🛰️ Daily AI Frontier
‹ back to 2026-07-16

Fine-Grained Vision-Language Pretraining with Organ-Conditioned Pattern Tokens for CT Understanding

Research Multimodal & Generative

Merged summary

TL;DR — OCP-CT is a vision-language pretraining framework that aligns 3D CT volumes with radiology reports at the fine-grained level of "organ-conditioned radiological patterns," improving zero-shot abnormality diagnosis over prior methods.

  • Motivation: global scan-report contrast obscures per-organ evidence, while direct organ-level alignment is too coarse since one anatomy can present multiple distinct radiological appearances.
  • Method: keeps a stable global CT-report contrastive branch plus an "organ pattern interface" — sparse Mixture-of-Experts routes image/text tokens by latent radiological pattern, learnable slots query them into continuous pattern tokens, and paired token contrast aligns image-text pattern tokens using soft targets from report-derived clinical similarity.
  • Results: zero-shot abnormality diagnosis average AUROC of 84.5% on CT-RATE and 69.9% on RAD-ChestCT, absolute gains of +6.7 and +0.8 points over the strongest prior reported results.
  • Note: cross-modal (3D CT imaging + text) medical VLM, evaluated on the public CT-RATE and RAD-ChestCT benchmarks.

Sources (1)

Fine-Grained Vision-Language Pretraining with Organ-Conditioned Pattern Tokens for CT Understanding

arXiv cs.CV Guoliang You, Xiaomeng Chu 2026-07-15 arXiv:2607.13892

TL;DR — OCP-CT is a vision-language pretraining framework that aligns 3D CT volumes with radiology reports at the fine-grained level of "organ-conditioned radiological patterns," improving zero-shot abnormality diagnosis over prior methods.

  • Motivation: global scan-report contrast obscures per-organ evidence, while direct organ-level alignment is too coarse since one anatomy can present multiple distinct radiological appearances.
  • Method: keeps a stable global CT-report contrastive branch plus an "organ pattern interface" — sparse Mixture-of-Experts routes image/text tokens by latent radiological pattern, learnable slots query them into continuous pattern tokens, and paired token contrast aligns image-text pattern tokens using soft targets from report-derived clinical similarity.
  • Results: zero-shot abnormality diagnosis average AUROC of 84.5% on CT-RATE and 69.9% on RAD-ChestCT, absolute gains of +6.7 and +0.8 points over the strongest prior reported results.
  • Note: cross-modal (3D CT imaging + text) medical VLM, evaluated on the public CT-RATE and RAD-ChestCT benchmarks.
item →