{"id":"W2895871797","doi":"10.32920/22734398.v1","title":"A Novel Focal Tversky Loss Function with Improved Attention U-Net for Lesion Segmentation","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":67,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Dice; Segmentation; 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000175718,0.0002867146,0.0002191565,0.0001420377,0.0002143518,0.0001798598,0.0005600581,0.0001916794,0.000003148699],"category_scores_gemma":[0.00001197229,0.0002510903,0.0001183343,0.0003800953,0.00004002585,0.0004159434,0.0006373587,0.0002718697,0.00003927793],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001690565,"about_ca_system_score_gemma":0.00008621342,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005007373,"about_ca_topic_score_gemma":0.0001381034,"domain_scores_codex":[0.9980091,0.00002171226,0.0003361114,0.001037068,0.0002825369,0.0003135004],"domain_scores_gemma":[0.9984563,0.0001357438,0.0003279962,0.0007759702,0.0002188421,0.00008515907],"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":[0.0009698733,0.0008834392,0.0006832367,0.0009415316,0.0004900318,0.00000812298,0.0004127521,0.1884942,0.343602,0.1457491,0.01202186,0.3057439],"study_design_scores_gemma":[0.001672375,0.0004593706,0.004291105,0.0001200098,0.00009073457,0.00001357001,0.00005277602,0.9613199,0.003833862,0.02638182,0.001104644,0.0006597945],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003282413,0.00000849429,0.9912757,0.001559307,0.0007692671,0.002129294,0.00002783388,0.0008798797,0.00006775541],"genre_scores_gemma":[0.1200403,0.00004902438,0.8719262,0.0003895783,0.0004182896,0.002952023,0.0008906028,0.00008329418,0.003250611],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7728258,"threshold_uncertainty_score":0.9999942,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05545238564034197,"score_gpt":0.3025661462564296,"score_spread":0.2471137606160876,"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."}}