{"id":"W2963356165","doi":"10.1109/icassp.2019.8683759","title":"Capsule Networks for Brain Tumor Classification Based on MRI Images and Coarse Tumor Boundaries","year":2019,"lang":"en","type":"article","venue":"","topic":"Brain Tumor Detection and Classification","field":"Neuroscience","cited_by":371,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; Concordia University","funders":"","keywords":"Computer science; Convolutional neural network; Artificial intelligence; Brain tumor; Pipeline (software); Process (computing); Feature extraction; Pattern recognition (psychology); Deep learning; Contextual image classification; Focus (optics); Image (mathematics); Pathology","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003421505,0.0001730907,0.0001629634,0.0001093035,0.0003972443,0.0004093928,0.0001530752,0.00004855567,0.000298479],"category_scores_gemma":[0.0005302679,0.0001536616,0.00006006499,0.0002278855,0.0002751024,0.000214267,0.00001952898,0.0001496577,0.0001071543],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005585106,"about_ca_system_score_gemma":0.00008755108,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009847057,"about_ca_topic_score_gemma":0.000007482592,"domain_scores_codex":[0.998553,0.0001236162,0.0002426503,0.0005972909,0.0002086933,0.0002747135],"domain_scores_gemma":[0.9988001,0.00050507,0.000152123,0.0003865317,0.00005809412,0.00009809172],"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":[0.0003898595,0.0002242749,0.0003688854,0.00008556697,0.000004246679,0.00000557319,0.00009554108,0.0007863213,0.8882841,0.06405108,0.03925814,0.006446363],"study_design_scores_gemma":[0.001185959,0.0003139946,0.006129663,0.00001955441,0.000008099837,0.0000208582,0.0001903195,0.7500179,0.1916224,0.000509117,0.04970962,0.0002725344],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6322154,0.00007460897,0.2627954,0.04726555,0.00362798,0.00588009,0.0001663022,0.001466362,0.04650825],"genre_scores_gemma":[0.9828833,0.000002011148,0.0006984688,0.01152393,0.00007959852,0.0001477459,0.00001217725,0.00002991047,0.004622903],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7492316,"threshold_uncertainty_score":0.6266139,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02508829657823564,"score_gpt":0.2634344644609843,"score_spread":0.2383461678827486,"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."}}