{"id":"W3090937968","doi":"10.1007/978-3-030-69541-5_41","title":"Utilizing Transfer Learning and a Customized Loss Function for Optic Disc Segmentation from Retinal Images","year":2021,"lang":"en","type":"preprint","venue":"Lecture notes in computer science","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Optic disc; Artificial intelligence; Segmentation; Computer science; Retinal; Optic cup (embryology); Computer vision; Glaucoma; Fundus (uterus); Robustness (evolution); Sørensen–Dice coefficient; Image segmentation; Pattern recognition (psychology); Ophthalmology; Medicine","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":[0.001049104,0.0006543495,0.0007097066,0.0008050956,0.0003004195,0.0009183673,0.0009817961,0.001271633,0.00132304],"category_scores_gemma":[0.001985979,0.0003689335,0.000685939,0.0007420473,0.0004533955,0.0009613429,0.00134478,0.000885793,0.0006783702],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005875365,"about_ca_system_score_gemma":0.001260072,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004705808,"about_ca_topic_score_gemma":0.003800186,"domain_scores_codex":[0.9997548,0.0000525013,0.00001746909,0.00006147795,0.00007210941,0.0000415583],"domain_scores_gemma":[0.9994938,0.000172534,0.00005120141,0.00009520078,0.0001563803,0.00003088943],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005136861,0.0001997546,0.001732625,0.0001751779,0.0001068347,0.0001519127,0.00009165592,0.2321615,0.09621204,0.004372509,0.003350202,0.6609321],"study_design_scores_gemma":[0.00000752796,0.00003696361,0.0004144573,0.000006206231,0.00001300358,0.0000579651,0.000008981882,0.9838725,0.01355146,0.001655019,0.0003687796,0.000007111815],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03709115,0.0001921831,0.9606231,0.0001676387,0.00003051973,0.00005069301,0.00007979672,0.001174623,0.0005902225],"genre_scores_gemma":[0.465134,0.0004103427,0.529272,0.0001941385,0.00009090643,0.0001352051,0.0005695972,0.0003602019,0.003833662],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004705808,"threshold_uncertainty_score":0.009356856,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01564782765400996,"score_gpt":0.2982146050625069,"score_spread":0.2825667774084969,"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."}}