{"id":"W4406213437","doi":"10.1016/j.cageo.2025.105853","title":"Addressing class imbalance in micro-CT image segmentation: A modified U-Net model with pixel-level class weighting","year":2025,"lang":"en","type":"article","venue":"Computers & Geosciences","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Class (philosophy); Weighting; Pixel; Segmentation; Artificial intelligence; Image (mathematics); Computer science; Net (polyhedron); Image segmentation; Pattern recognition (psychology); Computer vision; Mathematics; Medicine; Radiology","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":[0.003364877,0.0008123918,0.001745561,0.00105182,0.0006913936,0.001589311,0.003618345,0.002822868,0.001722861],"category_scores_gemma":[0.00469442,0.0006271545,0.001123899,0.001217137,0.0007342163,0.002264495,0.001453124,0.001555525,0.0004079933],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001366566,"about_ca_system_score_gemma":0.001369971,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01445488,"about_ca_topic_score_gemma":0.01252194,"domain_scores_codex":[0.9992852,0.0001593392,0.00004812763,0.0002273346,0.0001752922,0.0001047233],"domain_scores_gemma":[0.9984227,0.0007359196,0.0001473261,0.0001310722,0.0004815801,0.00008138899],"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":[0.0003639094,0.0002081904,0.002880944,0.00009167563,0.0001142752,0.00009850445,0.00009252383,0.785448,0.003003613,0.008285151,0.001978495,0.1974348],"study_design_scores_gemma":[0.00000225958,0.000009496254,0.000106772,0.000002980831,0.000008318498,0.000006673865,0.000003137493,0.9983804,0.0002530667,0.00110608,0.0001187068,0.00000218214],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04351971,0.0005529728,0.9534977,0.0004173101,0.0001366005,0.0001011462,0.0001413189,0.0004484686,0.001184724],"genre_scores_gemma":[0.7730953,0.000451321,0.217382,0.0004562756,0.0002530266,0.0002861062,0.0004345775,0.0002261265,0.007415204],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01445488,"threshold_uncertainty_score":0.02874148,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04641570247423604,"score_gpt":0.3167057665127214,"score_spread":0.2702900640384853,"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."}}