{"id":"W2591708961","doi":"10.1007/s13534-017-0020-9","title":"Automatic error correction using adaptive weighting for vessel-based deformable image registration","year":2017,"lang":"en","type":"article","venue":"Biomedical Engineering Letters","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"Custom Security Industries (Canada); Ontario Tech University","funders":"","keywords":"Weighting; Image registration; Metric (unit); Artificial intelligence; Computer science; Computer vision; Adaptation (eye); Error detection and correction; Image (mathematics); Algorithm; Engineering; Radiology; Optics; Physics; Medicine","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001515457,0.0008028739,0.0008698161,0.001504041,0.0004310166,0.001178057,0.00140985,0.001165554,0.001777427],"category_scores_gemma":[0.003928164,0.0006756571,0.0008551654,0.001513057,0.0004235836,0.001320964,0.001574976,0.001315355,0.0008830101],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004429047,"about_ca_system_score_gemma":0.001169842,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002803294,"about_ca_topic_score_gemma":0.004007318,"domain_scores_codex":[0.9990532,0.0001604471,0.00007434357,0.000193548,0.0004275713,0.00009094018],"domain_scores_gemma":[0.9985061,0.0003828793,0.0002062544,0.000391202,0.0004671589,0.00004631808],"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":[0.0003713278,0.0001655493,0.001557314,0.000231891,0.0001592973,0.0001219995,0.0002515453,0.04350754,0.322572,0.00673413,0.002813401,0.6215139],"study_design_scores_gemma":[0.00002414324,0.0001069439,0.002428311,0.00002407274,0.00009857455,0.0003814165,0.00003931689,0.7958351,0.1919727,0.003108348,0.005917339,0.00006378281],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02076829,0.0001972355,0.9772017,0.00006439564,0.00004668105,0.00004284825,0.00004047999,0.00117011,0.0004683639],"genre_scores_gemma":[0.1746544,0.0003191668,0.8208856,0.00006634129,0.00002839557,0.00006753951,0.0002509297,0.000859738,0.002867945],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002803294,"threshold_uncertainty_score":0.008014619,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02512994212924669,"score_gpt":0.2840362227337077,"score_spread":0.258906280604461,"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."}}