Metraipolis › archive › dc_37896015cd5d
Integrating Unimodal and Vision-Language Representations in Latent Space for Multi-Label Chest X-Ray Classification — arXiv:2609.09185
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.09185
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T10:57:04.531Z
- SHA-256 of the archived text
2d93b9a1e4e8aa6ac6b99e8ec378acbfa63e43accd8b11afb2f710785c11361e- Stable URL of this page
https://metraipolis.com/documento/dc_37896015cd5d
How to cite
Integrating Unimodal and Vision-Language Representations in Latent Space for Multi-Label Chest X-Ray Classification — arXiv:2609.09185 — arXiv (en), https://arxiv.org/abs/2609.09185 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_37896015cd5d (Metraipolis archive dc_37896015cd5d, sha256 2d93b9a1e4e8aa6ac6b99e8ec378acbfa63e43accd8b11afb2f710785c11361e)
BibTeX
@misc{dc37896015cd5d,
title = {Integrating Unimodal and Vision-Language Representations in Latent Space for Multi-Label Chest X-Ray Classification — arXiv:2609.09185},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.09185},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_37896015cd5d; sha256 2d93b9a1e4e8aa6ac6b99e8ec378acbfa63e43accd8b11afb2f710785c11361e},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.09185. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Multi-label chest X-ray classification has attracted considerable attention in recent years, with the effective use of visual representations and clinical semantic knowledge playing an important role. This study proposes a framework that combines unimodal representations from RAD-DINO with vision--language representations from BioViL-T for the classification of 14 labels in the MIMIC-CXR-JPG dataset. The RAD-DINO and BioViL-T embeddings and their combined representation are refined separately in latent space before being normalized and fused across the three branches. In addition to improving classification performance, the study aims to clarify the role of each embedding source and the degree to which they complement one another. Experiments show that RAD-DINO outperforms BioViL-T when used independently, whereas early fusion further improves the results, indicating that the two embedding sources contain complementary information. The best-performing model achieves a mean AUROC of 0.840 and an mAP of 0.467. Ablation analysis shows that hybrid fusion provides consistent and statistically significant improvements over early fusion when each embedding source is refined in latent space, suggesting that fusion effectiveness depends on the quality of the representation supplied by each branch. However, the study has only been evaluated internally on MIMIC-CXR-JPG; its generalizability to data from other healthcare institutions therefore remains to be validated. The source code is available at: this https URL . Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-10 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.09185 — 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 2026-10-16T10:02:34.276Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-10?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).