{"id":"W4390189894","doi":"10.1109/iccvw60793.2023.00281","title":"ALFA – Leveraging All Levels of Feature Abstraction for Enhancing the Generalization of Histopathology Image Classification Across Unseen Hospitals","year":2023,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Brock University; University of Waterloo","funders":"","keywords":"Computer science; Generalizability theory; Abstraction; Feature extraction; Artificial intelligence; Pattern recognition (psychology); Encoder; Feature (linguistics); Contextual image classification; Robustness (evolution); Feature vector; Machine learning; Image (mathematics); Mathematics","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":[0.001971273,0.001275743,0.0009572703,0.001055478,0.000536349,0.0009709816,0.001844736,0.0009985024,0.00182023],"category_scores_gemma":[0.003743279,0.0004620948,0.001652441,0.0007458715,0.0009116986,0.001732783,0.001935396,0.001762597,0.001481703],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007132228,"about_ca_system_score_gemma":0.001367801,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006808944,"about_ca_topic_score_gemma":0.008379003,"domain_scores_codex":[0.9990702,0.0002201062,0.00004481637,0.0003201558,0.0002077992,0.0001369461],"domain_scores_gemma":[0.9983974,0.0004530727,0.0001243768,0.0006015168,0.0003300892,0.00009361647],"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":[0.0003728712,0.0003566819,0.007785106,0.0001777757,0.0002550822,0.0002933367,0.0003896536,0.2666634,0.03550785,0.007277491,0.01263629,0.6682844],"study_design_scores_gemma":[0.00001349546,0.0001404999,0.00152494,0.00001841631,0.00004032956,0.0001310926,0.00004061696,0.9776864,0.007912412,0.008741034,0.00372506,0.00002561098],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06049386,0.0007647972,0.9276099,0.0006605085,0.00009693308,0.0001671802,0.0005410676,0.006693564,0.002972236],"genre_scores_gemma":[0.6795917,0.0005605786,0.3087737,0.000764445,0.000194241,0.000310569,0.002329177,0.0004021204,0.007073437],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006808944,"threshold_uncertainty_score":0.0135386,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0491325197272561,"score_gpt":0.3289185942746244,"score_spread":0.2797860745473684,"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."}}