paper-with-me

홈 › Papers

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

2025-09-04 · Yuheng Li, Yenho Chen, Yuxiang Lai, Jike Zhong, Vanessa Wildman, Xiaofeng Yang 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.

📄 PDF Abstract BibTeX arXiv:2509.03800

Code (0)

등록된 구현이 없습니다.

Tasks

Visual Question AnsweringRepresentation LearningSpatial Reasoning

Similar Papers 제목 키워드 기반

MEDVISTAGYM: A Scalable Training Environment for Thinking with Medical Images via Tool-Integrated Reinforcement Learning

2026-01-12 · Meng Lu, Yuxing Lu, Yuchen Zhuang, Megan Mullins 외 arxiv

Vision language models (VLMs) achieve strong performance on general image understanding but struggle to think with medical images, especially when performing multi-step reasoning through iterative visual interaction. Med…

Reinforcement LearningMultimodal ReasoningVisual Reasoning

U-VLM: Hierarchical Vision Language Modeling for Report Generation

2026-02-28 · Pengcheng Shi, Minghui Zhang, Kehan Song, Jiaqi Liu 외 arxiv

Automated radiology report generation is key for reducing radiologist workload and improving diagnostic consistency, yet generating accurate reports for 3D medical imaging remains challenging. Existing vision-language mo…

Better Tokens for Better 3D: Advancing Vision-Language Modeling in 3D Medical Imaging

2025-10-23 · Ibrahim Ethem Hamamci, Sezgin Er, Suprosanna Shit, Hadrien Reynaud 외 arxiv

Recent progress in vision-language modeling for 3D medical imaging has been fueled by large-scale computed tomography (CT) corpora with paired free-text reports, stronger architectures, and powerful pretrained models. Th…

Seeing Like Radiologists: Context- and Gaze-Guided Vision-Language Pretraining for Chest X-rays

2026-03-27 · Kang Liu, Zhuoqi Ma, Siyu Liang, Yunan Li 외 arxiv

Despite recent advances in medical vision-language pretraining, existing models still struggle to capture the diagnostic workflow: radiographs are typically treated as context-agnostic images, while radiologists' gaze --…

Representation LearningContrastive LearningVisual ReasoningText Retrieval

Boosting Vision Semantic Density with Anatomy Normality Modeling for Medical Vision-language Pre-training

2025-08-01 · Weiwei Cao, Jianpeng Zhang, Zhongyi Shui, Sinuo Wang 외 arxiv

Vision-language pre-training (VLP) has great potential for developing multifunctional and general medical diagnostic capabilities. However, aligning medical images with a low signal-to-noise ratio (SNR) to reports with a…

Contrastive LearningTransfer Learning