{"id":"W3174288574","doi":"10.1016/j.neucom.2021.06.085","title":"CNN-based visual processing approach for biological sample microinjection systems","year":2021,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Zebrafish Biomedical Research Applications","field":"Biochemistry, Genetics and Molecular Biology","cited_by":13,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Victoria","funders":"National Natural Science Foundation of China","keywords":"Microinjection; Computer science; Sample (material); Orientation (vector space); Zebrafish; Convolutional neural network; Rotation (mathematics); Artificial intelligence; Computer vision; Process (computing); Path (computing); Pipette; Real-time computing; Biology; 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":[0.0001991678,0.0001108744,0.0001194814,0.00003394561,0.0002189055,0.00008351899,0.0001403632,0.0001290498,0.00000259695],"category_scores_gemma":[0.0006945636,0.0001045249,0.00007793923,0.0002104424,0.00006757193,0.000002080308,0.0001001699,0.00008702192,0.000002038239],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001681174,"about_ca_system_score_gemma":0.0001940777,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008012963,"about_ca_topic_score_gemma":7.938763e-7,"domain_scores_codex":[0.9987465,0.00008836979,0.0001988142,0.00050894,0.0001365716,0.0003207881],"domain_scores_gemma":[0.9993535,0.000107877,0.00006838535,0.000163534,0.0001976382,0.000109047],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002766885,0.0001573397,0.0005898187,0.00009737279,0.000008908055,0.000001242541,0.000003770924,0.0009399659,0.9810205,0.00003860233,0.0006153597,0.0164995],"study_design_scores_gemma":[0.00125801,0.0005706787,0.001687605,0.00003846634,0.00001492394,0.00005863162,0.0001342837,0.4729605,0.4446331,0.00004312873,0.07821767,0.0003829635],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2615769,0.0002331211,0.7374181,0.0001162346,0.00005273184,0.0003635512,0.00001538774,0.00003952106,0.0001844711],"genre_scores_gemma":[0.9653171,0.000005537423,0.03294207,0.0003512106,0.0004977889,0.0001350448,0.0006779364,0.00002200143,0.00005127569],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7044761,"threshold_uncertainty_score":0.4262402,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03347871725575596,"score_gpt":0.3233560064409106,"score_spread":0.2898772891851546,"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."}}