MIMIC-CXR

The MIMIC-CXR dataset is a large collection of chest X-ray images and associated radiology reports used to evaluate and improve medical report generation models.

Papers using MIMIC-CXR (21)

Non-Contrastive Vision-Language Learning with Predictive Embedding Alignment2026Mrgagents: A Multi-agent Framework For Improved Medical Report Generation With Med-lvlms2025 · 4 citesA Benchmark for Hallucination Detection in VLMs for Gastrointestinal Endoscopy2026Multimodal Large Language Models For Medical Report Generation Via Customized Prompt Tuning2025 · 1 citesMedical Context Distorts Decisions in Clinical Vision Language Models2026A Reasoning-Enabled Vision-Language Foundation Model for Chest X-ray Interpretation2026Grounded Multimodal Retrieval-Augmented Drafting of Radiology Impressions Using Case-Based Similarity Search2026Instruction-Free Tuning of Large Vision Language Models for Medical Instruction Following2026Less Is More? Selective Visual Attention to High-Importance Regions for Multimodal Radiology Summarization2026MedMO: Grounding and Understanding Multimodal Large Language Model for Medical Images2026MedProbCLIP: Probabilistic Adaptation of Vision-Language Foundation Model for Reliable Radiograph-Report Retrieval2026Exploring the Capabilities of Large Language Model Encoders for Image-Text Retrieval in Chest X-rays2025On the Risk of Misleading Reports: Diagnosing Textual Biases in Multimodal Clinical AI2025Teaching AI Stepwise Diagnostic Reasoning With Report-guided Chain-of-thought Learning2025Process Reward Models For Sentence-level Verification Of LVLM Radiology Reports2025RA-RRG: Multimodal Retrieval-Augmented Radiology Report Generation with Key Phrase Extraction2025Reducing Hallucinations of Medical Multimodal Large Language Models with Visual Retrieval-Augmented Generation2025A Comparison of Pre-trained Vision-and-Language Models for Multimodal Representation Learning across Medical Images and Reports2020 · 76 citesAn X-Ray Is Worth 15 Features: Sparse Autoencoders for Interpretable Radiology Report Generation2024 · 2 citesMulti-modal Understanding and Generation for Medical Images and Text via Vision-Language Pre-Training2021 · 1 citesMultimodal Large Language Model driven Radiology Report Generation with Clinical Knowledge Enhancement2024 · 1 cites