{"id":"W3146474852","doi":"","title":"A HYBRID FEATURE SELECTION STRATEGY FOR IMAGE DEFINING FEATURES: TOWARDS INTERPRETATION OF OPTIC NERVE IMAGES","year":2005,"lang":"en","type":"article","venue":"Research Explorer (The University of Manchester)","topic":"Glaucoma and retinal disorders","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Artificial intelligence; Computer science; Optic nerve; Computer vision; Feature (linguistics); Feature selection; Feature extraction; Pattern recognition (psychology); Glaucoma; Image processing; Optic cup (embryology); Tomography; Image (mathematics); Radiology; Medicine; Anatomy","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":[0.001297556,0.0007434768,0.0008267337,0.001891008,0.0002651082,0.0009911617,0.0006347277,0.0005330688,0.0008281151],"category_scores_gemma":[0.002359443,0.0001950148,0.0007208579,0.00127314,0.0003450574,0.000648507,0.0004629741,0.0004712741,0.0004708547],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002367598,"about_ca_system_score_gemma":0.0004318923,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009996773,"about_ca_topic_score_gemma":0.0009203811,"domain_scores_codex":[0.9994358,0.0001542464,0.00004836408,0.0001135496,0.0002071991,0.00004074331],"domain_scores_gemma":[0.9990616,0.0003501096,0.00008690805,0.00009482732,0.0003698555,0.00003671271],"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":[0.0002704448,0.0001381783,0.00328902,0.0001302994,0.0001047822,0.0002042051,0.0002027795,0.01253624,0.1376483,0.002587654,0.002186315,0.8407019],"study_design_scores_gemma":[0.0001053189,0.000672712,0.02189583,0.00006192785,0.0002788149,0.001357327,0.0002949202,0.8259833,0.1288198,0.009477153,0.010943,0.0001099327],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03640675,0.0001857527,0.9621123,0.0001193931,0.00001950236,0.00007437945,0.00008721901,0.0005714911,0.0004232684],"genre_scores_gemma":[0.2559559,0.0002284768,0.7418073,0.0001126021,0.0000623641,0.0001976357,0.0003993684,0.0001209392,0.001115393],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.001891008,"threshold_uncertainty_score":0.006862164,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03438277563883097,"score_gpt":0.3113444651356508,"score_spread":0.2769616894968198,"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."}}