{"id":"W4401632081","doi":"10.1117/12.3035725","title":"Swin UNet: a memory-efficient and accurate deep learning model for medical image segmentation","year":2024,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Artificial intelligence; Deep learning; Segmentation; Image segmentation; Convolutional neural network; Segmentation-based object categorization; Probabilistic logic; Scale-space segmentation; Scalability; Encoder; Machine learning; Pattern recognition (psychology); Computer vision; Database","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":[0.0006029805,0.000982539,0.0008830976,0.00065637,0.0003077674,0.001001784,0.00260284,0.001282977,0.002202464],"category_scores_gemma":[0.001710171,0.0005882619,0.0008350915,0.0006335736,0.0005284665,0.001702103,0.001327563,0.001376892,0.0007848106],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001196087,"about_ca_system_score_gemma":0.001402268,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008975248,"about_ca_topic_score_gemma":0.01351909,"domain_scores_codex":[0.9998148,0.00002620688,0.00001201186,0.00006223094,0.0000529926,0.0000317211],"domain_scores_gemma":[0.9997087,0.00008963996,0.00004190512,0.00005257634,0.00007984811,0.00002720335],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002988511,0.0001495047,0.001356964,0.0001221887,0.0001116433,0.0001655307,0.0000625978,0.6458488,0.01552757,0.008040478,0.009467476,0.3188483],"study_design_scores_gemma":[0.000004428301,0.00001404021,0.00005099357,0.00000346791,0.000005014961,0.00002050418,0.000002275526,0.9960483,0.001910131,0.001419307,0.0005177556,0.000003781753],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01509904,0.0005203008,0.9788712,0.0002993994,0.00006481652,0.00006765882,0.0002930406,0.003392852,0.001391691],"genre_scores_gemma":[0.5340244,0.001004232,0.4502665,0.0009460928,0.0001149508,0.0002829445,0.002284714,0.0007673865,0.01030884],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008975248,"threshold_uncertainty_score":0.01784599,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01184777087732224,"score_gpt":0.3288687207979259,"score_spread":0.3170209499206036,"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."}}