{"id":"W4408110112","doi":"10.1007/978-3-031-82475-3_2","title":"Medical Image Denosing via Explainable AI Feature Preserving Loss","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Artificial intelligence; Feature (linguistics); Image (mathematics); Pattern recognition (psychology); Computer vision; Linguistics","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":[0.0005252481,0.0004335447,0.0003745774,0.0005243574,0.0001490188,0.0006345263,0.0005508725,0.0006563641,0.002207294],"category_scores_gemma":[0.001287036,0.000201703,0.0005058431,0.0003719623,0.0004651053,0.0007118895,0.0007710014,0.001156769,0.000721604],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002396418,"about_ca_system_score_gemma":0.0002457321,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003809796,"about_ca_topic_score_gemma":0.0005628655,"domain_scores_codex":[0.9997922,0.00004147524,0.00001053282,0.00003911912,0.00009405235,0.00002272217],"domain_scores_gemma":[0.9996946,0.0001042782,0.00003626172,0.00009503312,0.00005370549,0.00001611992],"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":[0.0004690555,0.0001049984,0.0006166167,0.0002749522,0.0001136219,0.0003571978,0.0001309094,0.1225379,0.1745399,0.07431684,0.006408062,0.6201299],"study_design_scores_gemma":[0.00002227158,0.0001336522,0.0007822808,0.0000235683,0.00004030594,0.0007855826,0.00002425208,0.8993272,0.05587347,0.03491677,0.008049569,0.00002117011],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008595135,0.0002911729,0.9884642,0.000185173,0.00005107526,0.00002218027,0.00004875923,0.0004185769,0.001923804],"genre_scores_gemma":[0.3545707,0.001001793,0.6296935,0.000364631,0.0002190158,0.00006693431,0.0003573307,0.0003350375,0.0133911],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002207294,"threshold_uncertainty_score":0.007384181,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009270335879796882,"score_gpt":0.2813603709611708,"score_spread":0.272090035081374,"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."}}