{"id":"W4406254866","doi":"10.1038/s41598-025-85632-9","title":"Improving spleen segmentation in ultrasound images using a hybrid deep learning framework","year":2025,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Segmentation; Artificial intelligence; Computer science; Autoencoder; Pattern recognition (psychology); Intersection (aeronautics); Deep learning; Noise (video); Image (mathematics); Cartography; Geography","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":[0.0007421541,0.001312081,0.0009231789,0.00167205,0.0003485406,0.001009751,0.001375951,0.001361747,0.001591096],"category_scores_gemma":[0.001216969,0.0006365876,0.0009126829,0.0008785647,0.0004488223,0.001062874,0.001213082,0.001089126,0.0008876773],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000713878,"about_ca_system_score_gemma":0.001113704,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005712712,"about_ca_topic_score_gemma":0.01051566,"domain_scores_codex":[0.9996542,0.00005388816,0.000018919,0.0001111438,0.0001050232,0.0000568316],"domain_scores_gemma":[0.9996582,0.0001024298,0.00004638797,0.00004933399,0.0001082028,0.00003542786],"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":[0.0003533637,0.0002000105,0.004226333,0.0002498079,0.0002277036,0.0003038662,0.0001717324,0.2543747,0.06267086,0.003344864,0.008066102,0.6658106],"study_design_scores_gemma":[0.00001133543,0.00005449065,0.0005651162,0.00001851924,0.00003143123,0.0001258814,0.00001787265,0.9847328,0.01141528,0.001591843,0.001422688,0.00001274948],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03933744,0.001186727,0.95222,0.000278106,0.00007119293,0.00007037505,0.0002798916,0.00467729,0.001878995],"genre_scores_gemma":[0.442135,0.001053595,0.5460924,0.0007638702,0.0001802936,0.0001309897,0.001839772,0.0006196197,0.007184418],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005712712,"threshold_uncertainty_score":0.01135892,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05212644816333024,"score_gpt":0.4009815680334505,"score_spread":0.3488551198701203,"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."}}