{"id":"W7132932319","doi":"","title":"Benchmarking the Robustness of Deep Learning Segmentation Models to Out-of-distribution and Corrupted Data in MR Neuroimaging","year":2022,"lang":"","type":"dissertation","venue":"TSpace","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Benchmarking; Robustness (evolution); Segmentation; Deep learning; Artificial neural network; Deep neural networks; Neuroimaging","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":[0.01171092,0.001719356,0.0006894085,0.001449067,0.0005068994,0.001735699,0.001964696,0.001852843,0.0009611744],"category_scores_gemma":[0.03592934,0.0006225316,0.001078561,0.001281692,0.001593141,0.00175982,0.002263115,0.001915925,0.0005871044],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001726494,"about_ca_system_score_gemma":0.001432943,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008285515,"about_ca_topic_score_gemma":0.008287992,"domain_scores_codex":[0.9965155,0.001575669,0.0002810373,0.0007082666,0.0007263433,0.0001931013],"domain_scores_gemma":[0.9899921,0.005822716,0.0007537252,0.001988762,0.001182125,0.0002604311],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004337979,0.0001698798,0.007371629,0.0002713103,0.0003807862,0.0001201778,0.0001376419,0.8869303,0.008796404,0.002468215,0.003248838,0.08967102],"study_design_scores_gemma":[0.00001986126,0.0001575376,0.002965612,0.00005070077,0.00004013374,0.0000611016,0.00004538295,0.9772151,0.01321914,0.005226675,0.0009739004,0.00002477969],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5403337,0.003160991,0.440612,0.001826413,0.000404479,0.0003237379,0.002243262,0.006727415,0.004367955],"genre_scores_gemma":[0.8497571,0.0009760734,0.1402572,0.000426836,0.00009381871,0.0002205532,0.005834575,0.001031948,0.00140185],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01171092,"threshold_uncertainty_score":0.06193393,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08697933090142528,"score_gpt":0.3561543094428477,"score_spread":0.2691749785414224,"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."}}