{"id":"W4409180185","doi":"10.1007/978-981-96-3863-5_27","title":"Patch-Level Up-Sampling for Multi-instance Learning in H&E Tissue Micro-Array Based Recurrence Prediction","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in electrical engineering","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Sampling (signal processing); Computer science; Artificial intelligence; Pattern recognition (psychology); Biomedical engineering; Materials science; Engineering; Computer vision","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004072422,0.0005633344,0.0005874649,0.0009832586,0.0001071939,0.0001034617,0.0006943039,0.0007689213,0.000005777687],"category_scores_gemma":[0.001259545,0.0006579786,0.0001395141,0.0007736807,0.00002226759,0.0001945708,0.0000793907,0.002179284,0.000004516546],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001345354,"about_ca_system_score_gemma":0.0003053582,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004679016,"about_ca_topic_score_gemma":0.0002268104,"domain_scores_codex":[0.9971798,0.00003281031,0.0006585317,0.001091922,0.0003381833,0.0006987235],"domain_scores_gemma":[0.9979492,0.001145631,0.0002002995,0.0004893687,0.0001305742,0.00008494618],"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":[0.00004939358,0.00002555763,0.00009789361,0.0003997158,0.00002595553,0.000006814932,0.0002038649,0.6215872,0.0113023,0.001373282,0.00002482276,0.3649032],"study_design_scores_gemma":[0.0008536914,0.0001576021,0.0001019507,0.001458057,0.0000176789,0.000008150039,2.296372e-7,0.9494237,0.01699085,0.001601032,0.02867449,0.000712535],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00002691971,0.002657153,0.9942514,0.0001542712,0.001471812,0.0007614184,0.00001831203,0.0004329096,0.0002257869],"genre_scores_gemma":[0.06212213,0.0003357262,0.9323272,0.0002396917,0.0005451319,0.0003729064,0.00007997777,0.0001669447,0.003810371],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3641906,"threshold_uncertainty_score":0.9995871,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03468046123795165,"score_gpt":0.2705749142369719,"score_spread":0.2358944529990203,"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."}}