{"id":"W2906465680","doi":"10.4103/jpi.jpi_70_18","title":"The Importance of eSlide Macro Images for Primary Diagnosis with Whole Slide Imaging","year":2018,"lang":"en","type":"article","venue":"Journal of Pathology Informatics","topic":"AI in cancer detection","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":true,"ca_institutions":"University Health Network","funders":"National Cancer Institute","keywords":"Computer science; Macro; Digital pathology; Scanner; Digitization; Computer vision; Artificial intelligence; Image quality; Rendering (computer graphics); Digital image; Image processing; Computer graphics (images); Image (mathematics)","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001137428,0.000106231,0.0002283553,0.0001091345,0.0001901245,0.00007454809,0.0007387988,0.0000417177,0.000001639323],"category_scores_gemma":[0.0001688478,0.00006571715,0.00008221576,0.0001964961,0.0003010181,0.001038285,0.0001194019,0.0001851101,0.00000317442],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008371589,"about_ca_system_score_gemma":0.0001740075,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":6.300385e-7,"about_ca_topic_score_gemma":0.000004935554,"domain_scores_codex":[0.9986022,0.00003650626,0.0008092475,0.00006204932,0.0002592533,0.0002307846],"domain_scores_gemma":[0.9970336,0.0003865355,0.001515394,0.0003561936,0.0006599732,0.00004830921],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0006125512,0.000212989,0.2807924,0.0006000303,0.0003559128,0.0002906857,0.02236146,0.0008274631,0.006023431,0.004349972,0.09039175,0.5931814],"study_design_scores_gemma":[0.01209731,0.01521355,0.2239747,0.001490355,0.0006262235,0.03170482,0.009147483,0.0639626,0.3113515,0.05932956,0.2690062,0.002095704],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1356256,0.0003207121,0.8604073,0.002090712,0.0007222579,0.0001673297,0.00000756899,0.00001891086,0.0006396222],"genre_scores_gemma":[0.4096574,0.0003033441,0.5871933,0.002314786,0.000416796,0.00003510709,9.541134e-7,0.00001876291,0.00005960993],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5910857,"threshold_uncertainty_score":0.2679868,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007945628112338001,"score_gpt":0.252855381744325,"score_spread":0.244909753631987,"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."}}