{"id":"W7077476230","doi":"10.5281/zenodo.16943111","title":"Multi-view deep learning of highly multiplexed imaging data improves association of cell states with clinical outcomes","year":2025,"lang":"en","type":"preprint","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Geochemistry and Geologic Mapping","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Lunenfeld-Tanenbaum Research Institute; Ontario Institute for Cancer Research; University of Toronto","funders":"","keywords":"Deep learning; Pipeline (software); Association (psychology); Multiplexing; Pattern recognition (psychology); Object (grammar); File format; Test data","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00242046,0.001050289,0.0007468445,0.001288169,0.0003262737,0.001371989,0.0009561836,0.001286258,0.05021903],"category_scores_gemma":[0.009326763,0.0003808925,0.0014705,0.0007282353,0.0003267771,0.0006923127,0.001016001,0.001806538,0.01522138],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000805022,"about_ca_system_score_gemma":0.001032605,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00488344,"about_ca_topic_score_gemma":0.006064284,"domain_scores_codex":[0.9993848,0.0001069869,0.00004291885,0.000231223,0.0001516766,0.00008251275],"domain_scores_gemma":[0.9966249,0.001927066,0.0001782222,0.0005169639,0.0004683029,0.0002845406],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.005950812,0.001129373,0.09712195,0.001119048,0.001103488,0.0005528526,0.0001394836,0.027723,0.03487054,0.001556329,0.6024457,0.2262874],"study_design_scores_gemma":[0.002591116,0.002340454,0.2346715,0.0006586204,0.001060092,0.0024241,0.0003994838,0.4070463,0.1842014,0.01771027,0.1465244,0.0003721631],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.2637273,0.002154592,0.08436052,0.005622221,0.002204587,0.0004637379,0.603574,0.02376478,0.01412828],"genre_scores_gemma":[0.4434825,0.0007355119,0.06208613,0.001558973,0.0003973113,0.0006520664,0.4674003,0.003846378,0.01984096],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.05021903,"threshold_uncertainty_score":0.1679994,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04704406491840603,"score_gpt":0.290664044827121,"score_spread":0.243619979908715,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}