{"id":"W2594785967","doi":"10.1117/1.jmi.4.2.021104","title":"Differentiation of arterioles from venules in mouse histology images using machine learning","year":2017,"lang":"en","type":"article","venue":"Journal of Medical Imaging","topic":"Digital Imaging for Blood Diseases","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"Canadian Institutes of Health Research; Cancer Care Ontario; London Health Sciences Centre; Natural Sciences and Engineering Research Council of Canada; Heart and Stroke Foundation of Canada","keywords":"Medicine; Generalizability theory; Artificial intelligence; Digital pathology; Feature selection; Pattern recognition (psychology); Receiver operating characteristic; Segmentation; Feature (linguistics); Computer science; Pathology; Biomedical engineering; Machine learning","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004349012,0.00009880359,0.0003002842,0.000196348,0.00007761042,0.0002431527,0.001180231,0.00003274747,0.00001505477],"category_scores_gemma":[0.001382058,0.00008642177,0.000095797,0.00004415858,0.0001935123,0.001039538,0.0003303001,0.000304441,0.000001483724],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000453874,"about_ca_system_score_gemma":0.0001154125,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003153937,"about_ca_topic_score_gemma":0.00001425215,"domain_scores_codex":[0.9984977,0.00009025515,0.0004801857,0.0001390788,0.00061844,0.0001743049],"domain_scores_gemma":[0.9985592,0.0001178224,0.0008252292,0.0002641379,0.00009160643,0.0001419501],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003178828,0.0003922689,0.7162657,0.00004886564,0.00006228046,0.0008370984,0.0005625467,0.0001123338,0.03900541,0.0006078735,0.0001178139,0.241956],"study_design_scores_gemma":[0.003002151,0.00005363472,0.2531886,0.001264637,0.00006864031,0.0003574083,0.0001119507,0.7119299,0.02146232,0.007747886,0.0004840796,0.0003288219],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9061844,0.002241166,0.08885088,0.002186963,0.0004219092,0.00002405466,0.000004775013,0.00001227428,0.00007355813],"genre_scores_gemma":[0.9930831,0.00006295399,0.0066672,0.00007265014,0.0000962078,2.77399e-7,0.000001311241,0.000008192597,0.000008169203],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7118175,"threshold_uncertainty_score":0.3524177,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01691633445342543,"score_gpt":0.2899682432812705,"score_spread":0.273051908827845,"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."}}