{"id":"W3100049547","doi":"10.1038/s41598-020-76459-7","title":"A fast and fully-automated deep-learning approach for accurate hemorrhage segmentation and volume quantification in non-contrast whole-head CT","year":2020,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Acute Ischemic Stroke Management","field":"Medicine","cited_by":78,"is_retracted":false,"has_abstract":true,"ca_institutions":"Fraser Health; Royal Columbian Hospital; Surrey Memorial Hospital; Simon Fraser University","funders":"Surrey Hospitals Foundation; SFU Community Trust Endowment Fund; Tianjin Medical University; Simon Fraser University","keywords":"Convolutional neural network; Computer science; Artificial intelligence; Voxel; Segmentation; Deep learning; Sørensen–Dice coefficient; Pattern recognition (psychology); Contrast (vision); Kappa; Projection (relational algebra); Nuclear medicine; Medicine; Image segmentation; Mathematics; Algorithm","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":[0.0008930334,0.0001686437,0.0002871073,0.000162602,0.0001719637,0.0002245903,0.00005120959,0.00004548107,0.00001081635],"category_scores_gemma":[0.0002665141,0.0001622105,0.00004109228,0.000434061,0.0001373231,0.0002209891,0.00007367925,0.0001433368,0.000005853251],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005485662,"about_ca_system_score_gemma":0.00003762339,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001828922,"about_ca_topic_score_gemma":0.000005309046,"domain_scores_codex":[0.9979746,0.00003181061,0.0005316555,0.0008821819,0.0003020721,0.000277686],"domain_scores_gemma":[0.9991186,0.00002417139,0.0003175282,0.000274793,0.0001019575,0.0001628942],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000276216,0.0002480425,0.09474181,0.001811745,0.0001123022,0.0008524558,0.005174539,0.001992831,0.7675629,0.000008838205,0.02095076,0.1062676],"study_design_scores_gemma":[0.001384709,0.0001054775,0.02162191,0.00005954422,0.0001156952,0.0003736881,0.002377669,0.9587984,0.0111564,0.000009358486,0.003791502,0.0002056601],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9288515,0.0001581129,0.0668699,0.0010013,0.0003603256,0.001765686,0.00000490319,0.0001842108,0.0008040468],"genre_scores_gemma":[0.9814212,0.000004292965,0.01607181,0.0001056278,0.00004975359,0.0001320832,0.0006416313,0.00002377219,0.001549877],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9568055,"threshold_uncertainty_score":0.6614754,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01998333067825826,"score_gpt":0.274743765957692,"score_spread":0.2547604352794338,"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."}}