{"id":"W3008167392","doi":"10.1016/j.media.2019.101612","title":"Trophectoderm segmentation in human embryo images via inceptioned U-Net","year":2020,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Reproductive Biology and Fertility","field":"Medicine","cited_by":73,"is_retracted":false,"has_abstract":false,"ca_institutions":"Canadian Hemophilia Society; Pacific Centre for Reproductive Medicine; Simon Fraser University","funders":"","keywords":"Jaccard index; Artificial intelligence; Segmentation; Computer science; Sørensen–Dice coefficient; Pattern recognition (psychology); Convolutional neural network; Dice; Deep learning; Image segmentation; Minimum bounding box; Machine learning; Image (mathematics); Mathematics; Statistics","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004269599,0.0001264457,0.0004758376,0.0001657946,0.0000643363,0.00001011813,0.0001042411,0.0001283556,0.004581114],"category_scores_gemma":[0.0007172916,0.0001009465,0.000199875,0.001041923,0.0002745836,0.0001048128,0.00004879316,0.0003148191,0.00008133506],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005227799,"about_ca_system_score_gemma":0.00004477791,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001708443,"about_ca_topic_score_gemma":0.00005103071,"domain_scores_codex":[0.9983439,0.0001995719,0.0003977666,0.0004894437,0.0003779742,0.0001913206],"domain_scores_gemma":[0.999283,0.00004066525,0.00007165639,0.0002592765,0.00008748847,0.0002579075],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0007113331,0.0003302931,0.2638933,0.00006616589,0.0009409562,0.0003352862,0.0007709151,0.000007891792,0.7221137,0.000005769535,0.001341218,0.009483199],"study_design_scores_gemma":[0.001298387,0.0001867923,0.9608718,0.000009924636,0.0009491662,0.000006167212,0.000210013,0.003725994,0.03240891,0.0001166243,0.00008842145,0.0001277779],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9339513,0.0001790225,0.05336226,0.01141256,0.00002667469,0.0001983396,0.00000516334,0.0000640359,0.0008006924],"genre_scores_gemma":[0.996168,0.00003068087,0.0009142281,0.002202934,0.0002219311,0.00001969314,0.0002610873,0.000007655117,0.0001738048],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6969785,"threshold_uncertainty_score":0.9963288,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01715075676409398,"score_gpt":0.3192022697082575,"score_spread":0.3020515129441635,"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."}}