{"id":"W3043892437","doi":"10.1016/j.bspc.2021.103475","title":"A computation-efficient CNN system for high-quality brain tumor segmentation","year":2022,"lang":"en","type":"article","venue":"Biomedical Signal Processing and Control","topic":"Brain Tumor Detection and Classification","field":"Neuroscience","cited_by":33,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada; Compute Canada","keywords":"Computer science; Convolutional neural network; Artificial intelligence; Normalization (sociology); Pattern recognition (psychology); Segmentation; Convolution (computer science); Block (permutation group theory); Computation; Feature (linguistics); Context (archaeology); Algorithm; Artificial neural network; Mathematics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003218339,0.0007321328,0.0005617635,0.0005512504,0.0003452109,0.0006868175,0.001190783,0.0007226377,0.005604849],"category_scores_gemma":[0.000620469,0.000379659,0.0004630134,0.0006136608,0.0001664814,0.0006190325,0.0008542235,0.0005715161,0.001917002],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006483961,"about_ca_system_score_gemma":0.001242857,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009885007,"about_ca_topic_score_gemma":0.01895781,"domain_scores_codex":[0.9998085,0.00001260856,0.000009778401,0.0000501715,0.00007741326,0.00004152641],"domain_scores_gemma":[0.9998067,0.00002942048,0.00001531137,0.00003630202,0.00009174442,0.00002051516],"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":[0.0003544958,0.0001411405,0.001396459,0.0001838982,0.0001587247,0.0002218806,0.00004182749,0.04612946,0.2086156,0.00253777,0.01661472,0.7236041],"study_design_scores_gemma":[0.00002221666,0.0001085054,0.001700534,0.00002073364,0.00006884905,0.0002466144,0.00001260022,0.9156038,0.0732598,0.00139884,0.007529988,0.00002765014],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04062707,0.0009407397,0.9443907,0.0003431666,0.000260717,0.0001726572,0.0007223792,0.007440533,0.005102024],"genre_scores_gemma":[0.4105745,0.0007581004,0.5707142,0.0005209255,0.0001677057,0.0001943959,0.002305431,0.0005457206,0.01421899],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009885007,"threshold_uncertainty_score":0.01965493,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02725551571580193,"score_gpt":0.2899320414438933,"score_spread":0.2626765257280914,"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."}}