{"id":"W2801475611","doi":"10.1016/j.compmedimag.2018.04.005","title":"Retinal blood vessel segmentation using fully convolutional network with transfer learning","year":2018,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":224,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada; University of Saskatchewan","keywords":"Computer science; Segmentation; Artificial intelligence; Robustness (evolution); Transfer of learning; Retinal; Deep learning; Pattern recognition (psychology); Computer vision; Image segmentation; Convolutional neural network; Medical imaging; Computer-aided diagnosis; Medicine; Ophthalmology","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0005927348,0.0008940737,0.0008376597,0.001154442,0.000438966,0.0008325259,0.001317889,0.0014083,0.002293329],"category_scores_gemma":[0.0008514236,0.000705039,0.001035504,0.0008029929,0.000316246,0.0009844032,0.00098923,0.001081291,0.001036145],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008888282,"about_ca_system_score_gemma":0.001560492,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01327422,"about_ca_topic_score_gemma":0.01591791,"domain_scores_codex":[0.999763,0.00002565297,0.00001163644,0.00008662414,0.00005903136,0.00005406452],"domain_scores_gemma":[0.9996814,0.00008532903,0.00003299168,0.00006266246,0.0001087371,0.00002894973],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003482146,0.0002279074,0.002411814,0.0001326887,0.0002070577,0.0001755966,0.00008239983,0.1652017,0.03979235,0.003263813,0.006494855,0.7816616],"study_design_scores_gemma":[0.000005541231,0.00002649234,0.0005321451,0.000007019363,0.00002264319,0.00004234094,0.000005330149,0.9899859,0.007506568,0.001260485,0.0005975217,0.000007916778],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0550226,0.0007042999,0.9362892,0.000315849,0.0000863942,0.00008508837,0.0002943621,0.004616008,0.002586241],"genre_scores_gemma":[0.5627583,0.0007250685,0.4232326,0.0002910246,0.0001011156,0.0001440066,0.001343822,0.000368562,0.01103544],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01327422,"threshold_uncertainty_score":0.02639389,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01190647296337326,"score_gpt":0.2724129232104857,"score_spread":0.2605064502471124,"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."}}