{"id":"W2958269485","doi":"10.1007/s11548-019-02022-z","title":"CycleGAN for style transfer in X-ray angiography","year":2019,"lang":"en","type":"article","venue":"International Journal of Computer Assisted Radiology and Surgery","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":false,"ca_institutions":"École de Technologie Supérieure","funders":"Mitacs","keywords":"Computer science; Artificial intelligence; Similarity (geometry); Task (project management); Translation (biology); Image translation; Data set; Consistency (knowledge bases); Deep learning; Image (mathematics); Angiography; Computer vision; Radiology; Medicine","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006446688,0.0001011645,0.0003197042,0.00048543,0.00002558266,0.00007324904,0.000383393,0.00007251576,0.000009281699],"category_scores_gemma":[0.00002008271,0.00008344007,0.0003212276,0.0001399161,0.00004154366,0.0003998317,0.00003417215,0.0001201085,0.000001260785],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001754223,"about_ca_system_score_gemma":0.00005229057,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003137753,"about_ca_topic_score_gemma":0.000002629498,"domain_scores_codex":[0.9989649,0.0001535598,0.0004171324,0.0001710863,0.0001397978,0.0001535092],"domain_scores_gemma":[0.9986147,0.0009084251,0.000116057,0.00009583239,0.0002113431,0.00005360919],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.001022932,0.000657988,0.3802561,0.00004123785,0.002965766,0.0005821797,0.001864524,0.02424448,0.004930366,0.02021316,0.0176343,0.5455869],"study_design_scores_gemma":[0.003085275,0.0004628585,0.7683428,0.0002295178,0.00003968786,0.001254654,0.0000429367,0.1981128,0.0006721627,0.001857124,0.02539412,0.0005060383],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1911119,0.0006069829,0.8038565,0.001613111,0.002701143,0.00006712017,0.000001821472,0.000007412396,0.00003403179],"genre_scores_gemma":[0.9732516,0.00008883221,0.02559042,0.0006420581,0.0004066681,0.000002214896,0.000002583872,0.000004823009,0.00001081907],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7821397,"threshold_uncertainty_score":0.3402587,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01128382826469731,"score_gpt":0.2291668803276143,"score_spread":0.217883052062917,"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."}}