{"id":"W3134874642","doi":"10.1158/1557-3265.adi21-po-018","title":"Abstract PO-018: Computational staining of tumor hypoxia from H&E images using convolutional neural networks","year":2021,"lang":"en","type":"article","venue":"Clinical Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Domtar (Canada); University of Toronto","funders":"","keywords":"Hypoxia (environmental); Stain; H&E stain; Tumor hypoxia; Staining; Pathology; Biology; Convolutional neural network; Necrosis; Chemistry; Medicine; Internal medicine; Radiation therapy; Artificial intelligence; Oxygen; Computer science","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":[0.000611435,0.0008246868,0.0003151679,0.0007004177,0.0001816544,0.0006964331,0.000990522,0.000975633,0.003532002],"category_scores_gemma":[0.001255234,0.0003565318,0.0005675555,0.000358613,0.0002708358,0.0004021655,0.0005084792,0.0006039721,0.0008728989],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001097015,"about_ca_system_score_gemma":0.0008125977,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01434707,"about_ca_topic_score_gemma":0.01202336,"domain_scores_codex":[0.9998678,0.00002064875,0.000006357688,0.00005122364,0.00002864663,0.00002536134],"domain_scores_gemma":[0.9997051,0.0001250029,0.00003479475,0.00003259071,0.00008119123,0.00002123596],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003940047,0.0002068764,0.005477708,0.0001318176,0.0001224053,0.0001843011,0.00003991111,0.7392365,0.01879192,0.001375015,0.006416671,0.2276229],"study_design_scores_gemma":[0.000002297746,0.00001295919,0.0003195625,0.000003782353,0.000003417345,0.000007439791,0.000001802278,0.9976115,0.001651888,0.0002004231,0.0001828517,0.000002031642],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3590604,0.0007896023,0.6198036,0.0009345674,0.0001880824,0.0002257945,0.002211949,0.01112946,0.005656566],"genre_scores_gemma":[0.8277856,0.0002902677,0.1582916,0.0002412291,0.0000496321,0.0001584985,0.003378063,0.0002673546,0.009537816],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01434707,"threshold_uncertainty_score":0.02852714,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2149513091293542,"score_gpt":0.5289596260580025,"score_spread":0.3140083169286483,"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."}}