{"id":"W2948704847","doi":"10.1109/access.2019.2920933","title":"Cell-Net: Embryonic Cell Counting and Centroid Localization via Residual Incremental Atrous Pyramid and Progressive Upsampling Convolution","year":2019,"lang":"en","type":"article","venue":"IEEE Access","topic":"Reproductive Biology and Fertility","field":"Medicine","cited_by":39,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Hemophilia Society; Pacific Centre for Reproductive Medicine; Simon Fraser University","funders":"","keywords":"Artificial intelligence; Computer science; Pyramid (geometry); Pattern recognition (psychology); Upsampling; Residual; Convolution (computer science); Feature extraction; Convolutional neural network; Mathematics; Algorithm; Artificial neural network; Image (mathematics)","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":[0.0002914715,0.0001417908,0.0002216922,0.00005340703,0.0001365408,0.00004461536,0.00006846021,0.0001281665,0.00003144069],"category_scores_gemma":[0.00003712231,0.0001241717,0.00002158314,0.00009037624,0.0001755312,0.0002656241,0.00007679293,0.0001702143,0.0000118025],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006654915,"about_ca_system_score_gemma":0.0000445574,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009644442,"about_ca_topic_score_gemma":0.000005638714,"domain_scores_codex":[0.9988791,0.00006244552,0.0002009747,0.0004762594,0.000141715,0.0002394858],"domain_scores_gemma":[0.9993629,0.00004047744,0.0001957873,0.0002097965,0.0001224566,0.00006851024],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001174034,0.0001058691,0.8926183,0.0003602705,0.00003051817,0.000008420026,0.0002676346,0.00007596333,0.1046957,0.000009834836,0.0001539454,0.0004995534],"study_design_scores_gemma":[0.002745187,0.0004200584,0.8134111,0.0001000862,0.0001253297,0.000063236,0.0002685409,0.006564792,0.1755825,0.0001835301,0.0002840098,0.0002516313],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9925109,0.003211073,0.002794041,0.0001064707,0.0003196178,0.0007439671,0.000006007201,0.00004407295,0.0002638305],"genre_scores_gemma":[0.9991947,0.00009426371,0.0001199895,0.0001609382,0.0002400796,0.00001162795,0.00005380888,0.0000147114,0.0001098554],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07920719,"threshold_uncertainty_score":0.5063573,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01473143424194887,"score_gpt":0.2804590505424663,"score_spread":0.2657276163005174,"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."}}