mlsanityData to 7 Oct 2026

Libra: Leveraging Temporal Images for Biomedical Radiology Analysis

arXiv 2411.19378 ↗First posted 28 Nov 2024cs.CV cs.AI cs.CLcited by 29

Not on the map. Why?

Abstract (arXiv)

Radiology report generation (RRG) requires advanced medical image analysis, effective temporal reasoning, and accurate text generation. While multimodal large language models (MLLMs) align with pre-trained vision encoders to enhance visual-language understanding, most existing methods rely on single-image analysis or rule-based heuristics to process multiple images, failing to fully leverage temporal information in multi-modal medical datasets. In this paper, we introduce Libra, a temporal-aware MLLM tailored for chest X-ray report generation. Libra combines a radiology-specific image encoder with a novel Temporal Alignment Connector (TAC), designed to accurately capture and integrate temporal differences between paired current and prior images. Extensive experiments on the MIMIC-CXR dataset demonstrate that Libra establishes a new state-of-the-art benchmark among similarly scaled MLLMs, setting new standards in both clinical relevance and lexical accuracy.

Key facts. Cited by 29 papers in the map (data through 7 Oct 2026). Builds on 47 of its 70 references that are in the map. First posted on arXiv 28 Nov 2024.

Builds on

47 of 70 references.

References · 47

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  4. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  5. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  6. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,462
  7. 2017Squeeze-and-Excitation Networkscited by 4,763
  8. 2023MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Modelscited by 2,689
  9. 2017Non-local Neural Networkscited by 2,290
  10. 2019CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparisoncited by 1,410
  11. 2023LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Daycited by 1,287
  12. 2019ZeRO: Memory Optimizations Toward Training Trillion Parameter Modelscited by 1,278
35 more
  1. 2023Vision-Language Models for Vision Tasks: A Surveycited by 834
  2. 2019MIMIC-CXR-JPG, a large publicly available database of labeled chest radiographscited by 590
  3. 2023BiomedCLIP: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairscited by 506
  4. 2020Generating Radiology Reports via Memory-driven Transformercited by 363
  5. 2020CheXbert: Combining Automatic Labelers and Expert Annotations for Accurate Radiology Report Labeling Using BERTcited by 329
  6. 2021RadGraph: Extracting Clinical Entities and Relations from Radiology Reportscited by 310
  7. 2019PadChest: A large chest x-ray image dataset with multi-label annotated reportscited by 308
  8. 2023Learning to Exploit Temporal Structure for Biomedical Vision-Language Processingcited by 210
  9. 2022Cross-modal Memory Networks for Radiology Report Generationcited by 183
  10. 2022VLP: A Survey on Vision-Language Pre-trainingcited by 159
  11. 2020When Radiology Report Generation Meets Knowledge Graphcited by 144
  12. 2018TieNet: Text-Image Embedding Network for Common Thorax Disease Classification and Reporting in Chest X-rayscited by 139
  13. 2020Improving Factual Completeness and Consistency of Image-to-Text Radiology Report Generationcited by 139
  14. 2023Interactive and Explainable Region-guided Radiology Report Generationcited by 139
  15. 2019Clinically Accurate Chest X-Ray Report Generationcited by 138
  16. 2024Exploring scalable medical image encoders beyond text supervisioncited by 129
  17. 2023Dynamic Graph Enhanced Contrastive Learning for Chest X-ray Report Generationcited by 114
  18. 2023METransformer: Radiology Report Generation by Transformer with Multiple Learnable Expert Tokenscited by 98
  19. 2023From CLIP to DINO: Visual Encoders Shout in Multi-modal Large Language Modelscited by 96
  20. 2021Pre-trained Language Models in Biomedical Domain: A Systematic Surveycited by 87
  21. 2022Improving the Factual Correctness of Radiology Report Generation with Semantic Rewardscited by 82
  22. 2023Advancing Radiograph Representation Learning with Masked Record Modelingcited by 75
  23. 2023MAIRA-1: A specialised large multimodal model for radiology report generationcited by 72
  24. 2021Knowledge Matters: Radiology Report Generation with General and Specific Knowledgecited by 68
  25. 2023EHRXQA: A Multi-Modal Question Answering Dataset for Electronic Health Records with Chest X-ray Imagescited by 53
  26. 2021Progressive Transformer-Based Generation of Radiology Reportscited by 43
  27. 2024Automated Radiology Report Generation: A Review of Recent Advancescited by 43
  28. 2023Expert Knowledge-Aware Image Difference Graph Representation Learning for Difference-Aware Medical Visual Question Answeringcited by 41
  29. 2023ORGAN: Observation-Guided Radiology Report Generation via Tree Reasoningcited by 39
  30. 2023Multimodal Image-Text Matching Improves Retrieval-based Chest X-Ray Report Generationcited by 37
  31. 2024MedVersa: A Generalist Foundation Model for Medical Image Interpretationcited by 37
  32. 2023Controllable Chest X-Ray Report Generation from Longitudinal Representationscited by 23
  33. 2023RECAP: Towards Precise Radiology Report Generation via Dynamic Disease Progression Reasoningcited by 22
  34. 2024MedM2G: Unifying Medical Multi-Modal Generation via Cross-Guided Diffusion with Visual Invariantcited by 21
  35. 2024M4CXR: Exploring Multi-task Potentials of Multi-modal Large Language Models for Chest X-ray Interpretationcited by 16

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 10; 2026: 19.

29 papers.

Sort:

By area:

  1. 2025RadEval: A framework for radiology text evaluationcited by 21
  2. 2025RADAR: Enhancing Radiology Report Generation with Supplementary Knowledge Injectioncited by 11
  3. 2025MedSG-Bench: A Benchmark for Medical Image Sequences Groundingcited by 8
  4. 2025Lunguage: A Benchmark for Structured and Sequential Chest X-ray Interpretationcited by 8
  5. 2025CXRAgent: Director-Orchestrated Multi-Stage Reasoning for Chest X-Ray Interpretationcited by 7
  6. 2025CCD: Mitigating Hallucinations in Radiology MLLMs via Clinical Contrastive Decodingcited by 4
  7. 2025A Review of Longitudinal Radiology Report Generation: Dataset Composition, Methods, and Performance Evaluationcited by 3
  8. 2026Enhancing Reinforcement Learning for Radiology Report Generation with Evidence-aware Rewards and Self-correcting Preference Learningcited by 3
  9. 2025CX-Mind: A Pioneering Multimodal Large Language Model for Interleaved Reasoning in Chest X-ray via Curriculum-Guided Reinforcement Learningcited by 2
  10. 2026A data- and compute-efficient chest X-ray foundation model beyond aggressive scalingcited by 2
  11. 2026Multi-Modal Multi-Agent Reinforcement Learning for Radiology Report Generationcited by 1
  12. 2026Seeing Like Radiologists: Context- and Gaze-Guided Vision-Language Pretraining for Chest X-rayscited by 1
17 more
  1. 2026MI-CXR: A Benchmark for Longitudinal Reasoning over Multi-Interval Chest X-rayscited by 1
  2. 2025Time to Revist Exact Matchcited by 0
  3. 2025Closing the Performance Gap Between AI and Radiologists in Chest X-Ray Reportingcited by 0
  4. 2026Standardizing Longitudinal Radiology Report Evaluation via Large Language Model Annotationcited by 0
  5. 2026MedGPT-oss: Training a General-Purpose Vision-Language Model for Biomedicinecited by 0
  6. 2026Ran Score: a LLM-based Evaluation Score for Radiology Report Generationcited by 0
  7. 2026Radiology Report Generation for Low-Quality X-Ray Imagescited by 0
  8. 2026CXRMate-2: Structured Multimodal Temporal Embeddings and Tractable Reinforcement Learning for Clinically Acceptable Chest X-ray Radiology Report Generationcited by 0
  9. 2026CCS: Clinical Consensus Selection for Radiology Report Generationcited by 0
  10. 2026Learning Directional Semantic Transitions for Longitudinal Chest X-ray Analysiscited by 0
  11. 2026SHOVIR: A Benchmark for Evaluating Vision Shortcut Learning in Radiology Report Generationcited by 0
  12. 2026GRCD: Grounded Region Change Detection for Multi-Finding Chest X-Ray Pairscited by 0
  13. 2026PanDent: Toward Comprehensive Tooth-Level Structure-Language Consistency in Dental Radiologycited by 0
  14. 2026LoMeVQA: A Comprehensive Benchmark for Longitudinal Medical VQAcited by 0
  15. 2026RadFusion: Towards Threshold-Controllable Radiology Report Generationcited by 0
  16. 2026CheXGround: Anatomical Region Tokens for Grounded Longitudinal Chest X-ray Interpretationcited by 0
  17. 2026Reporting Practice Matters: The Impact of Reference Choice on Chest X-ray Report Evaluationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Unlocking the Power of Spatial and Temporal Information in Medical Multimodal Pre-training
  2. 2025CoCa-CXR: Contrastive Captioners Learn Strong Temporal Structures for Chest X-Ray Vision-Language Understanding
  3. 2026Learning to See Locally and Align Clinically with Pathology Semantics for Radiology Report Generation
  4. 2023MedXChat: A Unified Multimodal Large Language Model Framework towards CXRs Understanding and Generation
  5. 2024TiBiX: Leveraging Temporal Information for Bidirectional X-ray and Report Generation
  6. 2025A Generative Framework for Bidirectional Image-Report Understanding in Chest Radiography
  7. 2026LUMEN: Longitudinal Multi-Modal Radiology Model for Prognosis and Diagnosis
  8. 2025Exploring the Capabilities of Large Language Model Encoders for Image-Text Retrieval in Chest X-rays