{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001388651,0.0007357961,0.000876856,0.001794409,0.0005048826,0.0009428737,0.0008813012,0.001136678,0.0008553251],"category_scores_gemma":[0.002211973,0.0003662591,0.001045282,0.0009431913,0.0003489399,0.0009367084,0.001176674,0.0006343434,0.0003916654],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004008044,"about_ca_system_score_gemma":0.0006614361,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004818322,"about_ca_topic_score_gemma":0.006616195,"domain_scores_codex":[0.9994142,0.0001176623,0.00003284522,0.0001930658,0.0001707007,0.00007149509],"domain_scores_gemma":[0.9988922,0.0003935373,0.000140303,0.0001415899,0.0003504173,0.00008192093],"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":[0.0006324787,0.0006185219,0.01273377,0.000294705,0.0004416608,0.0003046062,0.0003745191,0.276293,0.09604669,0.001807611,0.002879675,0.6075727],"study_design_scores_gemma":[0.000007037444,0.00005604908,0.002774263,0.0000064489,0.00004915911,0.00007119452,0.00002442597,0.9855016,0.01013367,0.001073594,0.0002855881,0.00001682777],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09981309,0.0003549778,0.89767,0.0001049779,0.00004522044,0.00006261142,0.0001201524,0.0007427891,0.001086125],"genre_scores_gemma":[0.7169607,0.0002062552,0.280234,0.00009242163,0.00007975879,0.00009387205,0.0002942236,0.0001142819,0.001924548],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004818322,"threshold_uncertainty_score":0.009580553,"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."}}