{"id":"W4378527617","doi":"10.32920/22734398","title":"A Novel Focal Tversky Loss Function with Improved Attention U-Net for Lesion Segmentation","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":40,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Segmentation; Dice; Pyramid (geometry); Function (biology); Image (mathematics); Artificial intelligence; Image segmentation; Computer science; Pattern recognition (psychology); Mathematics; Statistics; Geometry; Biology","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":[0.0004721633,0.0002612737,0.000376676,0.000193997,0.0001088089,0.00006769119,0.00008114034,0.000254384,0.00003628408],"category_scores_gemma":[0.0001376015,0.0001989939,0.0001758277,0.0001146455,0.00006567786,0.00006564194,0.0001237553,0.0006630031,0.00001946771],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001792679,"about_ca_system_score_gemma":0.0001612425,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003720775,"about_ca_topic_score_gemma":0.00003882965,"domain_scores_codex":[0.9984125,0.00002185654,0.0003438012,0.0005980457,0.0003482968,0.000275532],"domain_scores_gemma":[0.9990748,0.00008759207,0.0002201222,0.0002896629,0.0001804832,0.0001473638],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.009619847,0.001365443,0.02654008,0.008293996,0.002385055,0.00008182856,0.0006372038,0.006728115,0.6572406,0.001895538,0.02870804,0.2565043],"study_design_scores_gemma":[0.01553991,0.002395793,0.06468819,0.001928533,0.00197559,0.0001437201,0.000657462,0.9042438,0.001837112,0.001384719,0.004368674,0.0008364925],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1111569,0.00001833334,0.8812206,0.004347397,0.001093912,0.001544583,0.00001927833,0.0003239597,0.0002749477],"genre_scores_gemma":[0.75786,0.0001914868,0.2056131,0.002369082,0.0022912,0.0009915421,0.007426234,0.0003306406,0.02292673],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8975157,"threshold_uncertainty_score":0.8114735,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03454703525850763,"score_gpt":0.3225866770157166,"score_spread":0.288039641757209,"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."}}