arXiv cs.AI· S\'el\'ena Jean-Mactoux, Sophie Loizillon, Ghina Jardali, Amandine Cromb\'e, Nathalie Lassau, Alexandre B\^one·· 2 小时前AI 评分41
CAPTOR:面向胸腹盆肿瘤 CT 的视觉语言基础模型
CAPTOR: a vision-language foundation model for Chest-Abdomen-Pelvis Oncologic CT
AI 导读
研究者发布 CAPTOR,一个针对肿瘤学胸腹盆(CAP)CT 的视觉语言基础模型,采用解剖结构化预处理策略,在 25,512 组多中心 CT-报告对上完成对比预训练。
正文 · 原文
Abstract:Objectives: Radiologists interpreting oncologic chest-abdomen-pelvis (CAP) CT must also detect non-oncologic conditions, yet existing CT foundation models are trained on single anatomical regions or on non-oncologic data. We developed and evaluated CAPTOR, a vision-language foundation model for oncologic CAP CT that uses an anatomically structured preprocessing strategy to learn from whole examinations.
Materials & Methods: CAPTOR is a contrastive vision-language model pretrained on 25,512 predominantly oncologic CAP CT-report pairs (single or multiple series) from a retrospective multicenter dataset (North America, Europe, Asia). It was compared with five CT foundation models, a larger-scale variant (CAPTOR-100K) and an ablation without anatomical preprocessing (CAPTOR-NoPre) on classification and retrieval using held-out internal and public test sets, and on survival prediction using TumorImagingBench. Confidence intervals and pairwise comparisons used patient-level bootstrap and permutation tests.
Results: On 10,794 test studies, CAPTOR achieved higher AUC than all five models on CAP (0.767 vs. 0.695 for the next-best model; p<0.001) and oncologic subsets (0.784 vs. 0.734; p<0.001), with superior retrieval on both, and ranked first on three of four oncologic survival benchmarks. Despite substantially fewer training examinations, it performed comparably to CAPTOR-100K. Removing the anatomically structured preprocessing reduced classification performance, including on the institutionally held-out test subset (macro-AUC 0.737 vs. 0.691 for CAPTOR-NoPre, p<0.01).
Conclusion: Anatomically structured preprocessing enabled whole-examination CAP CT interpretation, including multiple-series acquisitions, and improved downstream performance. CAPTOR outperformed state-of-the-art CT foundation models on CAP and oncologic subsets while matching a substantially larger-scale variant.
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.14226 [cs.CV] |
| (or arXiv:2610.14226v2 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2610.14226 arXiv-issued DOI via DataCite |
Submission history
From: Séléna Jean-Mactoux [view email]
[v1]
Fri, 9 Oct 2026 18:39:01 UTC (4,108 KB)
[v2]
Wed, 18 Nov 2026 17:38:45 UTC (7,108 KB)
来源:arXiv cs.AI · arxiv.org