{"id":"W3095903828","doi":"10.48550/arxiv.2010.15865","title":"Ink Marker Segmentation in Histopathology Images Using Deep Learning","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Histopathology; Digital pathology; Pixel; Artificial intelligence; Computer science; Segmentation; Image segmentation; Computer vision; Pattern recognition (psychology); Process (computing); Digital image; Image processing; Pathology; Image (mathematics); 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006071557,0.00096144,0.0005701662,0.001973263,0.0003250194,0.001075942,0.001060064,0.001213505,0.001356003],"category_scores_gemma":[0.00108053,0.0004419652,0.000912266,0.001053968,0.0003910806,0.0009030763,0.0007665973,0.000838503,0.001031211],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001032535,"about_ca_system_score_gemma":0.0007915602,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00772169,"about_ca_topic_score_gemma":0.01113209,"domain_scores_codex":[0.9996905,0.00003679332,0.00001810653,0.0001074978,0.00007681811,0.0000702386],"domain_scores_gemma":[0.9996995,0.00007195758,0.00004571948,0.00005739662,0.0001014188,0.00002397272],"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":[0.0006026347,0.0002567436,0.008034441,0.0002813035,0.0001747733,0.0005211416,0.0001784146,0.2077203,0.07022429,0.001977992,0.007880036,0.7021478],"study_design_scores_gemma":[0.00001085758,0.00008205202,0.001802163,0.00003183306,0.00003670073,0.0001492506,0.00004364634,0.9647011,0.02851742,0.00219457,0.002416968,0.00001352498],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2332403,0.002321999,0.7478328,0.0007262541,0.0002366459,0.0002603763,0.001268783,0.009800711,0.004312103],"genre_scores_gemma":[0.6695002,0.001238446,0.316785,0.000434592,0.00009669722,0.0001265033,0.003972918,0.0003268743,0.007518782],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00772169,"threshold_uncertainty_score":0.0153535,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.073377194391096,"score_gpt":0.2061099996445978,"score_spread":0.1327328052535018,"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."}}