{"id":"W4414156394","doi":"10.3390/biomedinformatics5030053","title":"High-Precision, Automatic, and Fast Segmentation Method of Hepatic Vessels and Liver Tumors from CT Images Using a Fusion Decision-Based Stacking Deep Learning Model","year":2025,"lang":"en","type":"article","venue":"BioMedInformatics","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec en Outaouais","funders":"","keywords":"Deep learning; Segmentation; Robustness (evolution); Stacking; Liver tumor; Flexibility (engineering); Image segmentation; Pattern recognition (psychology)","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":[],"consensus_categories":[],"category_scores_codex":[0.0006348017,0.0001756066,0.0002932979,0.0004834913,0.0002240367,0.0001997312,0.0002636318,0.00005773951,0.000005660453],"category_scores_gemma":[0.000214208,0.0001611436,0.00003401871,0.0006001136,0.0000746929,0.0009966027,0.0003225971,0.0001282563,0.00000119378],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00013906,"about_ca_system_score_gemma":0.0001132919,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001318576,"about_ca_topic_score_gemma":0.000005855558,"domain_scores_codex":[0.9984311,0.00008065076,0.0006454184,0.0002250307,0.0004364246,0.0001813407],"domain_scores_gemma":[0.9981489,0.0009309687,0.0004201064,0.0002789414,0.0001508183,0.00007023467],"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":[0.00001516352,0.00001978602,0.0005472851,0.0002789386,0.00002582893,0.000002205172,0.003446992,0.04962363,0.01035937,0.0001222726,0.00002286783,0.9355357],"study_design_scores_gemma":[0.0005760563,0.00005718711,0.001389422,0.0005123129,0.0000379915,0.000005223724,0.0004063746,0.9628577,0.03130079,0.002707454,0.000007656382,0.0001418697],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3456503,0.000115856,0.6538139,0.00002400081,0.0001463478,0.0001690487,0.000006296326,0.00006210205,0.00001219129],"genre_scores_gemma":[0.4022922,0.00005475659,0.5975766,0.00004826187,0.000008302948,0.000005613017,0.000005127693,0.000005580184,0.000003548429],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9353938,"threshold_uncertainty_score":0.6571246,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0133035424696099,"score_gpt":0.2859272044504051,"score_spread":0.2726236619807952,"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."}}