{"id":"W4387500263","doi":"10.21203/rs.3.rs-3409827/v1","title":"Swin-EchoNet: Deep Learning-based Two-Chamber Segmentation of 2D Echocardiography using Swin Transformer","year":2023,"lang":"en","type":"preprint","venue":"Research Square","topic":"Cardiac Valve Diseases and Treatments","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"ASTER","funders":"","keywords":"Segmentation; Sørensen–Dice coefficient; Ventricle; Artificial intelligence; Ejection fraction; Computer science; Pattern recognition (psychology); Left atrium; Computer vision; Image segmentation; Medicine; Cardiology; Heart failure","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":[0.0006568356,0.0009233398,0.0006316749,0.001001201,0.0002487579,0.0007648665,0.0009518557,0.001004102,0.002675466],"category_scores_gemma":[0.001163478,0.0004138209,0.0006554511,0.0005789793,0.0003317758,0.0009269932,0.0008175459,0.0007458018,0.001082136],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007420293,"about_ca_system_score_gemma":0.0007796547,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005813992,"about_ca_topic_score_gemma":0.008966116,"domain_scores_codex":[0.9998026,0.00003708474,0.00001422638,0.00006073484,0.00005447529,0.00003093813],"domain_scores_gemma":[0.9996846,0.0001166201,0.00003650288,0.00004878814,0.00008373972,0.00002976228],"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":[0.0006281484,0.0003054819,0.003524368,0.000199641,0.0002002107,0.0003243425,0.0001050924,0.3935713,0.02932887,0.004477662,0.01310707,0.5542278],"study_design_scores_gemma":[0.00000861737,0.00003059765,0.0002274099,0.000007906295,0.000006201049,0.00004293459,0.000006637266,0.9925674,0.00536922,0.0009755061,0.0007518176,0.000005705558],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05576837,0.0005901005,0.9323605,0.0002996787,0.0001413978,0.0001274475,0.0006730485,0.008087372,0.001951934],"genre_scores_gemma":[0.5843598,0.0005495986,0.4037995,0.0004761903,0.00008383452,0.0001986602,0.003313385,0.0006051307,0.006614063],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005813992,"threshold_uncertainty_score":0.01156026,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08153451435301387,"score_gpt":0.4660014504104671,"score_spread":0.3844669360574532,"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."}}