{"id":"W4413148282","doi":"10.18280/ts.420403","title":"Addressing Boundary Ambiguity in Renal Tumor Segmentation: A Softmax-Refined Deep Learning Approach","year":2025,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Chengdu Science and Technology Program; Sichuan Province Science and Technology Support Program","keywords":"Softmax function; Ambiguity; Artificial intelligence; Segmentation; Deep learning; Computer science; Boundary (topology); Pattern recognition (psychology); Mathematics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001360168,0.001388872,0.001263296,0.0009857932,0.0004338151,0.00110174,0.002202406,0.002353188,0.001863102],"category_scores_gemma":[0.002820163,0.0008096136,0.001131721,0.0007955896,0.000704555,0.001722411,0.00151391,0.002254793,0.0007212005],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00103319,"about_ca_system_score_gemma":0.001398018,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005921723,"about_ca_topic_score_gemma":0.0077476,"domain_scores_codex":[0.999537,0.00008651895,0.00002911382,0.0001541156,0.00011215,0.00008117284],"domain_scores_gemma":[0.9992581,0.0003649942,0.00008963238,0.00007370187,0.0001694919,0.00004413592],"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":[0.0003798411,0.0001906619,0.001700447,0.0001640771,0.0001377666,0.0002232481,0.0001375583,0.6798314,0.01625984,0.004394684,0.004024688,0.2925558],"study_design_scores_gemma":[0.000006604384,0.00001910836,0.0001273334,0.000009253964,0.00001211086,0.00002196822,0.000006001363,0.9956203,0.002067487,0.001834499,0.0002699507,0.00000531296],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04313024,0.0007998119,0.9516285,0.0005294228,0.00006329932,0.00006903813,0.0001805701,0.002044416,0.001554731],"genre_scores_gemma":[0.624043,0.0007797118,0.3634177,0.001154704,0.0001767236,0.0002268751,0.001375812,0.0004917525,0.008333731],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005921723,"threshold_uncertainty_score":0.01177448,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02444994104306319,"score_gpt":0.3120447784122475,"score_spread":0.2875948373691843,"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."}}