{"id":"W3036488719","doi":"10.1007/978-3-030-50516-5_31","title":"Deep Retinal Diseases Detection and Explainability Using OCT Images","year":2020,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":21,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Moncton","funders":"","keywords":"Computer science; Optical coherence tomography; Drusen; Convolutional neural network; Blindness; Retinal; Computer-aided diagnosis; Artificial intelligence; CAD; Retinal Disorder; Ophthalmology; Deep learning; Pattern recognition (psychology); Computer vision; Optometry; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002315129,0.0002701095,0.0004471714,0.0002999807,0.0001768269,0.0001343711,0.0001771777,0.00009902044,0.00001534944],"category_scores_gemma":[0.0002955562,0.0002260512,0.0001191329,0.0002647917,0.0007934949,0.0001271097,0.0002015767,0.0004709724,0.000003197764],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001723722,"about_ca_system_score_gemma":0.000146797,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003709635,"about_ca_topic_score_gemma":0.000009251823,"domain_scores_codex":[0.9981893,0.00002522403,0.0002545934,0.0008419814,0.0004463771,0.0002424736],"domain_scores_gemma":[0.9990201,0.0001519461,0.0001222384,0.0003510691,0.0001572401,0.0001974278],"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":[0.0001533168,0.00004863635,0.01289374,0.0005590543,0.0000529052,0.0005507102,0.0004774489,0.004776596,0.006830962,0.00008484926,0.000004777996,0.973567],"study_design_scores_gemma":[0.0004466395,0.000397171,0.008118207,0.0009158599,0.0003956552,0.0004808246,0.000002247502,0.9616461,0.004593529,0.02221221,0.000193304,0.000598203],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006832391,0.001099763,0.9903634,0.0009163161,0.0001682043,0.0001802335,0.000002998273,0.00006381214,0.0003728966],"genre_scores_gemma":[0.9564189,0.00004057776,0.04243227,0.0005762742,0.0004607642,0.000001692613,0.000003576022,0.0000206646,0.000045328],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9729688,"threshold_uncertainty_score":0.9218099,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01575746507621066,"score_gpt":0.2712025578238605,"score_spread":0.2554450927476498,"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."}}