{"id":"W4397043685","doi":"10.1016/j.radonc.2024.110332","title":"Generalizability of deep learning in organ-at-risk segmentation: A transfer learning study in cervical brachytherapy","year":2024,"lang":"en","type":"article","venue":"Radiotherapy and Oncology","topic":"Advanced Radiotherapy Techniques","field":"Physics and Astronomy","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"Princess Margaret Cancer Centre; Ontario Institute for Cancer Research; University of Toronto","funders":"Canadian Institutes of Health Research","keywords":"Generalizability theory; Transfer of learning; Brachytherapy; Segmentation; Medicine; Artificial intelligence; Computer science; Radiology; Psychology; Radiation therapy; Developmental psychology","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":[0.004393183,0.001170601,0.0005629846,0.0005585058,0.0003216389,0.0006709289,0.00108311,0.001402643,0.0009385484],"category_scores_gemma":[0.01388293,0.0003331901,0.0009037916,0.0004350724,0.0008661291,0.001168275,0.001241643,0.001434594,0.0003122486],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001234288,"about_ca_system_score_gemma":0.0006742027,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007394876,"about_ca_topic_score_gemma":0.003362053,"domain_scores_codex":[0.9991166,0.0003649768,0.00005327746,0.000266368,0.0001214963,0.00007738043],"domain_scores_gemma":[0.9954131,0.002885666,0.0002937457,0.0005995368,0.0006436913,0.0001642068],"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":[0.002199822,0.001138642,0.03190354,0.0003839236,0.0005258851,0.0002969179,0.0003716264,0.7015006,0.01756824,0.0005091119,0.001369391,0.2422322],"study_design_scores_gemma":[0.00005730342,0.001724647,0.01082769,0.00004620651,0.0001220204,0.0001216044,0.0001203431,0.9730543,0.01217884,0.001197102,0.0005181005,0.00003188239],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9573659,0.001113692,0.03848529,0.0004237802,0.00006640668,0.0001640221,0.0001509184,0.0006646734,0.001565354],"genre_scores_gemma":[0.9930909,0.0001509315,0.005777376,0.00009093144,0.00001533327,0.00004170648,0.0001917099,0.00005853265,0.0005824157],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.007394876,"threshold_uncertainty_score":0.02323371,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01014802531871278,"score_gpt":0.3168720454236572,"score_spread":0.3067240201049444,"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."}}