{"ID":6267212,"CreatedAt":"2026-07-10T01:11:38.759438437Z","UpdatedAt":"2026-07-13T01:02:08.706470581Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.08503","arxiv_id":"2607.08503","title":"CT-CLIP Representations for Multimodal Lung Cancer Survival Prediction","abstract":"Accurate prognosis prediction is important for treatment planning in lung cancer, but deep learning-driven survival modelling is often limited by the scarcity of curated imaging cohorts with reliable outcome data. This study evaluates whether representations from a domain-specific foundation model can be used for multimodal survival prediction in data-constrained clinical settings. We assess the foundation model CT-CLIP as a feature extractor for pretreatment computed tomography images and clinical variables from 242 diagnosed lung cancer patients. The evaluation includes adaptation strategies based on frozen encoders, full fine-tuning, and low-rank adaptation, together with modality ablations and comparisons with clinical and multimodal baselines. The results show that a frozen CT-CLIP model combined with a trainable lightweight survival head outperforms the clinical baseline and achieves comparable or improved performance relative to other multimodal approaches, and separates patients into clinically meaningful high- and low-risk groups.","short_abstract":"Accurate prognosis prediction is important for treatment planning in lung cancer, but deep learning-driven survival modelling is often limited by the scarcity of curated imaging cohorts with reliable outcome data. This study evaluates whether representations from a domain-specific foundation model can be used for multi...","url_abs":"https://arxiv.org/abs/2607.08503","url_pdf":"https://arxiv.org/pdf/2607.08503v1","authors":"[\"Sofie Allgöwer\",\"Mikael Johansson\",\"Andreas Hallqvist\",\"Jonas Andersson\",\"Åse Johnsson\",\"Ida Häggström\",\"Jennifer Alvén\"]","published":"2026-07-09T14:00:14Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}