{"id":"W4406047891","doi":"10.1073/pnas.2321319121","title":"Image segmentation with traveling waves in an exactly solvable recurrent neural network","year":2025,"lang":"en","type":"article","venue":"Proceedings of the National Academy of Sciences","topic":"Cell Image Analysis Techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University; Western University","funders":"National Institute of Neurological Disorders and Stroke; National Eye Institute","keywords":"Segmentation; Artificial intelligence; Computer science; Image segmentation; Object (grammar); Grayscale; Artificial neural network; Recurrent neural network; Segmentation-based object categorization; Pattern recognition (psychology); Image (mathematics); Scale-space segmentation; Computation; Simple (philosophy); Computer vision; Algorithm","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":[0.0004567981,0.0003164876,0.0003987854,0.0003093247,0.0003060405,0.0007869108,0.0006100246,0.0009749505,0.001038524],"category_scores_gemma":[0.001509516,0.0003235216,0.0004785969,0.0002510805,0.001047237,0.001263852,0.0005477755,0.0005713707,0.0001545672],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008518285,"about_ca_system_score_gemma":0.0004043464,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002697352,"about_ca_topic_score_gemma":0.001793769,"domain_scores_codex":[0.999866,0.00004470768,0.000006604875,0.00003040422,0.00002914308,0.0000231489],"domain_scores_gemma":[0.9997497,0.0001258587,0.00005425714,0.00001987711,0.00003013452,0.0000201684],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005695547,0.00002746268,0.0004995682,0.00003966596,0.00003142484,0.0002653115,0.0001709195,0.7752146,0.0182181,0.1980623,0.0005705929,0.006843263],"study_design_scores_gemma":[0.000002934821,0.000004674393,0.00003228969,0.000001055753,0.000001395011,0.000008717465,0.000004552736,0.9894556,0.0003575079,0.01006172,0.00006725272,0.000002208408],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2105404,0.0002251865,0.7809131,0.0005263705,0.00003887716,0.00002450514,0.00005106779,0.0002693552,0.007411079],"genre_scores_gemma":[0.9403914,0.0001530945,0.05505018,0.0000879923,0.00002163876,0.00004899405,0.00005040728,0.00006026694,0.004136001],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002697352,"threshold_uncertainty_score":0.006180465,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01853569517294158,"score_gpt":0.318458008345791,"score_spread":0.2999223131728494,"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."}}