{"paper":{"title":"Time-driven Survival Analysis from FDG-PET/CT in Non-Small Cell Lung Cancer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A model that adds a time-horizon input to FDG-PET/CT image embeddings predicts overall survival more accurately in non-small cell lung cancer.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ashish Chauhan, Elin Lundstr\\\"om, H{\\aa}kan Ahlstr\\\"om, Joel Kullberg, Johan \\\"Ofverstedt, Sambit Tarai, Therese Sj\\\"oholm, Veronica Sanchez Rodriguez","submitted_at":"2026-04-08T09:43:30Z","abstract_excerpt":"Purpose: Automated medical image-based prediction of clinical outcomes, such as overall survival (OS), has great potential in improving patient prognostics and personalized treatment planning. We developed a deep regression framework using tissue-wise FDG-PET/CT projections as input, along with a temporal input representing a scalar time horizon (in days) to predict OS in patients with Non-Small Cell Lung Cancer (NSCLC).\n  Methods: The proposed framework employed a ResNet-50 backbone to process input images and generate corresponding image embeddings. The embeddings were then combined with tem"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"The incorporation of temporal data with image embeddings demonstrated an advantage in predicting OS, outperforming the baseline method with an improvement in AUC of 4.3%.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the U-CAN cohort (n=556 training, n=292 test) is representative of broader NSCLC populations and that the time-horizon input generalizes without overfitting to the specific follow-up patterns or censoring mechanisms in this dataset.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A time-aware ResNet-based model on PET/CT images improves overall survival prediction in NSCLC by incorporating temporal data, achieving 4.3% higher AUC than fixed-time baselines.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A model that adds a time-horizon input to FDG-PET/CT image embeddings predicts overall survival more accurately in non-small cell lung cancer.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"d9e63dc848de424c34e56b4abe7d6766c26bc7ce28c823564a43d0e05c8f439e"},"source":{"id":"2604.06885","kind":"arxiv","version":1},"verdict":{"id":"4baf6538-2c2a-427b-93f0-4690862f1334","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T18:52:52.622242Z","strongest_claim":"The incorporation of temporal data with image embeddings demonstrated an advantage in predicting OS, outperforming the baseline method with an improvement in AUC of 4.3%.","one_line_summary":"A time-aware ResNet-based model on PET/CT images improves overall survival prediction in NSCLC by incorporating temporal data, achieving 4.3% higher AUC than fixed-time baselines.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the U-CAN cohort (n=556 training, n=292 test) is representative of broader NSCLC populations and that the time-horizon input generalizes without overfitting to the specific follow-up patterns or censoring mechanisms in this dataset.","pith_extraction_headline":"A model that adds a time-horizon input to FDG-PET/CT image embeddings predicts overall survival more accurately in non-small cell lung cancer."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.06885/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":26,"sample":[{"doi":"10.3322/caac.21834","year":2022,"title":"Siegel, Isabelle Soerjomataram, and Ahmedin Jemal","work_id":"d78a12d5-b1cc-4dc9-925d-a8a8032fc002","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1016/j.neo.2023.100955","year":2024,"title":"Kolb T, M¨ uller S, M¨ oller P, et al., Molecular heterogeneity in histomorphologic subtypes of lung adenocarcinoma represents a challenge for treatment decision, Neoplasia 49 (2024) 100955.doi:https:","work_id":"ddc24b06-0d97-4a8f-8461-231c12a35454","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1634/theoncologist.2017-0659","year":2018,"title":"Lababede O, Meziane MA, The Eighth Edition of TNM Staging of Lung Cancer: Reference Chart and Diagrams, Oncologist 23 (7) (2018) 844–848.doi:https: //doi.org/10.1634/theoncologist.2017-0659. 15","work_id":"b9a48ce9-3367-4d4a-8041-53c0188a7148","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1038/bjc.2017.232","year":2017,"title":"Alexander M, Wolfe R, Ball D, et al., Lung cancer prognostic index: a risk score to predict overall survival after the diagnosis of non-small-cell lung cancer, Br J Cancer 117 (5) (2017) 744–751.doi:h","work_id":"c49de7d7-d800-40ff-a099-cb9a62060cd1","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1109/access.2019.2916586","year":2019,"title":"Yang CH, Moi SH, Ou-Yang F, et al., Identifying Risk Stratification Associated With a Cancer for Overall Survival by Deep Learning-Based CoxPH, IEEE Access 7 (2019) 67708–67717.doi:https://doi.org/10.","work_id":"16a69149-204a-465a-a49f-da3212e67f44","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":26,"snapshot_sha256":"7aa8f4ea3537a4d13b43053347b6e824217179dace30855c436d9e3e171487f8","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"8e47f88af5069f2762e71fd766889be20d2b787c03a604ce98391cbb9106599d"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}