{"id":"W2915335211","doi":"10.1007/s00521-019-04096-x","title":"Deep convolutional neural network for automatically segmenting acute ischemic stroke lesion in multi-modality MRI","year":2019,"lang":"en","type":"article","venue":"Neural Computing and Applications","topic":"Acute Ischemic Stroke Management","field":"Medicine","cited_by":105,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Saskatchewan","funders":"Hunan Provincial Science and Technology Department; National Natural Science Foundation of China","keywords":"Convolutional neural network; Modality (human–computer interaction); Artificial intelligence; Computer science; Segmentation; Sørensen–Dice coefficient; Pattern recognition (psychology); Deep learning; Stroke (engine); Artificial neural network; Magnetic resonance imaging; Image segmentation; Medicine; Radiology","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":[0.0004412879,0.0008827165,0.0005381895,0.001280824,0.0002641248,0.0006052675,0.0006706489,0.0008301645,0.001084102],"category_scores_gemma":[0.0008390477,0.0003772694,0.0006022861,0.0006629296,0.0001675251,0.0005164716,0.0005718711,0.000645789,0.0004703238],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004920334,"about_ca_system_score_gemma":0.0009140052,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01854406,"about_ca_topic_score_gemma":0.03063016,"domain_scores_codex":[0.9998705,0.00001506554,0.00001032239,0.00003834823,0.00002625347,0.00003948329],"domain_scores_gemma":[0.9998336,0.00005887568,0.00002206672,0.00001508558,0.00005260718,0.00001787121],"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":[0.001012385,0.0005203784,0.01705351,0.0003535201,0.0003647699,0.0008680492,0.0001393254,0.09319703,0.06440949,0.001773775,0.01517681,0.805131],"study_design_scores_gemma":[0.00001909286,0.00009704581,0.007431039,0.00004176078,0.0001543717,0.0003021586,0.00003487657,0.9703066,0.0176581,0.001769175,0.002160948,0.00002484483],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3500775,0.00808716,0.6273715,0.0009643724,0.0003710159,0.0002513905,0.003694329,0.004052892,0.005129826],"genre_scores_gemma":[0.8594152,0.002487415,0.1273449,0.0003387932,0.0001673591,0.0001171031,0.003206583,0.0001456016,0.006777047],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01854406,"threshold_uncertainty_score":0.03687221,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02189602168874222,"score_gpt":0.3055555412347409,"score_spread":0.2836595195459987,"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."}}