{"id":"W4409705379","doi":"10.3390/jimaging11050131","title":"Improvements in Image Registration, Segmentation, and Artifact Removal in ThermOcular Imaging System","year":2025,"lang":"en","type":"article","venue":"Journal of Imaging","topic":"Optical Systems and Laser Technology","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Artifact (error); Computer vision; Artificial intelligence; Computer science; Image registration; Segmentation; Image segmentation; Image processing; Pattern recognition (psychology); Image (mathematics)","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001396402,0.0008043254,0.0008884473,0.001461472,0.0004149543,0.001451962,0.001343218,0.001105847,0.00271532],"category_scores_gemma":[0.003128753,0.0004804678,0.0009997978,0.0009854997,0.0003081573,0.001397716,0.00101104,0.001032654,0.002327417],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006212202,"about_ca_system_score_gemma":0.001349619,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004846332,"about_ca_topic_score_gemma":0.005774856,"domain_scores_codex":[0.9987546,0.0002044745,0.0001205792,0.0003784575,0.000431665,0.000110158],"domain_scores_gemma":[0.9992367,0.000134334,0.00007941871,0.0002128864,0.0003036934,0.00003284471],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0005773039,0.0001571069,0.003323986,0.0004755544,0.0001610767,0.0003914212,0.0002342128,0.02447479,0.1767348,0.00253935,0.0103166,0.7806139],"study_design_scores_gemma":[0.00006053546,0.0006298052,0.01165581,0.0001319608,0.0002298556,0.001652562,0.000134239,0.6701797,0.2594015,0.002809505,0.05294456,0.0001698617],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05720868,0.002834578,0.9155018,0.0005522761,0.0004567378,0.0002381311,0.0007258366,0.01780744,0.004674456],"genre_scores_gemma":[0.2337268,0.001293099,0.755711,0.0004612949,0.0001982354,0.0001881118,0.002082449,0.001119138,0.005219744],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004846332,"threshold_uncertainty_score":0.009636223,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0024367180527014,"score_gpt":0.2136103451575659,"score_spread":0.2111736271048645,"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."}}