{"id":"W2982287615","doi":"10.1016/j.media.2019.101593","title":"Multi-indices quantification of optic nerve head in fundus image via multitask collaborative learning","year":2019,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":28,"is_retracted":false,"has_abstract":false,"ca_institutions":"Western University","funders":"National Natural Science Foundation of China","keywords":"Computer science; Multi-task learning; Artificial intelligence; Feature (linguistics); Fundus (uterus); Task (project management); Pattern recognition (psychology); Representation (politics); Feature learning; Ensemble learning; Segmentation; Machine learning","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":[0.001324084,0.0002370802,0.001117176,0.001096449,0.00006156418,0.00004888377,0.0002188038,0.000143939,0.001401201],"category_scores_gemma":[0.001571818,0.0001952722,0.0004591097,0.004311156,0.0002943356,0.0002491494,0.00006418043,0.0006525191,0.0002949453],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008204605,"about_ca_system_score_gemma":0.0001593552,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001649108,"about_ca_topic_score_gemma":0.0002816593,"domain_scores_codex":[0.9968647,0.000355548,0.0008568772,0.0005748422,0.000988399,0.000359615],"domain_scores_gemma":[0.9980198,0.0002999209,0.0003878965,0.0004855821,0.0005193023,0.000287477],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002015255,0.001117674,0.6963196,0.0003342514,0.002911296,0.0006891133,0.001291747,0.0008173217,0.282522,0.00000873097,0.0001005894,0.01368609],"study_design_scores_gemma":[0.002759508,0.000246217,0.2231193,0.0003207964,0.004279692,0.00001902964,0.002500586,0.7545711,0.01163667,0.000007685605,0.0001941298,0.000345293],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9698498,0.0005825558,0.02686452,0.001629845,0.00003974192,0.000245082,0.000008496429,0.00005349375,0.0007265061],"genre_scores_gemma":[0.9829376,0.00009675542,0.01500787,0.00007775736,0.00004294194,0.00001549304,0.0002345483,0.00002351554,0.001563492],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7537538,"threshold_uncertainty_score":0.9995117,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01497967206527752,"score_gpt":0.3393255286006531,"score_spread":0.3243458565353756,"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."}}