{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007716549,0.0001067077,0.0001634189,0.00008924131,0.0009588773,0.0001003564,0.0001028624,0.00002760274,0.00003921308],"category_scores_gemma":[0.0001626261,0.00009676863,0.00004044429,0.0003019924,0.0001437126,0.00005218371,0.00002511686,0.0001282819,0.000004090945],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001250707,"about_ca_system_score_gemma":0.0000999129,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001539356,"about_ca_topic_score_gemma":3.270031e-7,"domain_scores_codex":[0.9982443,0.0003167609,0.0003396561,0.0003953342,0.0004999883,0.0002039995],"domain_scores_gemma":[0.9990529,0.0004924611,0.0002282775,0.00005623666,0.0000459616,0.0001241052],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004341849,0.0002302489,0.00001532692,0.0002238231,0.000005794426,0.000005827484,0.000287079,0.0004478205,0.822334,0.002650453,0.000254086,0.1731113],"study_design_scores_gemma":[0.009120652,0.001056691,0.001437067,0.00006187773,0.00005586804,0.0001394418,0.003773351,0.9381995,0.04062321,0.001011949,0.004046013,0.0004744085],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2834153,0.00008384187,0.7096604,0.005264741,0.0003296589,0.0007722502,0.0001175814,0.0002681576,0.00008817147],"genre_scores_gemma":[0.9970747,1.583969e-7,0.0001736616,0.002095297,0.0001138973,0.0004307021,0.00001958893,0.00001192343,0.00008010414],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9377517,"threshold_uncertainty_score":0.7375005,"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."}}