{"id":"W4407566436","doi":"10.1109/tim.2025.3541664","title":"Novel CNN-Based Approach for Burn Severity Assessment and Fine-Grained Boundary Segmentation in Burn Images","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Instrumentation and Measurement","topic":"Fire Detection and Safety Systems","field":"Engineering","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University; Montreal Heart Institute; Université de Montréal; University of Alberta; SKiN Health","funders":"","keywords":"Burn-in; Segmentation; Computer science; Image segmentation; Boundary (topology); Pediatric burn; Artificial intelligence; Computer vision; Engineering; Reliability engineering; Medicine; Mathematics; Surgery","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":[0.0003753367,0.0001781877,0.0001764407,0.0002860584,0.0001934313,0.00008545675,0.00003796016,0.00007212902,0.00001027257],"category_scores_gemma":[0.000002808074,0.0001899578,0.00005068094,0.000211474,0.00003584442,0.0001452815,6.242715e-7,0.0001374222,5.258003e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004198864,"about_ca_system_score_gemma":0.00006544423,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006734307,"about_ca_topic_score_gemma":0.0001785793,"domain_scores_codex":[0.9989668,0.00003963461,0.0003400797,0.0002400575,0.0002516628,0.0001617517],"domain_scores_gemma":[0.999698,0.00003039122,0.0000389699,0.0001030667,0.00007269917,0.00005688629],"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":[0.0004890219,0.0009134081,0.001002611,0.001926495,0.0003824394,0.000001083691,0.00123812,0.2098261,0.3123394,0.0001700375,0.0004686275,0.4712427],"study_design_scores_gemma":[0.01219121,0.0002968594,0.01602548,0.0002725846,0.0001373237,0.000006954331,0.00220112,0.8233231,0.1433607,0.00008220389,0.001534434,0.0005680369],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02964375,0.0000645956,0.9677579,0.0002319922,0.0005723367,0.0009674281,0.00005134933,0.0001171832,0.000593461],"genre_scores_gemma":[0.9892246,0.00003904065,0.009923899,0.0001398816,0.00001243333,0.0005430962,0.00002291247,0.00001540084,0.00007877671],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9595808,"threshold_uncertainty_score":0.7746257,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0259327235583379,"score_gpt":0.2620148287273842,"score_spread":0.2360821051690463,"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."}}