{"id":"W3110887319","doi":"10.1109/icpr48806.2021.9412378","title":"Transfer Learning Through Weighted Loss Function and Group Normalization for Vessel Segmentation from Retinal Images","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Artificial intelligence; Computer science; Segmentation; Retinal; Optic disc; Normalization (sociology); Glaucoma; Computer vision; Sørensen–Dice coefficient; Pattern recognition (psychology); Deep learning; Robustness (evolution); Image segmentation; Ophthalmology; 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":[0.0001738082,0.0002283283,0.0004090329,0.00008651331,0.0001308822,0.0001534356,0.00003753941,0.0001773387,0.0002644974],"category_scores_gemma":[0.00003933086,0.0002034286,0.000178279,0.0001275433,0.00005077785,0.0002446169,0.00004319452,0.0003688328,0.000002456421],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004830294,"about_ca_system_score_gemma":0.00004232148,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007416685,"about_ca_topic_score_gemma":0.00001339062,"domain_scores_codex":[0.9986265,0.00009439657,0.0003381892,0.0005417518,0.0002414903,0.0001576979],"domain_scores_gemma":[0.9993554,0.00007551517,0.00008862596,0.0001675973,0.0002545548,0.00005828464],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.003891156,0.0009168247,0.3499277,0.005061764,0.004445569,0.0001222064,0.007881348,0.002291364,0.5415694,0.001193533,0.002873023,0.07982609],"study_design_scores_gemma":[0.0225892,0.002575969,0.2672415,0.008300398,0.03217832,0.0001937931,0.03389629,0.2611197,0.3477214,0.0118699,0.008469879,0.003843595],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3916934,0.0006333175,0.6058254,0.0009655848,0.0001229344,0.0002473801,0.00001122122,0.0000824346,0.0004182884],"genre_scores_gemma":[0.9621767,0.001199132,0.02572466,0.0004114829,0.0003597829,0.00007218626,0.008650357,0.00004051647,0.00136518],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5801008,"threshold_uncertainty_score":0.8295576,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01556008192296025,"score_gpt":0.2799625566304048,"score_spread":0.2644024747074445,"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."}}