arXiv:2510. 15042v3 Announce Type: replace-cross Abstract: In the 3D medical image domain, vision-language pre-training is used to create vision-language encoders (VLEs) that can support radiologists by retrieving patients with similar abnormalities, predicting likelihoods of abnormality, or, with downstream adaptation, generating radiological reports.
Vision-language pre-training (VLP) holds great promise for general-purpose medical AI by leveraging radiology reports as rich textual supervision, yet existing methods struggle with 3D CT imaging due to inefficient visual backbones and coarse semantic alignment. To address these issues, we propose a tailored VLP framework featuring three key components: (1) a CNN-ViT hybrid encoder that replaces ViT's patch embedding with a 3D CNN backbone to efficiently capture local anatomical details while preserving global attention and compatibility with pre-trained cross-modal priors; (2) a disease-level contrastive learning mechanism using learnable query tokens to dynamically extract disease-specific semantics from full reports and align them with corresponding visual features, thereby disentangling distinct diseases within the same anatomical region; and (3) a diagnosis-aware prompt strategy that employs real clinical phrases and aggregated disease prototypes to bridge the pre-training-inference gap and enhance zero-shot diagnostic reliability.
arXiv:2606. 20477v1 Announce Type: cross Abstract: We study how to train visually grounded vision-language models (VLMs) for radiology without manual spatial annotations.
arXiv:2601.15891v4 Announce Type: replace Abstract: Vision-language pretraining has driven progress in medical image representation learning, but it depends on paired image-text data and can inherit...
arXiv:2409.16183v2 Announce Type: replace Abstract: Radiology is a vital and complex component of modern clinical workflow and covers many tasks. Recently, vision-language (VL) foundation models in m...
arXiv:2608. 08713v1 Announce Type: cross Abstract: Vision-language models offer a promising path toward automating radiology report generation, but applying them to full 3D CT volumes poses substantial computational challenges.
Current evaluation protocols for Vision-Language Models (VLMs) in Radiology Report Generation (RRG) rely on report-level metrics that measure lexical overlap or aggregate clinical correctness. However, such metrics do not test whether individual diagnostic statements stem from the actual pathological evidence visible in the image.
The paper introduces Locked Image Multiple Instance PreTraining (LIMIT), a method that aligns slide‑level pathology reports with patch‑level visual features by freezing a vision encoder and fine‑tuning a text encoder. LIMIT uses report embeddings as cross‑attention queries over bags of patch features, optimizing slide representations via InfoNCE. Applying LIMIT, the authors create CONCH‑Z, which achieves state‑of‑the‑art zero‑shot performance on 22 pathology tasks, outperforming vision‑language encoders trained on curated caption datasets and narrowing the gap with larger slide‑level foundation models.
The paper introduces Diagnostic Loss (DLoss), an objective designed to align radiology report generation with the asymmetric requirement of accurately stating supported diagnoses while avoiding unsupported ones. DLoss operates on decoder token probabilities, aggregating mass over vocabularies for supported and unsupported diagnoses and applying asymmetric pooling to encourage correct diagnoses and suppress spurious ones. Applied to various 3D MedVLMs on 50,000 abdominal CT scans, DLoss improves diagnostic faithfulness without compromising conventional language‑generation metrics.
arXiv:2606. 03180v1 Announce Type: cross Abstract: Vision-language models (VLMs) for radiology have emerged as a scalable paradigm by leveraging image-report pairs naturally produced in clinical workflows.
arXiv:2608. 03890v1 Announce Type: cross Abstract: A clinically useful chest X-ray system must go beyond fluent report generation: it should classify findings with tunable decision thresholds, localize them spatially, and derive the anatomical measurements upon which many diagnoses depend.
arXiv:2608.22619v1 Announce Type: cross Abstract: Generative segmentation provides an alternative to direct pixel-wise prediction by operating on learned latent representations, but effective image-t...