{"id":"W4400454076","doi":"10.1117/1.jmi.11.4.044002","title":"Projected pooling loss for red nucleus segmentation with soft topology constraints","year":2024,"lang":"en","type":"article","venue":"Journal of Medical Imaging","topic":"Topological and Geometric Data Analysis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Montreal Neurological Institute and Hospital","funders":"Chinese Government Scholarship; Assistance publique-Hôpitaux de Paris; Agence Nationale de la Recherche; Association France Parkinson; European Commission; China Scholarship Council; EU Joint Programme – Neurodegenerative Disease Research; Biogen; Yale University","keywords":"Medicine; Pooling; Segmentation; Topology (electrical circuits); Nucleus; Artificial intelligence; Combinatorics","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00105874,0.00008659382,0.0002158107,0.0003429594,0.00006709046,0.0001997444,0.0005800975,0.00004856293,0.0001975309],"category_scores_gemma":[0.0006764191,0.00005246645,0.00009742232,0.0007420763,0.0001990287,0.0004735022,0.00008963807,0.0002791006,0.00000484591],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004218021,"about_ca_system_score_gemma":0.000228078,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001019391,"about_ca_topic_score_gemma":0.000001678182,"domain_scores_codex":[0.9984868,0.00005552871,0.000386788,0.000189991,0.0006586181,0.0002222462],"domain_scores_gemma":[0.9989917,0.0004218719,0.0001465134,0.0001053959,0.0001591235,0.0001753884],"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":[0.00002456528,0.00006216165,0.0007957108,0.00004068005,0.0001528515,0.001293941,0.0002544512,0.00002607029,0.000272605,0.007106118,0.003913064,0.9860578],"study_design_scores_gemma":[0.003622977,0.0005757426,0.001408852,0.0008510546,0.0003807634,0.01093907,0.001251212,0.9147089,0.001104876,0.01909744,0.04552434,0.0005347942],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006068367,0.0004833309,0.9611319,0.03164645,0.000459751,0.000062895,0.000004165536,0.00004599617,0.00009716832],"genre_scores_gemma":[0.9397969,0.00007793158,0.05868536,0.001009135,0.0003622243,0.00000340805,0.000004552232,0.000006692141,0.00005385632],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.985523,"threshold_uncertainty_score":0.2162825,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01518282694581315,"score_gpt":0.3083966653326332,"score_spread":0.2932138383868201,"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."}}