{"id":"W4285109585","doi":"10.1109/tevc.2022.3178299","title":"Evolutionary Computation in Action: Hyperdimensional Deep Embedding Spaces of Gigapixel Pathology Images","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Evolutionary Computation","topic":"AI in cancer detection","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo; McMaster University; Ontario Tech University","funders":"","keywords":"Artificial intelligence; Interpretability; Computer science; Digital pathology; Deep learning; Pattern recognition (psychology); Feature vector; Evolutionary algorithm; Evolutionary computation; Feature (linguistics); Feature selection; Visualization; Representation (politics)","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":[0.0004640835,0.0002932719,0.0003397648,0.001175105,0.0008619663,0.00003782679,0.0004212449,0.0001219922,0.000087104],"category_scores_gemma":[0.00001070421,0.0003717894,0.0001833233,0.001729917,0.0001575219,0.001102988,0.00003047332,0.0006338931,0.00002824877],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001314098,"about_ca_system_score_gemma":0.0003084045,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001278614,"about_ca_topic_score_gemma":0.00003159931,"domain_scores_codex":[0.9965011,0.0006480507,0.0007274711,0.0007862875,0.0009527831,0.0003843062],"domain_scores_gemma":[0.9984673,0.0004684608,0.0003881104,0.0003220705,0.0002658447,0.00008818891],"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":[0.00014075,0.0004847218,0.0001344096,0.00002657083,0.00003118808,0.00002450549,0.000456063,0.9607597,0.003877027,0.0003920813,0.0004110517,0.03326193],"study_design_scores_gemma":[0.001071835,0.0005961367,0.01247429,0.00003067498,0.00002207925,0.0004846836,0.0004081086,0.9767647,0.001300067,0.006342061,0.0001561715,0.0003491995],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07498771,0.0002785812,0.9202361,0.0008798657,0.002715712,0.0004316084,0.00005062719,0.0002811813,0.0001386763],"genre_scores_gemma":[0.9189112,0.00003343589,0.08049677,0.0001349301,0.00006952274,0.0002026276,0.00004171357,0.00002742984,0.00008234673],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8439235,"threshold_uncertainty_score":0.9998734,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02046694541035996,"score_gpt":0.2799315033262245,"score_spread":0.2594645579158645,"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."}}