{"id":"W2937085287","doi":"10.1016/j.neucom.2019.03.049","title":"Efficient multi-kernel DCNN with pixel dropout for stroke MRI segmentation","year":2019,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":46,"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":"Artificial intelligence; Computer science; Segmentation; Dropout (neural networks); Pattern recognition (psychology); Benchmark (surveying); Kernel (algebra); Image segmentation; Computer vision; Machine learning; Mathematics","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":[0.0007029216,0.0007157373,0.001013573,0.0007830283,0.0005084698,0.0008344766,0.001216006,0.001137037,0.001994062],"category_scores_gemma":[0.001068895,0.0004429825,0.0007087701,0.0008854767,0.0002395799,0.0008923112,0.0009276429,0.0008846115,0.000982313],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007782421,"about_ca_system_score_gemma":0.001815202,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0147535,"about_ca_topic_score_gemma":0.0228373,"domain_scores_codex":[0.9997428,0.00002991518,0.00002059398,0.0000659736,0.00008373492,0.0000568804],"domain_scores_gemma":[0.9996074,0.00007709426,0.00003165472,0.00006842266,0.0001869563,0.00002841229],"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":[0.0006607437,0.0002286649,0.002155191,0.0001811141,0.0001491204,0.0001249561,0.00008248068,0.09586874,0.03706777,0.002262097,0.006151075,0.8550681],"study_design_scores_gemma":[0.000007981626,0.00003324993,0.0007685037,0.000009017333,0.00002927389,0.00005932349,0.00001263169,0.9865498,0.01071306,0.0006425944,0.001165367,0.00000915613],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04935868,0.001429949,0.9442044,0.0002671886,0.0001322778,0.00008168523,0.0003061662,0.002594011,0.001625505],"genre_scores_gemma":[0.5118246,0.0008232538,0.4757872,0.0002597219,0.00009947814,0.0001259208,0.00133625,0.0003225429,0.009421085],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.0147535,"threshold_uncertainty_score":0.02933526,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01520935702106699,"score_gpt":0.2690721429839013,"score_spread":0.2538627859628343,"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."}}