{"id":"W2530895041","doi":"10.1049/htl.2016.0067","title":"High‐frequency‐based features for low and high retina haemorrhage classification","year":2016,"lang":"en","type":"article","venue":"Healthcare Technology Letters","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure; Concordia University","funders":"","keywords":"Artificial intelligence; Grading (engineering); Hilbert–Huang transform; Pattern recognition (psychology); Fundus (uterus); Discrete wavelet transform; Computer science; Support vector machine; Blindness; Retinal; Diabetic retinopathy; Wavelet; Computer vision; Wavelet transform; Ophthalmology; Medicine; Optometry; Engineering","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":[0.0001846921,0.0001676041,0.0003433685,0.0004185291,0.0001338677,0.00001077014,0.0001064783,0.0002391262,0.00001033228],"category_scores_gemma":[0.000240143,0.0001149193,0.00007224923,0.0003034818,0.0003567779,0.00004440983,0.00001712418,0.0002335131,0.00001095807],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001223053,"about_ca_system_score_gemma":0.00005756414,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002178687,"about_ca_topic_score_gemma":0.00002802658,"domain_scores_codex":[0.9987618,0.00003991643,0.0002546887,0.0004491095,0.0001363924,0.0003581374],"domain_scores_gemma":[0.9990454,0.000108478,0.0001369582,0.0004740696,0.0001337854,0.0001013587],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0002782616,0.00008900535,0.1499115,0.001036632,0.0001033976,0.0001749575,0.00003931143,5.669324e-7,0.6429853,0.01521053,0.009596602,0.1805739],"study_design_scores_gemma":[0.01379696,0.002208152,0.6658376,0.004649554,0.001094359,0.001068876,0.0006056835,0.0009939285,0.282613,0.01725036,0.008128318,0.001753262],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.4936163,0.0002321752,0.004600203,0.5009521,0.0000653185,0.0002426226,0.00001954222,0.0002648226,0.00000697236],"genre_scores_gemma":[0.9716999,0.00007144093,0.01707183,0.01070291,0.0001059225,0.0001201503,0.00004886055,0.00002797329,0.000150988],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5159261,"threshold_uncertainty_score":0.4686273,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01587260140492673,"score_gpt":0.2890002653944023,"score_spread":0.2731276639894755,"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."}}