{"id":"W6963501043","doi":"10.21227/4gqq-er08","title":"Automatic Segmentation of Stroke Lesions in Non-contrast Computed Tomography Datasets with Convolutional Neural Networks","year":2020,"lang":"en","type":"dataset","venue":"IEEE DataPort","topic":"Tree-ring climate responses","field":"Earth and Planetary Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Convolutional neural network; Segmentation; Pattern recognition (psychology); Lesion; Sørensen–Dice coefficient; Artificial neural network; Similarity (geometry); Stroke (engine)","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":[0.0002560873,0.0003566552,0.0005770681,0.0003688653,0.00009165615,0.00006595337,0.0006510373,0.000170552,0.0004547017],"category_scores_gemma":[0.00002898061,0.0003055111,0.00007132584,0.0005679352,0.0002092173,0.0003382576,0.00004134909,0.0004578188,0.00008827932],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001044803,"about_ca_system_score_gemma":0.0001677975,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00390697,"about_ca_topic_score_gemma":0.01408227,"domain_scores_codex":[0.997688,0.000148529,0.0006497266,0.000537876,0.0005714032,0.0004044483],"domain_scores_gemma":[0.9983528,0.0003918216,0.0004515982,0.000576853,0.00003599329,0.0001909011],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.0001912735,0.00006347133,0.03814332,0.0001875072,0.00009647139,0.0002637348,0.000009021451,0.01691051,0.000007655126,1.412816e-7,0.942138,0.001988932],"study_design_scores_gemma":[0.001206871,0.0003813818,0.725643,0.0003304285,0.0002068919,0.00009965827,0.00005238195,0.2368902,0.00001721179,0.000001106866,0.03463301,0.0005378328],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.02038834,0.0001004508,0.0002575016,0.00002764767,0.0004170827,0.0004777732,0.9782748,0.00005138612,0.000005043029],"genre_scores_gemma":[0.07172079,0.00005071051,0.0006050068,0.0001176386,0.0001074877,0.000005575404,0.9273841,0.000007464264,0.000001180877],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.907505,"threshold_uncertainty_score":0.9999397,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01733727751603585,"score_gpt":0.244742462559307,"score_spread":0.2274051850432711,"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."}}