{"id":"W98693656","doi":"10.1007/978-3-319-10581-9_15","title":"Deep Learning of Image Features from Unlabeled Data for Multiple Sclerosis Lesion Segmentation","year":2014,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Image Processing Techniques and Applications","field":"Engineering","cited_by":57,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Artificial intelligence; Computer science; Pattern recognition (psychology); Segmentation; Classifier (UML); Semi-supervised learning; Supervised learning; Image segmentation; Deep learning; Labeled data; Training set; Machine learning; Artificial neural network","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":[0.0002405452,0.0002000431,0.0002345745,0.0001642409,0.0001205512,0.0001107926,0.0008630696,0.0001457796,0.000005511191],"category_scores_gemma":[0.00007697313,0.0001944411,0.00003581755,0.0001172173,0.0001604922,0.0001682906,0.0002666795,0.0002884531,0.000002084039],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006213018,"about_ca_system_score_gemma":0.0000275211,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002322149,"about_ca_topic_score_gemma":0.00003238934,"domain_scores_codex":[0.998894,0.000006557216,0.0002377243,0.0004745267,0.0002066198,0.0001805872],"domain_scores_gemma":[0.9988555,0.0003037996,0.0001189977,0.0005849069,0.0001044508,0.00003233734],"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":[0.000003787,0.000005251078,0.00001016061,0.00009456065,0.0000063639,2.519594e-7,0.0001240852,0.04810971,0.0607516,0.000106888,0.0000603193,0.890727],"study_design_scores_gemma":[0.0001630589,0.00002629764,0.00007755154,0.0003236294,0.00001537104,8.036799e-7,2.291863e-7,0.9320391,0.05914966,0.007538071,0.0004574501,0.000208738],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001256332,0.0003918944,0.9986358,0.00004466975,0.0001341297,0.0003032146,0.00004501047,0.00018428,0.0001353122],"genre_scores_gemma":[0.1645239,0.00009364606,0.8348505,0.00004825335,0.0001226836,0.00001687228,0.0002789753,0.00003698378,0.00002814028],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8905183,"threshold_uncertainty_score":0.7929077,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03448078388453218,"score_gpt":0.2677185207841131,"score_spread":0.2332377368995809,"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."}}