{"id":"W4417250735","doi":"10.1109/bibe66822.2025.00017","title":"Improving Right Ventricle Segmentation in Cardiac Magnetic Resonance Imaging Through Transfer Learning","year":2025,"lang":"","type":"article","venue":"","topic":"Cardiac Valve Diseases and Treatments","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Segmentation; Convolutional neural network; Transfer of learning; Hausdorff distance; Pattern recognition (psychology); Magnetic resonance imaging; Deep learning; Sørensen–Dice coefficient; Similarity (geometry)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001176208,0.0009108615,0.0006602628,0.001025393,0.0003364728,0.0007326371,0.001030004,0.001164753,0.001156743],"category_scores_gemma":[0.002705903,0.0003249116,0.0007048132,0.0006183161,0.0004503298,0.0009598192,0.000958254,0.0007973539,0.0008277253],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006441637,"about_ca_system_score_gemma":0.0007421174,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00378934,"about_ca_topic_score_gemma":0.004913937,"domain_scores_codex":[0.9995273,0.0001107939,0.0000278044,0.0001777196,0.000103393,0.00005301093],"domain_scores_gemma":[0.999292,0.0003110732,0.00009266297,0.000126302,0.0001387993,0.00003911197],"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":[0.0003228273,0.0002318941,0.004993626,0.0001235805,0.0001345511,0.0003472861,0.000186123,0.2757264,0.06188563,0.001085936,0.003674096,0.651288],"study_design_scores_gemma":[0.00000754507,0.00006707593,0.001281915,0.000008407523,0.00002047767,0.0001338143,0.00002021449,0.9803559,0.01622937,0.001215459,0.0006458689,0.00001407066],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2060472,0.001098218,0.7841513,0.0003596476,0.00007968119,0.0001267792,0.0001879592,0.005409397,0.002539859],"genre_scores_gemma":[0.7977692,0.0004475017,0.1973603,0.000270001,0.0000817325,0.00008619165,0.0005659321,0.0003396413,0.003079592],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00378934,"threshold_uncertainty_score":0.007534564,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005143689034623267,"score_gpt":0.2937065405204319,"score_spread":0.2885628514858087,"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."}}