{"id":"W2980604726","doi":"10.1109/ispa.2019.8868639","title":"Transfer Learning with U-Net type model for Automatic Segmentation of Three Retinal Layers In Optical Coherence Tomography Images","year":2019,"lang":"en","type":"article","venue":"","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Optical coherence tomography; Segmentation; Artificial intelligence; Encoder; Deep learning; Pattern recognition (psychology); Image segmentation; Layer (electronics); Computer vision; Ophthalmology","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":[0.0008060671,0.001200353,0.000779762,0.0006997869,0.000328547,0.0007930105,0.001596819,0.001778708,0.001696646],"category_scores_gemma":[0.001384404,0.0004252801,0.001068329,0.0004814652,0.0005034848,0.0008829504,0.0005977859,0.001349824,0.0005338528],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001223896,"about_ca_system_score_gemma":0.001146634,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01777018,"about_ca_topic_score_gemma":0.01608667,"domain_scores_codex":[0.999751,0.00004648227,0.00001623436,0.00009188037,0.00004121031,0.00005315919],"domain_scores_gemma":[0.9996763,0.000138001,0.00003767415,0.00002843463,0.0001015759,0.00001805947],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0004740601,0.000302803,0.003262362,0.000124697,0.0001530799,0.0002627568,0.00009344461,0.8127674,0.007334695,0.002301385,0.004366049,0.1685573],"study_design_scores_gemma":[0.000005730505,0.00005436123,0.0002444957,0.000008156304,0.00001158677,0.00002187648,0.000005997494,0.9972241,0.001735158,0.0004972209,0.0001861632,0.000005167018],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2971022,0.004155271,0.6811266,0.001105154,0.000401618,0.0003528854,0.0009511664,0.007047686,0.007757525],"genre_scores_gemma":[0.8937426,0.0007253882,0.09506848,0.0005111076,0.00007129661,0.0002873552,0.001231433,0.0001440723,0.008218212],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01777018,"threshold_uncertainty_score":0.03533345,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01631057906659335,"score_gpt":0.2778237198517505,"score_spread":0.2615131407851571,"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."}}