{"id":"W4321444690","doi":"10.1101/2023.02.17.528925","title":"Active mesh and neural network pipeline for cell aggregate segmentation","year":2023,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Cell Image Analysis Techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institute of Cancer Research","funders":"Engineering and Physical Sciences Research Council; Medical Research Council; Wellcome Trust; Francis Crick Institute; Universiteit Utrecht; Cancer Research UK","keywords":"Segmentation; Computer science; Artificial intelligence; Polygon mesh; Pipeline (software); Computer vision; Deep learning; Image segmentation; Artificial neural network; Pattern recognition (psychology); Computer graphics (images)","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003919031,0.0004194869,0.0003829008,0.0001118549,0.0001274649,0.0001302988,0.0002930935,0.0004557089,0.000005840164],"category_scores_gemma":[0.0001111764,0.0004704033,0.0001880406,0.0001966849,0.00008406564,0.00001026657,0.0005717031,0.0002711818,0.000005062874],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005149608,"about_ca_system_score_gemma":0.0001317202,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002866621,"about_ca_topic_score_gemma":0.00001195562,"domain_scores_codex":[0.9979643,0.00008679112,0.0003733065,0.0009998704,0.0001567905,0.0004189913],"domain_scores_gemma":[0.9982705,0.00003235174,0.0003919161,0.0008040357,0.0003641642,0.0001370328],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00007698781,0.0000441908,0.0008019196,0.0001807665,0.000131649,0.000007904127,0.00000319866,0.0001576756,0.9885182,0.000007074312,0.010052,0.00001844585],"study_design_scores_gemma":[0.0004366553,0.00008624755,0.002115412,0.00006774611,0.0002279528,9.932029e-9,0.000003088168,0.003152511,0.9894985,0.000005297926,0.00389157,0.0005150333],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9556606,0.002012398,0.03952236,0.0001654848,0.0003812474,0.001663425,0.0002369711,0.0003460573,0.00001150114],"genre_scores_gemma":[0.9846238,0.00147025,0.0118451,0.0002737591,0.001001401,0.0005041177,0.0000187977,0.000168139,0.00009460389],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02896328,"threshold_uncertainty_score":0.9997748,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01184611313532357,"score_gpt":0.2455873080737132,"score_spread":0.2337411949383897,"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."}}