{"id":"W4399478109","doi":"10.1002/mp.17242","title":"Semi‐supervised learning framework with shape encoding for neonatal ventricular segmentation from 3D ultrasound","year":2024,"lang":"en","type":"article","venue":"Medical Physics","topic":"Fetal and Pediatric Neurological Disorders","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University; London Health Sciences Centre; University of Guelph","funders":"Natural Sciences and Engineering Research Council of Canada; Government of Canada; Canadian Institutes of Health Research; Government of Ontario","keywords":"Segmentation; Encoding (memory); Ultrasound; Artificial intelligence; Computer science; Pattern recognition (psychology); Medicine; Radiology","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001124181,0.000155573,0.0002337288,0.00002583541,0.00008863879,0.00003791173,0.00008080658,0.0001498701,0.0007954536],"category_scores_gemma":[0.0004759178,0.0001060952,0.000112753,0.0002991435,0.00008125898,0.00007956263,0.0000247927,0.0006134273,0.00005709255],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002575617,"about_ca_system_score_gemma":0.0000881722,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001384968,"about_ca_topic_score_gemma":7.41049e-7,"domain_scores_codex":[0.998615,0.00003083486,0.0001755583,0.0003387333,0.0005937829,0.0002460817],"domain_scores_gemma":[0.9985214,0.001115599,0.00002867159,0.00009553265,0.00003316332,0.0002055665],"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":[0.001685781,0.0008711129,0.07322057,0.001656212,0.0008928381,0.003130643,0.003545174,0.0006304284,0.005175237,0.001908169,0.005014342,0.9022695],"study_design_scores_gemma":[0.03340788,0.01866287,0.04215676,0.007694312,0.007651285,0.0009354175,0.003767352,0.5216321,0.03062715,0.1518973,0.1762366,0.005331088],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7604987,0.002208138,0.2338722,0.001633169,0.0004251821,0.0005095506,0.00002916836,0.0002796714,0.0005442197],"genre_scores_gemma":[0.9950027,0.0001669035,0.001447364,0.001425869,0.001416838,0.00004562651,0.0003852074,0.00002994678,0.0000795446],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8969384,"threshold_uncertainty_score":0.8709659,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0140446926797901,"score_gpt":0.2627625719833362,"score_spread":0.2487178793035461,"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."}}