{"id":"W2587791302","doi":"10.1117/12.2252988","title":"Use of Gabor filters and deep networks in the segmentation of retinal vessel morphology","year":2017,"lang":"en","type":"article","venue":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Artificial intelligence; Computer science; Softmax function; Convolutional neural network; Computer vision; Segmentation; Pattern recognition (psychology); Gabor filter; Image segmentation; Fundus (uterus); Normalization (sociology); Pixel; Feature extraction","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":[],"consensus_categories":[],"category_scores_codex":[0.0006604672,0.0001723606,0.0004164995,0.00009300709,0.00006467241,0.00006561327,0.0004677371,0.0001083093,0.000005019794],"category_scores_gemma":[0.000834245,0.0001216489,0.0003265221,0.0001545317,0.0004573946,0.0003373906,0.00009649841,0.0002499458,1.118467e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004024851,"about_ca_system_score_gemma":0.00001592021,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005395536,"about_ca_topic_score_gemma":2.623901e-7,"domain_scores_codex":[0.9985769,4.004514e-8,0.0005618595,0.0002265967,0.0004256837,0.0002088712],"domain_scores_gemma":[0.9982246,0.0001665435,0.0005827492,0.00008071912,0.0008902625,0.0000551697],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000490658,0.0002660385,0.0618795,0.001092269,0.0006886603,8.342609e-7,0.00093199,0.0004126878,0.8679528,0.06357121,0.001396419,0.001316958],"study_design_scores_gemma":[0.00588942,0.00193831,0.333515,0.002820327,0.002073986,0.0002154535,0.0105737,0.3918641,0.2482314,0.001220872,0.0009086188,0.0007487712],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9956077,0.000110045,0.00007194042,0.003529106,0.00005777888,0.0002953303,0.00001251899,0.000009994751,0.0003056374],"genre_scores_gemma":[0.9617284,0.0002865929,0.03765731,0.00009558895,0.0001195598,0.00003372008,0.000006262328,0.00002036191,0.00005220166],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6197214,"threshold_uncertainty_score":0.4960699,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01818592488172109,"score_gpt":0.2644840656858855,"score_spread":0.2462981408041644,"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."}}