{"id":"W6926033487","doi":"10.21227/jps9-0b57","title":"Pretrained CNN model for segmenting non-contrast computed tomography stroke lesion datasets","year":2020,"lang":"en","type":"dataset","venue":"IEEE DataPort","topic":"Quasicrystal Structures and Properties","field":"Materials Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Convolutional neural network; Segmentation; Lesion; Pattern recognition (psychology); Sørensen–Dice coefficient; Similarity (geometry); Stroke (engine); Artificial neural network","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":[0.0004787619,0.0006186232,0.0008077134,0.0001417517,0.000367064,0.0003970836,0.001492949,0.0003578266,0.0002135862],"category_scores_gemma":[0.00006325774,0.0005236206,0.0002192786,0.000164607,0.0001493927,0.0004327702,0.0004200582,0.0003857116,0.000121536],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003898148,"about_ca_system_score_gemma":0.0001890636,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002616922,"about_ca_topic_score_gemma":0.0001227254,"domain_scores_codex":[0.9966881,0.0000562932,0.0007929621,0.001147681,0.0006127844,0.0007021468],"domain_scores_gemma":[0.9978207,0.0000759071,0.0005325486,0.001212726,0.00009235965,0.0002657414],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001963016,0.0000459907,0.000002079386,0.0006666832,0.00005845441,0.00002750693,0.000035297,0.0004073966,0.08524156,0.000001641178,0.9130453,0.0002718059],"study_design_scores_gemma":[0.0008901111,0.0001970655,0.000013503,0.0002130542,0.0002580132,0.00001652574,0.00001996668,0.02638477,0.02093697,0.00005444857,0.9501939,0.0008216069],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.0007903399,0.00008960922,0.01521867,0.00004565853,0.001394576,0.001123794,0.9812258,0.0001021447,0.000009432775],"genre_scores_gemma":[0.002679492,0.00003276322,0.004676618,0.0006057668,0.0007312532,0.00009477099,0.991082,0.00005202375,0.00004535098],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.06430459,"threshold_uncertainty_score":0.9997215,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03551933986921761,"score_gpt":0.269529872778586,"score_spread":0.2340105329093684,"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."}}