{"id":"W2956998909","doi":"10.1038/s42256-019-0068-6","title":"Intelligent feature engineering and ontological mapping of brain tumour histomorphologies by deep learning","year":2019,"lang":"en","type":"article","venue":"Nature Machine Intelligence","topic":"AI in cancer detection","field":"Computer Science","cited_by":49,"is_retracted":false,"has_abstract":false,"ca_institutions":"University Health Network; Princess Margaret Cancer Centre; University of Toronto","funders":"Brain Tumour Charity; Princess Margaret Cancer Foundation","keywords":"Interpretability; Artificial intelligence; Deep learning; Transparency (behavior); Transformative learning; Computer science; Salient; Feature (linguistics); Feature engineering; Machine learning; Psychology; Computer security","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005304893,0.0004310435,0.0004701687,0.002339455,0.0005420648,0.001879605,0.001066465,0.0005696787,0.001241317],"category_scores_gemma":[0.001970608,0.0003021864,0.001249079,0.001591461,0.0005363996,0.001509606,0.001596064,0.001115556,0.0005564722],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008900987,"about_ca_system_score_gemma":0.000972967,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006736912,"about_ca_topic_score_gemma":0.009866421,"domain_scores_codex":[0.9996417,0.00005953452,0.00003231321,0.00009995137,0.0001037394,0.00006274411],"domain_scores_gemma":[0.99951,0.0001318666,0.00005738498,0.0001199315,0.0001527429,0.00002800836],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001805846,0.0002257159,0.01267299,0.000316721,0.0001463945,0.0004085561,0.000679145,0.09333456,0.03164145,0.0475894,0.00777475,0.8050298],"study_design_scores_gemma":[0.00001135908,0.0000361461,0.003375014,0.00007199068,0.00006650821,0.0002457979,0.0003490502,0.8954936,0.01209254,0.08127645,0.006952186,0.00002929454],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06250858,0.0002690617,0.9327908,0.000346868,0.00005432768,0.00006664161,0.0006984564,0.001074299,0.002190918],"genre_scores_gemma":[0.6508884,0.0003692569,0.3442152,0.0001266553,0.000035734,0.0001186879,0.001943369,0.0002301423,0.002072494],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006736912,"threshold_uncertainty_score":0.01339537,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006696904013917719,"score_gpt":0.2354984356166868,"score_spread":0.2288015316027691,"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."}}