mlsanityData to 14 Oct 2026

MedVista3D: Vision-Language Modeling for Reducing Diagnostic Errors in 3D CT Disease Detection, Understanding and Reporting

arXiv 2509.03800 ↗First posted 4 Sep 2025cs.CVcited by 4

On the map: Multimodal LLMs / vision-language models → Medical vision-language models

Abstract (arXiv)

Radiologic diagnostic errors-under-reading errors, inattentional blindness, and communication failures-remain prevalent in clinical practice. These issues often stem from missed localized abnormalities, limited global context, and variability in report language. These challenges are amplified in 3D imaging, where clinicians must examine hundreds of slices per scan. Addressing them requires systems with precise localized detection, global volume-level reasoning, and semantically consistent natural language reporting. However, existing 3D vision-language models are unable to meet all three needs jointly, lacking local-global understanding for spatial reasoning and struggling with the variability and noise of uncurated radiology reports. We present MedVista3D, a multi-scale semantic-enriched vision-language pretraining framework for 3D CT analysis. To enable joint disease detection and holistic interpretation, MedVista3D performs local and global image-text alignment for fine-grained representation learning within full-volume context. To address report variability, we apply language model rewrites and introduce a Radiology Semantic Matching Bank for semantics-aware alignment. MedVista3D achieves state-of-the-art performance on zero-shot disease classification, report retrieval, and medical visual question answering, while transferring well to organ segmentation and prognosis prediction. Code and datasets will be released.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Placed in Medical vision-language models, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 31 of its 46 references that are in the map. First posted on arXiv 4 Sep 2025.

Builds on

31 of 46 references.

Closest ancestors · 6

Same direction, newest first

  1. 2025Large-scale and Fine-grained Vision-language Pre-training for Enhanced CT Image Understanding24 Jan
  2. 2024Can Medical Vision-Language Pre-training Succeed with Purely Synthetic Data?17 Oct
  3. 2024Merlin: A Computed Tomography Vision-Language Foundation Model and Dataset10 Jun
  4. 2024Enhancing Representation in Medical Vision-Language Foundation Models via Multi-Scale Information Extraction Techniques3 Jan
  5. 2023CXR-LLAVA: a multimodal large language model for interpreting chest X-ray images22 Oct
  6. 2023LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day1 Jun

Other references · 25

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2024The Llama 3 Herd of Modelscited by 14,715
  3. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  4. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  5. 2023Improved Baselines with Visual Instruction Tuningcited by 4,418
  6. 2022TotalSegmentator: robust segmentation of 104 anatomical structures in CT imagescited by 613
  7. 2019On Variational Bounds of Mutual Informationcited by 559
  8. 2017Deep Learning for Medical Image Analysiscited by 401
  9. 2022Making the Most of Text Semantics to Improve Biomedical Vision--Language Processingcited by 339
  10. 2023Demystifying CLIP Datacited by 270
  11. 2023PMC-CLIP: Contrastive Language-Image Pre-training using Biomedical Documentscited by 212
  12. 2024Generalist Foundation Models from a Multimodal Dataset for 3D Computed Tomographycited by 199
13 more
  1. 2022Unsupervised Medical Image Translation with Adversarial Diffusion Modelscited by 192
  2. 2023BioCLIP: A Vision Foundation Model for the Tree of Lifecited by 161
  3. 2022Multi-Granularity Cross-modal Alignment for Generalized Medical Visual Representation Learningcited by 159
  4. 2023MedKLIP: Medical Knowledge Enhanced Language-Image Pre-Training in Radiologycited by 149
  5. 2023STU-Net: Scalable and Transferable Medical Image Segmentation Models Empowered by Large-Scale Supervised Pre-trainingcited by 100
  6. 2020Machine-Learning-Based Multiple Abnormality Prediction with Large-Scale Chest Computed Tomography Volumescited by 67
  7. 2021UniMiSS: Universal Medical Self-Supervised Learning via Breaking Dimensionality Barriercited by 55
  8. 2024RadGenome-Chest CT: A Grounded Vision-Language Dataset for Chest CT Analysiscited by 42
  9. 2020Joint Modeling of Chest Radiographs and Radiology Reports for Pulmonary Edema Assessmentcited by 37
  10. 2024Contrastive Localized Language-Image Pre-Trainingcited by 33
  11. 2023Artificial General Intelligence for Medical Imaging Analysiscited by 32
  12. 2024CT-GLIP: 3D Grounded Language-Image Pretraining with CT Scans and Radiology Reports for Full-Body Scenarioscited by 30
  13. 2024Multi-View and Multi-Scale Alignment for Contrastive Language-Image Pre-training in Mammographycited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 3.

4 papers.

  1. 2025Self-Supervised Dynamical System Representations for Physiological Time-Seriescited by 3
  2. 2026Learning to Read Where to Look: Disease-Aware Vision-Language Pretraining for 3D CTcited by 3
  3. 2026ASAP: Advancing Medical Volumetric Representation Learning with Anatomy-aware Semantically-adaptive Pre-trainingcited by 1
  4. 2026Volumetric Radiology AI in the Era of Multimodal Large Language Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Bridged Semantic Alignment for Zero-shot 3D Medical Image Diagnosis
  2. 2024MG-3D: Multi-Grained Knowledge-Enhanced 3D Medical Vision-Language Pre-training
  3. 2026Disease-Centric Vision-Language Pretraining with Hybrid Visual Encoding for 3D Computed Tomography
  4. 2023T3D: Advancing 3D Medical Vision-Language Pre-training by Learning Multi-View Visual Consistency
  5. 2025Better Tokens for Better 3D: Advancing Vision-Language Modeling in 3D Medical Imaging
  6. 20243D-CT-GPT: Generating 3D Radiology Reports through Integration of Large Vision-Language Models
  7. 2026NV-Reason-CT: 3D Visual Language Model for CT Analysis
  8. 2025Region-Aware Multimodal Large Language Model via SlowFast Tokenization and Pseudo-Mask Guidance for 3D CT Report Generation