{"id":"W3163753640","doi":"10.1038/s41598-024-52183-4","title":"DiagSet: a dataset for prostate cancer histopathological image classification","year":2024,"lang":"en","type":"article","venue":"Scientific Reports","topic":"AI in cancer detection","field":"Computer Science","cited_by":41,"is_retracted":false,"has_abstract":true,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute","funders":"European Regional Development Fund; National Center for Research and Development","keywords":"Medical diagnosis; Thresholding; Computer science; Artificial intelligence; Pattern recognition (psychology); Prostate cancer; Cancer detection; Cancer; Image (mathematics); Machine learning; Radiology; Medicine","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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001528566,0.0001209159,0.0001134373,0.0001659693,0.0002964909,0.00122038,0.0003384353,0.00005585756,0.00002353632],"category_scores_gemma":[0.0001030074,0.0001012699,0.00006960367,0.000681548,0.0001923228,0.0008951919,0.0001372133,0.000110199,0.00006845087],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002565751,"about_ca_system_score_gemma":0.0002977376,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002231984,"about_ca_topic_score_gemma":0.00002253338,"domain_scores_codex":[0.9976693,0.00003504812,0.0003578402,0.001270744,0.0003768076,0.000290257],"domain_scores_gemma":[0.9984875,0.00005250734,0.000139516,0.001104564,0.0001323334,0.00008355839],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000007234062,0.00004474439,0.0002291496,0.0001317777,0.0000100721,0.0004920969,0.0006690395,0.0000380791,0.08706926,0.002134647,0.7596842,0.1494897],"study_design_scores_gemma":[0.00004619201,0.00003682986,0.0005462727,0.00004044822,0.00001177689,0.0002340799,0.00001148512,0.0409531,0.01000898,0.02376451,0.924174,0.0001723164],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01889286,0.001726092,0.9062753,0.006062853,0.06298681,0.001751427,0.0006144313,0.001036362,0.0006538767],"genre_scores_gemma":[0.9292448,0.00006919829,0.05625924,0.0002753072,0.0006187819,0.002511834,0.001788391,0.00005050977,0.009181952],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9103519,"threshold_uncertainty_score":0.9998165,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03572578786713289,"score_gpt":0.3208717744251828,"score_spread":0.2851459865580499,"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."}}