{"id":"W7126080695","doi":"10.1109/bibm66473.2025.11356986","title":"Active Learning for Lesion Segmentation Using Contrastive Learning with Strong Augmentation","year":2025,"lang":"","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"National Key Research and Development Program of China; Natural Science Foundation of Beijing Municipality; National Natural Science Foundation of China","keywords":"Segmentation; Active learning (machine learning); Pattern recognition (psychology); Annotation; Selection (genetic algorithm); Image segmentation; Sampling (signal processing)","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":[0.001737517,0.001157473,0.001143291,0.0009635005,0.0004164663,0.001208926,0.00282733,0.00170477,0.001296972],"category_scores_gemma":[0.003810501,0.0007675205,0.001218189,0.0005833972,0.00134299,0.001637545,0.001748316,0.00219989,0.0004997998],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009302683,"about_ca_system_score_gemma":0.000902169,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002418316,"about_ca_topic_score_gemma":0.004351136,"domain_scores_codex":[0.999446,0.0001503174,0.0000229981,0.0001744084,0.0001425584,0.00006365175],"domain_scores_gemma":[0.9985288,0.0008400199,0.0001366786,0.0001978171,0.000216542,0.00008011628],"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":[0.0003287083,0.0002910058,0.001854783,0.0001702961,0.0001362035,0.0001798003,0.0002078265,0.6062087,0.03197971,0.009768086,0.002557778,0.3463171],"study_design_scores_gemma":[0.000004774671,0.0000281709,0.00008012776,0.000003746668,0.000005630231,0.00002157261,0.000004168949,0.9947386,0.003140962,0.00172948,0.0002383374,0.000004382922],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01688227,0.000207097,0.9810966,0.000167528,0.00002407616,0.00005295354,0.00003562593,0.000885531,0.0006483418],"genre_scores_gemma":[0.6412098,0.0003265238,0.3535633,0.0005265293,0.00009910039,0.0002683871,0.0003436631,0.0002689013,0.003393779],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00282733,"threshold_uncertainty_score":0.00918901,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0337395359083766,"score_gpt":0.3297916385378132,"score_spread":0.2960521026294367,"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."}}