{"id":"W4251386841","doi":"10.22215/etd/2008-06599","title":"Segmentation and extraction of regions of interest for automated detection of anomalies in clinical thermal infrared images","year":2008,"lang":"en","type":"dissertation","venue":"","topic":"Infrared Thermography in Medicine","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Library and Archives Canada","funders":"","keywords":"Segmentation; Computer science; Artificial intelligence; Pattern recognition (psychology); A priori and a posteriori; Identification (biology); Computer vision; Image segmentation; Edge detection; Scale-space segmentation; Anomaly detection; Region growing; Image processing; Image (mathematics)","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":[0.000362609,0.0001832924,0.0007260037,0.0007136412,0.00002199466,0.000001986449,0.00005366029,0.0003886192,0.00002545538],"category_scores_gemma":[0.0003866781,0.0001612694,0.0001850404,0.0002859744,0.0002078994,0.0001040113,0.000007078194,0.000236562,1.658854e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002713348,"about_ca_system_score_gemma":0.0001010626,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001372816,"about_ca_topic_score_gemma":0.0001761822,"domain_scores_codex":[0.9980719,0.00008848179,0.001328507,0.0002210939,0.0001738384,0.0001161657],"domain_scores_gemma":[0.9979579,0.000330864,0.001017923,0.0002080427,0.0004436986,0.00004159134],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.004338969,0.0003780559,0.01909801,0.002393454,0.0003008478,0.000005983316,0.002041924,0.000004752982,0.9466718,0.00006628345,0.0002310622,0.02446883],"study_design_scores_gemma":[0.00299144,0.001500548,0.57126,0.001120862,0.0003006416,0.0000230118,0.00448908,0.000499738,0.4175947,0.00009478389,0.00001481383,0.0001103078],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9962276,0.0003817852,0.0003952045,0.00002431614,0.0003225887,0.001049199,0.00003356513,0.00005926176,0.00150649],"genre_scores_gemma":[0.9948259,0.000703001,0.003070275,0.00001273367,0.00007509001,0.00005777386,0.0006622458,0.00003105962,0.0005618961],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5521621,"threshold_uncertainty_score":0.6576377,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04898271215536742,"score_gpt":0.3826319493589679,"score_spread":0.3336492372036005,"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."}}