{"id":"W4392927829","doi":"10.32920/25412656","title":"Domain Generalization Across Multi-centre Digital Pathology Images for Lymph Node Segmentation and Classification","year":2024,"lang":"en","type":"preprint","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Deep learning; Digital pathology; Computer science; Artificial intelligence; Transfer of learning; Workflow; Generalization; Segmentation; Machine learning; Domain (mathematical analysis); Medical diagnosis; Task (project management); Pattern recognition (psychology); Medicine; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002339106,0.0008406482,0.0007325575,0.002197413,0.0006033205,0.001390441,0.001103686,0.001394235,0.002104424],"category_scores_gemma":[0.004957228,0.0003476761,0.001622473,0.001354876,0.0005536967,0.0009067057,0.001337365,0.001352394,0.001765191],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001143745,"about_ca_system_score_gemma":0.001509194,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00890264,"about_ca_topic_score_gemma":0.009878068,"domain_scores_codex":[0.9986659,0.0001868107,0.00006574103,0.0005803831,0.000317286,0.0001838941],"domain_scores_gemma":[0.9981407,0.0004227286,0.000211439,0.0005315925,0.0005678721,0.0001255583],"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":[0.001504248,0.0006308173,0.03326401,0.0006019757,0.000494189,0.0007030538,0.0006006734,0.1636961,0.05188432,0.002703612,0.02712477,0.7167922],"study_design_scores_gemma":[0.00007520398,0.0002594877,0.04080526,0.0001400017,0.0002160619,0.001227272,0.0005262236,0.8944708,0.040134,0.007914586,0.01413223,0.00009881794],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.5741733,0.003901952,0.3946363,0.002330738,0.0006358164,0.0004903636,0.005134956,0.008998768,0.009697909],"genre_scores_gemma":[0.8701981,0.001212476,0.1153426,0.0003992777,0.0002040565,0.0001288738,0.008662456,0.0002873238,0.00356489],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.00890264,"threshold_uncertainty_score":0.01770163,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02986715034609315,"score_gpt":0.313594560318499,"score_spread":0.2837274099724059,"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."}}