{"id":"W4408618258","doi":"10.1101/2025.03.14.643377","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":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Cell Image Analysis Techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; Sinai Health System; Lunenfeld-Tanenbaum Research Institute; Institute of Cancer Research; Ontario Institute for Cancer Research; University of Toronto","funders":"","keywords":"Association (psychology); Multiplexing; Computer science; Deep learning; Artificial intelligence; Medical physics; Medicine; Psychology; Telecommunications","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001312924,0.0004503069,0.0009544911,0.0001879321,0.00006045226,0.00006024746,0.001036196,0.0004594647,0.000004258816],"category_scores_gemma":[0.001121612,0.0004307652,0.0002662099,0.0002569166,0.0001389967,0.0000200348,0.001643045,0.000586447,0.000001520849],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000702144,"about_ca_system_score_gemma":0.0003992758,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001737922,"about_ca_topic_score_gemma":0.00002901557,"domain_scores_codex":[0.9967661,0.000347873,0.001077174,0.001146885,0.0003165794,0.0003454046],"domain_scores_gemma":[0.9949043,0.0001473161,0.001703197,0.002143137,0.001005678,0.00009642061],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00003188734,0.0002185263,0.2688916,0.0004165974,0.0004720515,0.000003017063,0.000004017854,0.00005298344,0.7297593,0.000001220361,0.0001315525,0.00001730547],"study_design_scores_gemma":[0.0008110686,0.00007637052,0.1053483,0.0002280434,0.0005635537,2.834048e-9,0.00001000425,0.004109038,0.8860191,1.803682e-7,0.002368402,0.0004659473],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9771491,0.003931207,0.01726256,0.00007425917,0.0001620798,0.0008691675,0.000372288,0.0001656116,0.0000137359],"genre_scores_gemma":[0.9348208,0.002599698,0.06223222,0.00007943012,0.00007572185,0.00004179887,0.00002875181,0.0000665971,0.0000549823],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1635433,"threshold_uncertainty_score":0.9998144,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01270284203227544,"score_gpt":0.2787785325572751,"score_spread":0.2660756905249997,"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."}}