{"id":"W4205466533","doi":"10.18280/ts.380616","title":"Early Detection of Hemorrhagic Stroke Using a Lightweight Deep Learning Neural Network Model","year":2021,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Brain Tumor Detection and Classification","field":"Neuroscience","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Ministry of Science and ICT, South Korea; National Research Foundation of Korea; National Research Foundation","keywords":"Sørensen–Dice coefficient; Random forest; Computer science; Artificial intelligence; Stroke (engine); Segmentation; Convolutional neural network; Deep learning; Artificial neural network; Convolution (computer science); Pattern recognition (psychology); Image segmentation; Machine learning; Engineering","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003763317,0.0007442237,0.000672324,0.0005907194,0.0002644117,0.0005398541,0.000912382,0.0007260007,0.00133732],"category_scores_gemma":[0.0007961277,0.0002798866,0.000569398,0.0004161599,0.0002034119,0.0007138542,0.0004989844,0.0007570834,0.0004014554],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006703704,"about_ca_system_score_gemma":0.0009201856,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009625362,"about_ca_topic_score_gemma":0.01207723,"domain_scores_codex":[0.9998147,0.00002272737,0.00001198116,0.00005217879,0.00004811388,0.00005019737],"domain_scores_gemma":[0.9998216,0.0000516633,0.00002319075,0.00001751864,0.00007205166,0.00001393672],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005454368,0.0003494885,0.008182244,0.0001150726,0.0001786894,0.0003460749,0.00005703177,0.5103932,0.01860304,0.002538633,0.006121278,0.4525698],"study_design_scores_gemma":[0.000005084104,0.00003423084,0.0005217532,0.000005717651,0.00001271364,0.0000390811,0.00000408354,0.9966605,0.00181437,0.0006304168,0.0002675846,0.000004474178],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1966399,0.001725746,0.7924643,0.0007389879,0.0001935504,0.0001185055,0.0005396681,0.002734327,0.004844996],"genre_scores_gemma":[0.9146451,0.0006257161,0.07656594,0.000258315,0.00007312679,0.00009533759,0.000867345,0.00005633739,0.006812808],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009625362,"threshold_uncertainty_score":0.01913869,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03844452189882566,"score_gpt":0.2465693932948275,"score_spread":0.2081248713960019,"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."}}