{"id":"W2913720416","doi":"10.1007/978-3-030-11726-9_23","title":"3D U-Net for Brain Tumour Segmentation","year":2019,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":60,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Segmentation; Artificial intelligence; Cross entropy; Dice; Convolutional neural network; Categorical variable; Artificial neural network; Pattern recognition (psychology); Metric (unit); Network architecture; Machine learning; Statistics","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":[0.0004363691,0.001290624,0.0008036516,0.001481857,0.0004492801,0.001831935,0.001380096,0.001769333,0.01247824],"category_scores_gemma":[0.0007323659,0.0008150789,0.001092777,0.001257055,0.0003029835,0.0008455677,0.001277816,0.0007165631,0.005267987],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006318339,"about_ca_system_score_gemma":0.0008625728,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004399856,"about_ca_topic_score_gemma":0.007896301,"domain_scores_codex":[0.999788,0.00003003081,0.00001312297,0.00005015655,0.00008949553,0.00002928065],"domain_scores_gemma":[0.9998197,0.00006680972,0.0000147154,0.00003579895,0.00004794405,0.00001512753],"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":[0.0003664109,0.00006527924,0.0007217994,0.0003944474,0.0001042214,0.0003409892,0.00008929415,0.07952537,0.02313827,0.008065998,0.03330987,0.853878],"study_design_scores_gemma":[0.00001843306,0.00007610586,0.0006483339,0.00009490462,0.00005359002,0.0007239893,0.00003881269,0.9324598,0.03004598,0.0082166,0.02758134,0.0000421935],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.009722019,0.002381862,0.9652588,0.000320015,0.0002570643,0.0001509627,0.001631202,0.01162998,0.00864804],"genre_scores_gemma":[0.1071371,0.002374518,0.8660705,0.0004796976,0.0001735884,0.0002876131,0.002842983,0.002141864,0.01849218],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01247824,"threshold_uncertainty_score":0.04174387,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01909323443072166,"score_gpt":0.2755283187651785,"score_spread":0.2564350843344568,"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."}}