{"id":"W4391935875","doi":"10.1109/tmi.2024.3367367","title":"A Collaborative Self-Supervised Domain Adaptation for Low-Quality Medical Image Enhancement","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Medical Imaging","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"China Scholarship Council; National Natural Science Foundation of China","keywords":"Computer science; Artificial intelligence; Image quality; Segmentation; Medical imaging; Benchmark (surveying); Quality (philosophy); Image segmentation; Adaptation (eye); Computer vision; Pattern recognition (psychology); Machine learning; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001603685,0.0007131817,0.001012922,0.0006892672,0.0002656975,0.0007135899,0.001453448,0.00106697,0.001095064],"category_scores_gemma":[0.003497364,0.0003459924,0.000964776,0.0005386362,0.0007267891,0.001052656,0.00117412,0.001120859,0.000565332],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004011668,"about_ca_system_score_gemma":0.0005291114,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001412806,"about_ca_topic_score_gemma":0.001556897,"domain_scores_codex":[0.9991672,0.0001932539,0.0000398143,0.0003004526,0.0002287474,0.00007059444],"domain_scores_gemma":[0.9985355,0.0004434827,0.0001517938,0.0002896561,0.0004893005,0.00009018822],"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":[0.0004383343,0.0004034834,0.003360388,0.000261278,0.0001965155,0.0002911302,0.0002817617,0.3628527,0.07860073,0.002862599,0.006526617,0.5439245],"study_design_scores_gemma":[0.00001998214,0.00005916082,0.0005294968,0.000008590434,0.00001741043,0.0001048267,0.00001512257,0.9891733,0.008003772,0.001315875,0.0007399445,0.0000125439],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02919243,0.0004385893,0.9682049,0.0001326725,0.00005543117,0.0000667109,0.00005386338,0.0009544662,0.0009009847],"genre_scores_gemma":[0.5231655,0.0004768746,0.4701411,0.0006110529,0.0001411024,0.0001722628,0.0005440327,0.0002950302,0.004453004],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.001603685,"threshold_uncertainty_score":0.008481145,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01332964732665652,"score_gpt":0.3414177534573144,"score_spread":0.3280881061306579,"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."}}