{"id":"W2955463555","doi":"10.1016/j.compbiomed.2019.103342","title":"Deep learning for the classification of human sperm","year":2019,"lang":"en","type":"article","venue":"Computers in Biology and Medicine","topic":"Sperm and Testicular Function","field":"Medicine","cited_by":150,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"Canadian Institutes of Health Research; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Sperm; Artificial intelligence; Deep learning; Computer science; Machine learning; Biology","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0006914997,0.0006247105,0.0006038126,0.0006960718,0.0002959656,0.0006403838,0.001076363,0.001187844,0.003385559],"category_scores_gemma":[0.001686501,0.0002631216,0.0006405083,0.0008599074,0.0003937976,0.0006583494,0.000868535,0.001585766,0.001287985],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008609298,"about_ca_system_score_gemma":0.0009000362,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01048743,"about_ca_topic_score_gemma":0.01121063,"domain_scores_codex":[0.9998066,0.00005017341,0.00001039126,0.00004884317,0.00004360954,0.00004048067],"domain_scores_gemma":[0.9995463,0.0002011046,0.0000381426,0.00005071215,0.0001314174,0.00003224306],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002554296,0.0001461246,0.003545617,0.0002279546,0.0001229606,0.00008770499,0.00006848219,0.2244067,0.004279878,0.01537737,0.03178548,0.7196963],"study_design_scores_gemma":[0.000009531042,0.00003008048,0.0007391434,0.00002873132,0.00001373102,0.00002307129,0.00001369343,0.9828347,0.001527539,0.01197152,0.002800519,0.00000773585],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1082748,0.01817326,0.8540786,0.003919388,0.0007308111,0.0001096922,0.003472488,0.003903451,0.007337515],"genre_scores_gemma":[0.7795522,0.003835035,0.1845118,0.0008488708,0.0004276747,0.0001425423,0.003697492,0.0002082842,0.02677608],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01048743,"threshold_uncertainty_score":0.0208528,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03211020343811634,"score_gpt":0.3275956747492436,"score_spread":0.2954854713111272,"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."}}