{"id":"W3112577772","doi":"","title":"Longitudinal assessments of retinal degeneration after excitotoxic injury using an end-to-end pipeline with deep learning-based automatic layer segmentation","year":2020,"lang":"en","type":"article","venue":"Investigative Ophthalmology & Visual Science","topic":"Retinal and Optic Conditions","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia; Simon Fraser University","funders":"","keywords":"Pipeline (software); Segmentation; Degeneration (medical); Ophthalmology; End-to-end principle; Retinal degeneration; Layer (electronics); Medicine; Artificial intelligence; Retinal; Computer science; Chemistry","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":[0.0009439974,0.000593084,0.000573254,0.0008467081,0.0003619876,0.0007146435,0.0004580735,0.0005607517,0.001935209],"category_scores_gemma":[0.00108573,0.0003283563,0.0004984411,0.0003808856,0.0001808664,0.0004477734,0.0006248552,0.0007493465,0.0007206433],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004153932,"about_ca_system_score_gemma":0.0007307659,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005140584,"about_ca_topic_score_gemma":0.01265352,"domain_scores_codex":[0.999792,0.00002351573,0.00001564509,0.0000809257,0.00005447741,0.00003340169],"domain_scores_gemma":[0.9993314,0.00008297334,0.0001307559,0.0000883068,0.0002890919,0.00007746898],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.004929591,0.00160389,0.2470774,0.0006644272,0.001267233,0.001113196,0.0006224399,0.04828281,0.3046769,0.0009070918,0.009394186,0.3794608],"study_design_scores_gemma":[0.0001179121,0.003567575,0.5195988,0.0002366652,0.0008989379,0.0023403,0.0003722938,0.2808495,0.1813789,0.003975578,0.006426595,0.0002369948],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8780168,0.001515764,0.1082007,0.0002488118,0.0000872376,0.0002450955,0.007603555,0.002397782,0.00168435],"genre_scores_gemma":[0.9307305,0.0006464383,0.05809143,0.000104095,0.00002787963,0.0002595959,0.006138411,0.0002330911,0.00376861],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005140584,"threshold_uncertainty_score":0.0102213,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06860806161487956,"score_gpt":0.3875511870777527,"score_spread":0.3189431254628732,"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."}}