{"id":"W4391136734","doi":"10.1038/s41598-024-52588-1","title":"Multi-channel feature extraction for virtual histological staining of photon absorption remote sensing images","year":2024,"lang":"en","type":"article","venue":"Scientific Reports","topic":"AI in cancer detection","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"Illumisonics (Canada); University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; National Cancer Institute; National Institutes of Health; Canadian Institutes of Health Research; University of Waterloo; Mitacs; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; illumiSonics; Canada Foundation for Innovation; Centre for Bioengineering and Biotechnology, University of Waterloo; Alberta Precision Laboratories","keywords":"Digital pathology; Computer science; Staining; Artificial intelligence; H&E stain; Gold standard (test); Eosin; Feature (linguistics); Histology; Telepathology; Pattern recognition (psychology); Pathology; Biomedical engineering; Medicine; Radiology","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.00174107,0.0001379986,0.000169056,0.0002902063,0.0002708115,0.0004350513,0.0001531243,0.000127095,0.000004859443],"category_scores_gemma":[0.0002144482,0.0001262981,0.0001366653,0.0006081661,0.0001437249,0.0006966615,0.00008736653,0.0001911776,0.00000456645],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002487807,"about_ca_system_score_gemma":0.0001615408,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003618488,"about_ca_topic_score_gemma":0.000008982566,"domain_scores_codex":[0.9979073,0.00004730373,0.0003899129,0.0009639763,0.0004314745,0.0002600755],"domain_scores_gemma":[0.9986891,0.0001032306,0.0002941992,0.0006017297,0.0002604239,0.00005130652],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002297176,0.00002990122,0.000003750476,0.0001318407,0.00002471635,0.0003477788,0.001280855,0.001907521,0.6594789,0.0001080294,0.01017034,0.3264934],"study_design_scores_gemma":[0.0001010586,0.0001054671,0.0001024218,0.0001600479,0.00001878642,0.000862685,0.000114695,0.7450032,0.2210981,0.009561468,0.02268013,0.0001919132],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02150227,0.0005097247,0.9549103,0.0002710468,0.02205317,0.0003216884,0.000002266817,0.0003366168,0.00009291394],"genre_scores_gemma":[0.8665383,0.000006050276,0.1305904,0.00001397503,0.0001048427,0.00000362276,0.00001205117,0.00001440849,0.002716295],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8450361,"threshold_uncertainty_score":0.5150288,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03114922442575336,"score_gpt":0.2996746390540886,"score_spread":0.2685254146283352,"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."}}