Metraipolis › archive › dc_eadc1e689f23
Findings-aware Language-Image Pretraining for CT Volume Interpretation — arXiv:2611.02327
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.02327
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T11:42:23.820Z
- SHA-256 of the archived text
fc70f29d7ec098144e9d77bfde42821bdcda8291fa6f4128334070a0ddc5df59- Stable URL of this page
https://metraipolis.com/documento/dc_eadc1e689f23
How to cite
Findings-aware Language-Image Pretraining for CT Volume Interpretation — arXiv:2611.02327 — arXiv (en), https://arxiv.org/abs/2611.02327 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_eadc1e689f23 (Metraipolis archive dc_eadc1e689f23, sha256 fc70f29d7ec098144e9d77bfde42821bdcda8291fa6f4128334070a0ddc5df59)
BibTeX
@misc{dceadc1e689f23,
title = {Findings-aware Language-Image Pretraining for CT Volume Interpretation — arXiv:2611.02327},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.02327},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_eadc1e689f23; sha256 fc70f29d7ec098144e9d77bfde42821bdcda8291fa6f4128334070a0ddc5df59},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.02327. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Computed tomography (CT) provides diverse patient information and various clinical tasks, for which numerous deep learning models have been investigated. Recent years have seen the development of vision-language foundation models that can comprehensively extract clinical features, driven by representation learning that combines CT volumes with radiology reports. Existing approaches typically adopt Contrastive Language-Image Pre-training (CLIP)-based representation learning, where pairs from different cases are, in principle, treated as negative pairs such that the volume and report embeddings are pushed apart. In the biomedical imaging, however, treating different cases as negative pairs is not always appropriate, particularly when clinical similarity exists. In this study, we propose a supervised representation learning framework grounded in clinical knowledge from language foundation models, rather than the weak supervision used in CLIP. Specifically, we utilized a large language model to extract abnormal finding phrases from reports. We then explicitly constructed the target features that the image encoder should output, as the semantic representation of the extracted findings using a biomedical text embedding model. Our Findings-aware Language-Image Pre-training (FiLIP) outperformed weakly supervised approaches in multi-label zero-shot finding classification in both in-domain and external-domain evaluations, and also proved effective when fine-tuned for the downstream task of radiology report generation. Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Medical Physics (physics.med-ph). Pagina del lavoro: https://arxiv.org/abs/2611.02327 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-03T11:06:37.551Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).