Metraipolis › archive › dc_f3767d24ecda

CIGTSurv: Clinical Information Guided Tri-modal Survival Prediction with Local Prototype Association and Global Feature Alignment — arXiv:2608.03247

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.03247
License (as archived)
CC0-1.0
Archived
2026-10-31T12:31:25.764Z
SHA-256 of the archived text
12b7e4f84c80d1de48a0bd90f4bc3b01340b734a98c642cec44ab4fd0f41112e
Stable URL of this page
https://metraipolis.com/documento/dc_f3767d24ecda

How to cite

CIGTSurv: Clinical Information Guided Tri-modal Survival Prediction with Local Prototype Association and Global Feature Alignment — arXiv:2608.03247 — arXiv (en), https://arxiv.org/abs/2608.03247 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f3767d24ecda (Metraipolis archive dc_f3767d24ecda, sha256 12b7e4f84c80d1de48a0bd90f4bc3b01340b734a98c642cec44ab4fd0f41112e)
BibTeX
@misc{dcf3767d24ecda,
  title = {CIGTSurv: Clinical Information Guided Tri-modal Survival Prediction with Local Prototype Association and Global Feature Alignment — arXiv:2608.03247},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.03247},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f3767d24ecda; sha256 12b7e4f84c80d1de48a0bd90f4bc3b01340b734a98c642cec44ab4fd0f41112e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.03247. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Multimodal learning has significantly advanced survival prediction by integrating pathology images with genomic data. However, clinical information, despite its critical role in reflecting a patient' s overall health, remains underutilized due to its discrete, sparse, and low-dimensional nature. Furthermore, the inherent heterogeneity across these modalities pose significant challenges in modeling cross-modal interactions. In this paper, we propose CIGTSurv, a Clinical Information Guided Tri-modal framework for Survival prediction. Specifically, we first design a holistic text template and use pretrained foundation models to transform clinical tabular data into high-dimensional tokenized embeddings. Using clinical information as an anchor, we then introduce a dual-level interaction mechanism: 1) a local prototype association (LPA) module based on cross-attention to explicitly learn token-level correspondences between different modalities, and 2) a global feature alignment (GFA) loss based on Maximum Mean Discrepancy (MMD) to implicitly enhance cross-modal distribution consistency. Extensive experiments on five TCGA cancer cohorts demonstrate that CIGTSurv achieves state-of-the-art (SOTA) survival prediction performance. Our source code is publicly available at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-05 in cs.CL).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2608.03247 — 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 2026-10-31T12:17:37.810Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-05?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).