Dental-TriageBench is the first expert-annotated multimodal benchmark for hierarchical dental triage and shows a substantial performance gap between 19 MLLMs and junior dentists, especially on multi-domain referral cases.
hub
A vision- language foundation model to enhance efficiency of chest x-ray interpretation
23 Pith papers cite this work. Polarity classification is still indexing.
23
Pith papers citing it
abstract
Over 1.4 billion chest X-rays (CXRs) are performed annually due to their cost-effectiveness as an initial diagnostic test. This scale of radiological studies provides a significant opportunity to streamline CXR interpretation and documentation. While foundation models are a promising solution, the lack of publicly available large-scale datasets and benchmarks inhibits their iterative development and real-world evaluation. To overcome these challenges, we constructed a large-scale dataset (CheXinstruct), which we utilized to train a vision-language foundation model (CheXagent). We systematically demonstrated competitive performance across eight distinct task types on our novel evaluation benchmark (CheXbench). Beyond technical validation, we assessed the real-world utility of CheXagent in directly drafting radiology reports. Our clinical assessment with eight radiologists revealed a 36% time saving for residents using CheXagent-drafted reports, while attending radiologists showed no significant time difference editing resident-drafted or CheXagent-drafted reports. The CheXagent-drafted reports improved the writing efficiency of both radiology residents and attending radiologists in 81% and 61% of cases, respectively, without loss of quality. Overall, we demonstrate that CheXagent can effectively perform a variety of CXR interpretation tasks and holds potential to assist radiologists in routine clinical workflows.
hub tools
citation-role summary
background 4
citation-polarity summary
roles
background 4polarities
background 4representative citing papers
CheXpercept is a sequential multi-level perception benchmark showing VLMs perform adequately only on coarse lesion detection in chest X-rays while degrading sharply on finer tasks, with medical VLMs offering no advantage over general models.
Introduces MedReCo-DB dataset of 690k+ images and entity-aware models MedReCo/MedReCo-VLM that improve reference retrieval and comparative change interpretation in radiology across multiple centers and modalities.
DDX-TRACE is a physician-adjudicated benchmark for evaluating VLMs on evidence-supported diagnostic trajectories rather than final answers alone in multimodal neuroradiology.
HalluCXR benchmark shows 61.9-82.3% hallucination rates across VLMs on MIMIC-CXR images, identifies patterns such as length-based risk and over-fabrication of common findings, and demonstrates ensemble mitigation that cuts fabrication by up to 84.8%.
Medical VLMs frequently select negated options that contradict visible chest X-ray findings, achieving only ~30% accuracy on direct presence probes, but a post-hoc consistency verifier raises accuracy above 95%.
CheXmix combines masked autoencoder pretraining with early-fusion generative modeling to outperform prior models on chest X-ray classification by up to 8.6% AUROC, inpainting by 51%, and report generation by 45% on GREEN.
ESC-RL improves RL for radiology reports via group-wise evidence-aware rewards (GEAR) and LLM-driven self-correcting preference learning (SPL), reaching state-of-the-art on two chest X-ray datasets.
IMACT-CXR presents an integrated multi-agent system using AutoGen, Bayesian Knowledge Tracing, gaze feedback, and vision-language models to provide interactive tutoring for chest X-ray interpretation with preliminary evidence of improved learner performance.
RA-RRG extracts key phrases with LLMs, retrieves them via multimodal similarity, and conditions report generation on them to achieve SOTA CheXbert scores and competitive RadGraph F1 on MIMIC-CXR and IU X-ray while supporting multi-view inputs.
PMC-VQA dataset and MedVInT model achieve better generative performance on medical VQA benchmarks by visual instruction tuning on a newly constructed large-scale dataset.
Harrison.Rad 1.5 is a radiology-specific multimodal LLM that passes simulated FRCR 2B Short Case examinations and outperforms general-purpose frontier models on plain-film radiography reporting tasks.
A GRPO-based RL framework with probabilistic risk minimization, disagreement-aware synergy rewards, and entropy-guided sampling enables instance-level tool selection that closes the single-oracle risk gap on medical benchmarks.
CXRMate-2 improves chest X-ray report generation via temporal embeddings and tractable RL, delivering metric gains and 45% acceptability in radiologist review with no significant preference difference on most findings.
A vision-language model pre-trained via instruction tuning on CT-report pairs improves survival prediction accuracy over baselines, especially when clinical data alone is weak, while also producing text answers to clinical questions.
ECHO introduces one-step block diffusion via Direct Conditional Distillation and Response-Asymmetric Diffusion to generate chest X-ray reports faster than autoregressive models while improving clinical metrics.
DINOv3 at 512x512 resolution with ConvNeXt-B outperforms prior initializations for adult chest X-ray classification but shows no benefit in pediatric cohorts or at 1024 resolution.
RadAgents is a multi-agent framework coupling clinical priors with task-aware multimodal reasoning and radiologist-like workflows, plus grounding and retrieval-augmentation for conflict resolution in chest X-ray interpretation.
Synthetic clinical demonstrations at inference time improve safety of Med-VLMs against visual and textual jailbreaks while preserving general performance on medical tasks.
M4CXR is a multi-modal large language model that performs multiple tasks in chest X-ray analysis including report generation with claimed SOTA clinical accuracy using chain-of-thought prompting.
A new contest provides a chest X-ray dataset for lung nodule classification and localization; the best entry reaches 0.72 balanced accuracy and 0.79 AUC on classification but only predicts the correct nodule count on 53% of external test images with 12.83 mm median error.
Proposes bidirectional token-wise KL regularizer and visual-contrastive grounding objective to create fine-grained on-policy preference pairs for medical LVLMs by minimally editing model outputs.
The paper surveys data-centric strategies for foundation models in computational healthcare and supplies a curated list of related models and datasets.
citing papers explorer
-
Dental-TriageBench: Benchmarking Multimodal Reasoning for Hierarchical Dental Triage
Dental-TriageBench is the first expert-annotated multimodal benchmark for hierarchical dental triage and shows a substantial performance gap between 19 MLLMs and junior dentists, especially on multi-domain referral cases.
-
CheXpercept: A Benchmark for Evaluating Expert-Level Lesion Perception in Chest X-rays
CheXpercept is a sequential multi-level perception benchmark showing VLMs perform adequately only on coarse lesion detection in chest X-rays while degrading sharply on finer tasks, with medical VLMs offering no advantage over general models.
-
A Vision-language Framework for Comparative Reasoning in Radiology
Introduces MedReCo-DB dataset of 690k+ images and entity-aware models MedReCo/MedReCo-VLM that improve reference retrieval and comparative change interpretation in radiology across multiple centers and modalities.
-
DDX-TRACE: A Benchmark for Medical Diagnostic Trajectories in VLMs
DDX-TRACE is a physician-adjudicated benchmark for evaluating VLMs on evidence-supported diagnostic trajectories rather than final answers alone in multimodal neuroradiology.
-
HalluCXR: Benchmarking and Mitigating Hallucinations in Medical Vision-Language Models for Chest Radiograph Interpretation
HalluCXR benchmark shows 61.9-82.3% hallucination rates across VLMs on MIMIC-CXR images, identifies patterns such as length-based risk and over-fabrication of common findings, and demonstrates ensemble mitigation that cuts fabrication by up to 84.8%.
-
CXR-ContraBench: Benchmarking Negated-Option Attraction in Medical VLMs
Medical VLMs frequently select negated options that contradict visible chest X-ray findings, achieving only ~30% accuracy on direct presence probes, but a post-hoc consistency verifier raises accuracy above 95%.
-
CheXmix: Unified Generative Pretraining for Vision Language Models in Medical Imaging
CheXmix combines masked autoencoder pretraining with early-fusion generative modeling to outperform prior models on chest X-ray classification by up to 8.6% AUROC, inpainting by 51%, and report generation by 45% on GREEN.
-
Enhancing Reinforcement Learning for Radiology Report Generation with Evidence-aware Rewards and Self-correcting Preference Learning
ESC-RL improves RL for radiology reports via group-wise evidence-aware rewards (GEAR) and LLM-driven self-correcting preference learning (SPL), reaching state-of-the-art on two chest X-ray datasets.
-
IMACT-CXR: An Interactive Multi-Agent Conversational Tutoring System for Chest X-Ray Interpretation
IMACT-CXR presents an integrated multi-agent system using AutoGen, Bayesian Knowledge Tracing, gaze feedback, and vision-language models to provide interactive tutoring for chest X-ray interpretation with preliminary evidence of improved learner performance.
-
RA-RRG: Multimodal Retrieval-Augmented Radiology Report Generation with Key Phrase Extraction
RA-RRG extracts key phrases with LLMs, retrieves them via multimodal similarity, and conditions report generation on them to achieve SOTA CheXbert scores and competitive RadGraph F1 on MIMIC-CXR and IU X-ray while supporting multi-view inputs.
-
PMC-VQA: Visual Instruction Tuning for Medical Visual Question Answering
PMC-VQA dataset and MedVInT model achieve better generative performance on medical VQA benchmarks by visual instruction tuning on a newly constructed large-scale dataset.
-
Harrison.Rad 1.5 Technical Report: A radiology foundation model that can draft reports from images, priors and clinical context
Harrison.Rad 1.5 is a radiology-specific multimodal LLM that passes simulated FRCR 2B Short Case examinations and outperforms general-purpose frontier models on plain-film radiography reporting tasks.
-
Mind the Tool Failures: Achieving Synergistic Tool Gains for Medical Agents
A GRPO-based RL framework with probabilistic risk minimization, disagreement-aware synergy rewards, and entropy-guided sampling enables instance-level tool selection that closes the single-oracle risk gap on medical benchmarks.
-
CXRMate-2: Structured Multimodal Temporal Embeddings and Tractable Reinforcement Learning for Clinically Acceptable Chest X-ray Radiology Report Generation
CXRMate-2 improves chest X-ray report generation via temporal embeddings and tractable RL, delivering metric gains and 45% acceptability in radiologist review with no significant preference difference on most findings.
-
Medical Image Understanding Improves Survival Prediction via Visual Instruction Tuning
A vision-language model pre-trained via instruction tuning on CT-report pairs improves survival prediction accuracy over baselines, especially when clinical data alone is weak, while also producing text answers to clinical questions.
-
ECHO: Efficient Chest X-ray Report Generation with One-step Block Diffusion
ECHO introduces one-step block diffusion via Direct Conditional Distillation and Response-Asymmetric Diffusion to generate chest X-ray reports faster than autoregressive models while improving clinical metrics.
-
Resolution scaling governs DINOv3 transfer performance in chest radiograph classification
DINOv3 at 512x512 resolution with ConvNeXt-B outperforms prior initializations for adult chest X-ray classification but shows no benefit in pediatric cohorts or at 1024 resolution.
-
RadAgents: Multimodal Agentic Reasoning for Chest X-ray Interpretation with Radiologist-like Workflows
RadAgents is a multi-agent framework coupling clinical priors with task-aware multimodal reasoning and radiologist-like workflows, plus grounding and retrieval-augmentation for conflict resolution in chest X-ray interpretation.
-
Enhancing the Safety of Medical Vision-Language Models by Synthetic Demonstrations
Synthetic clinical demonstrations at inference time improve safety of Med-VLMs against visual and textual jailbreaks while preserving general performance on medical tasks.
-
M4CXR: Exploring Multi-task Potentials of Multi-modal Large Language Models for Chest X-ray Interpretation
M4CXR is a multi-modal large language model that performs multiple tasks in chest X-ray analysis including report generation with claimed SOTA clinical accuracy using chain-of-thought prompting.
-
NoduLoCC2026: Lung Nodule Localization and Classification Contest from Chest X-Ray Images
A new contest provides a chest X-ray dataset for lung nodule classification and localization; the best entry reaches 0.72 balanced accuracy and 0.79 AUC on classification but only predicts the correct nodule count on 53% of external test images with 12.83 mm median error.
-
Analyzing and Improving Fine-grained Preference Optimization in Medical LVLMs
Proposes bidirectional token-wise KL regularizer and visual-contrastive grounding objective to create fine-grained on-policy preference pairs for medical LVLMs by minimally editing model outputs.
-
Data-Centric Foundation Models in Computational Healthcare: A Survey
The paper surveys data-centric strategies for foundation models in computational healthcare and supplies a curated list of related models and datasets.