clinical Practice [83.11942224668127]
  Janus-Pro-CXR (1B) is a chest X-ray interpretation system based on DeepSeek Janus-Pro model.<n>Our system outperforms state-of-the-art X-ray report generation models in automated report generation.
  arXiv  Detail & Related papers  (2025-12-23T13:26:13Z)
• DiA-gnostic VLVAE: Disentangled Alignment-Constrained Vision Language Variational AutoEncoder for Robust Radiology Reporting with Missing Modalities [3.5045368873011924]
  We propose the DiA-gnostic VLVAE, which achieves robust radiology reporting through Disentangled Alignment.<n>Our framework is designed to be resilient to missing modalities by disentangling shared and modality-specific features.<n>A compact LLaMA-X decoder then uses these disentangled representations to generate reports efficiently.
  arXiv  Detail & Related papers  (2025-11-08T11:08:27Z)
• H-DDx: A Hierarchical Evaluation Framework for Differential Diagnosis [33.11853966969629]
  We introduce H-DDx, a hierarchical evaluation framework that better reflects clinical relevance.<n>In benchmarking 22 leading models, we show that conventional flat metrics underestimate performance by overlooking clinically meaningful outputs.<n>Our framework enhances interpretability by revealing hierarchical error patterns, demonstrating that LLMs often correctly identify the broader clinical context even when the precise diagnosis is missed.
  arXiv  Detail & Related papers  (2025-10-04T06:42:22Z)
• Eyes on the Image: Gaze Supervised Multimodal Learning for Chest X-ray Diagnosis and Report Generation [1.5087814338685968]
  We propose a two-stage framework that enhances disease classification and region-aware radiology report generation from chest X-rays.<n>In the first stage, we introduce a gaze-guided contrastive learning architecture for disease classification.<n>In the second stage, we present a modular report generation pipeline that extracts confidence-weighted diagnostic keywords.
  arXiv  Detail & Related papers  (2025-08-18T16:42:29Z)
• RadAlign: Advancing Radiology Report Generation with Vision-Language Concept Alignment [10.67889367763112]
  RadAlign is a novel framework that combines the predictive accuracy of vision-language models with the reasoning capabilities of large language models.<n>Our framework maintains strong clinical interpretability while reducing hallucinations, advancing automated medical imaging and report analysis through integrated predictive and generative AI.
  arXiv  Detail & Related papers  (2025-01-13T17:55:32Z)
• Instrumental Variable Learning for Chest X-ray Classification [52.68170685918908]
  We propose an interpretable instrumental variable (IV) learning framework to eliminate the spurious association and obtain accurate causal representation. Our approach's performance is demonstrated using the MIMIC-CXR, NIH ChestX-ray 14, and CheXpert datasets.
  arXiv  Detail & Related papers  (2023-05-20T03:12:23Z)
• Improving Classification Model Performance on Chest X-Rays through Lung Segmentation [63.45024974079371]
  We propose a deep learning approach to enhance abnormal chest x-ray (CXR) identification performance through segmentations. Our approach is designed in a cascaded manner and incorporates two modules: a deep neural network with criss-cross attention modules (XLSor) for localizing lung region in CXR images and a CXR classification model with a backbone of a self-supervised momentum contrast (MoCo) model pre-trained on large-scale CXR data sets.
  arXiv  Detail & Related papers  (2022-02-22T15:24:06Z)
• Many-to-One Distribution Learning and K-Nearest Neighbor Smoothing for Thoracic Disease Identification [83.6017225363714]
  deep learning has become the most powerful computer-aided diagnosis technology for improving disease identification performance. For chest X-ray imaging, annotating large-scale data requires professional domain knowledge and is time-consuming. In this paper, we propose many-to-one distribution learning (MODL) and K-nearest neighbor smoothing (KNNS) methods to improve a single model's disease identification performance.
  arXiv  Detail & Related papers  (2021-02-26T02:29:30Z)
• BS-Net: learning COVID-19 pneumonia severity on a large Chest X-Ray dataset [6.5800499500032705]
  We design an end-to-end deep learning architecture for predicting, on Chest X-rays images (CXR), a multi-regional score conveying the degree of lung compromise in COVID-19 patients. We exploit a clinical dataset of almost 5,000 CXR annotated images collected in the same hospital. Our solution outperforms single human annotators in rating accuracy and consistency.
  arXiv  Detail & Related papers  (2020-06-08T13:55:58Z)

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.