{"id":"W4410152883","doi":"10.1109/tase.2025.3567946","title":"Automated Parts Segmentation of Sperm via a Contrastive Learning-Based Part Matching Network","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Automation Science and Engineering","topic":"Sperm and Testicular Function","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"CReATe Fertility Centre; University of Toronto","funders":"","keywords":"Artificial intelligence; Segmentation; Computer science; Matching (statistics); Computer vision; Image segmentation; Pattern matching; Engineering; 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":[0.0003394014,0.00009577853,0.0001434593,0.0002922026,0.0001801529,0.00002993418,0.00003040635,0.00004292673,0.00002217263],"category_scores_gemma":[0.00003945264,0.00009164895,0.00003404147,0.0008487398,0.00007402041,0.0001828245,6.820554e-7,0.0001181473,0.000003828475],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009264929,"about_ca_system_score_gemma":0.0001172941,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001336072,"about_ca_topic_score_gemma":0.000001911227,"domain_scores_codex":[0.9991779,0.000013113,0.0002067033,0.0001767382,0.0002667141,0.0001588445],"domain_scores_gemma":[0.9995567,0.00009315073,0.00005090753,0.00008668882,0.0001513772,0.00006113396],"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":[0.00002987853,0.00004722985,0.0002124515,0.00007968618,0.00002328772,0.000001616746,0.0001543721,0.9239311,0.06647298,0.00004572583,0.00002183437,0.008979814],"study_design_scores_gemma":[0.0005865726,0.0001045652,0.01411411,0.0002857024,0.00006655266,0.000008628886,0.00006742611,0.926033,0.05859671,0.00001046616,0.00005498837,0.00007123641],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2881831,0.00001670823,0.7107216,0.00009753108,0.0003568378,0.0001764712,0.000001065071,0.0003525147,0.00009417526],"genre_scores_gemma":[0.9975558,0.000006907022,0.002253632,0.0000944463,0.00001853267,0.00002472248,0.000003453378,0.000006596386,0.00003593965],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7093727,"threshold_uncertainty_score":0.3737336,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008493594641053273,"score_gpt":0.2490279080292568,"score_spread":0.2405343133882035,"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."}}