{"id":"W4387414818","doi":"10.1007/978-3-031-44336-7_8","title":"How Inter-rater Variability Relates to Aleatoric and Epistemic Uncertainty: A Case Study with Deep Learning-Based Paraspinal Muscle Segmentation","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"Western University; Concordia University","funders":"","keywords":"Computer science; Segmentation; Artificial intelligence; Machine learning; Deep learning; Ground truth; Transformer; Uncertainty quantification","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":[0.005456112,0.0004956278,0.0004434289,0.0006179921,0.0004962062,0.002582737,0.0009477133,0.001257217,0.001096614],"category_scores_gemma":[0.03027481,0.0002944211,0.0004843876,0.0008574292,0.0009131469,0.001649881,0.001179545,0.001187716,0.0003504007],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000777666,"about_ca_system_score_gemma":0.0005310493,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003598333,"about_ca_topic_score_gemma":0.005022572,"domain_scores_codex":[0.9974406,0.001076804,0.0001630979,0.0006194504,0.0005407473,0.0001593012],"domain_scores_gemma":[0.9740689,0.02206269,0.001390087,0.0009783872,0.001279247,0.0002207046],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.002597949,0.0004599762,0.2062587,0.0006611648,0.0008559641,0.005794166,0.01296827,0.1151897,0.0508091,0.009648119,0.006578743,0.5881781],"study_design_scores_gemma":[0.00007224439,0.0009085268,0.2002164,0.0003652123,0.0006723332,0.00816016,0.007663382,0.6846032,0.04277141,0.04477008,0.009466715,0.0003304233],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8657481,0.001509325,0.1224117,0.001001898,0.0001200199,0.00008623719,0.0005617871,0.000373113,0.00818776],"genre_scores_gemma":[0.9875448,0.0001567676,0.01101772,0.00005992069,0.00003021957,0.00001841421,0.0001851915,0.00009888829,0.0008879903],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005456112,"threshold_uncertainty_score":0.02885497,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06319000894847941,"score_gpt":0.3493490479373006,"score_spread":0.2861590389888212,"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."}}