{"id":"W3206798574","doi":"10.1101/2021.10.12.464160","title":"DeepImageTranslator V2: analysis of multimodal medical images using semantic segmentation maps generated through deep learning","year":2021,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Medical Imaging Techniques and Applications","field":"Medicine","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"Centre Hospitalier Universitaire de Sherbrooke; Université de Sherbrooke; Université de Montréal; Cégep de Saint-Laurent","funders":"","keywords":"Artificial intelligence; Computer science; Deep learning; Segmentation; Software; Convolutional neural network; Pattern recognition (psychology); Computer vision","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":[0.001073034,0.001719113,0.0007374792,0.00146641,0.0002871093,0.001365796,0.001797285,0.0009312753,0.0143466],"category_scores_gemma":[0.00286309,0.0007618342,0.001379288,0.0006487911,0.0004496438,0.000779557,0.001558624,0.001179802,0.003250628],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009976061,"about_ca_system_score_gemma":0.001387579,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003192278,"about_ca_topic_score_gemma":0.003106016,"domain_scores_codex":[0.9996936,0.00004425785,0.00003016149,0.0001063752,0.0000882743,0.00003729267],"domain_scores_gemma":[0.9994254,0.0002621719,0.00006387909,0.00008452554,0.0001227968,0.00004120314],"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":[0.001085231,0.0002320348,0.005721561,0.001083607,0.000684934,0.0007477183,0.0003552183,0.1392847,0.05424254,0.006386586,0.09107693,0.699099],"study_design_scores_gemma":[0.00009604012,0.0001325494,0.00235202,0.00006234687,0.00005442837,0.0004210242,0.00004159388,0.9083806,0.06696193,0.006602388,0.01482306,0.00007199861],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03039896,0.0003749385,0.8070589,0.000331427,0.0001281406,0.0002243333,0.004517886,0.1553444,0.001621141],"genre_scores_gemma":[0.2319869,0.0005295133,0.733486,0.0004937104,0.00006213045,0.001138819,0.01196685,0.01485925,0.005476855],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.0143466,"threshold_uncertainty_score":0.04799414,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02172917753350544,"score_gpt":0.2959095556895984,"score_spread":0.274180378156093,"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."}}