{"id":"W4389429244","doi":"10.1186/s12880-023-01160-w","title":"MedFusionGAN: multimodal medical image fusion using an unsupervised deep generative adversarial network","year":2023,"lang":"en","type":"article","venue":"BMC Medical Imaging","topic":"Advanced Image Fusion Techniques","field":"Engineering","cited_by":58,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval; Hôtel-Dieu de Québec","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Artificial intelligence; Computer science; Pattern recognition (psychology); Medical imaging; Discriminator; Generator (circuit theory); Segmentation; Deep learning; Magnetic resonance imaging; Similarity (geometry); Computer vision; Image (mathematics); 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":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001404959,0.0004484275,0.0005121581,0.0002597453,0.0003718456,0.00008473822,0.0007115834,0.0003171746,0.004146096],"category_scores_gemma":[0.001497348,0.0004253038,0.0001523926,0.0009175769,0.0003283654,0.0007104435,0.0005442947,0.0008641806,0.0001946254],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001634092,"about_ca_system_score_gemma":0.0003047186,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000656442,"about_ca_topic_score_gemma":0.0001347977,"domain_scores_codex":[0.9954361,0.0003039702,0.0007292124,0.0006230319,0.001883699,0.001023942],"domain_scores_gemma":[0.9976567,0.0005457067,0.00007233053,0.0005378455,0.000134168,0.001053264],"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":[0.0002574423,0.0004894736,0.006191705,0.0006070447,0.0001764085,0.005548199,0.003222581,0.1005182,0.2391327,0.0006448341,0.04629541,0.596916],"study_design_scores_gemma":[0.001170806,0.00001778562,0.0004505554,0.0002770132,0.00002426463,0.00008152151,0.0002692607,0.9904921,0.005163155,0.0006087489,0.0009523577,0.0004924401],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06633003,0.0003071348,0.925974,0.0002708415,0.001787563,0.0003935059,0.000008560879,0.003895768,0.001032657],"genre_scores_gemma":[0.3345112,0.001110722,0.6528597,0.001960427,0.008253028,0.0001711919,0.0004812549,0.0005478463,0.0001045912],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8899739,"threshold_uncertainty_score":0.9998199,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01776154492416675,"score_gpt":0.2958762085555919,"score_spread":0.2781146636314252,"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."}}