{"id":"W2908300307","doi":"10.1109/tmi.2018.2859478","title":"Transfer Learning for Image Segmentation by Combining Image Weighting and Kernel Learning","year":2018,"lang":"en","type":"article","venue":"IEEE Transactions on Medical Imaging","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":97,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Canadian Institutes of Health Research; National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Servier; Eisai; Northern California Institute for Research and Education; F. Hoffmann-La Roche; Nederlandse Organisatie voor Wetenschappelijk Onderzoek; University of Southern California; Biogen; Eli Lilly and Company; Bristol-Myers Squibb; University of California, San Diego; BioClinica; U.S. Department of Defense; Meso Scale Diagnostics; Alzheimer's Disease Neuroimaging Initiative; Novartis Pharmaceuticals Corporation; Pfizer; Alzheimer's Association","keywords":"Artificial intelligence; Kernel (algebra); Computer science; Image segmentation; Weighting; Pattern recognition (psychology); Image (mathematics); Computer vision; Segmentation; Segmentation-based object categorization; Scale-space segmentation; Image texture; Mathematics; Medicine","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002408412,0.0009218349,0.001293694,0.001596222,0.0003276936,0.0008217056,0.001507343,0.001331328,0.001159402],"category_scores_gemma":[0.006316328,0.000512873,0.000987582,0.001614188,0.001051051,0.00237246,0.001842583,0.001297496,0.0007054833],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009545307,"about_ca_system_score_gemma":0.0008982903,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002846514,"about_ca_topic_score_gemma":0.00215196,"domain_scores_codex":[0.9991751,0.0002414949,0.00006030104,0.0002021805,0.0002512316,0.00006968649],"domain_scores_gemma":[0.998456,0.0006832147,0.0001589829,0.0003091675,0.0003348527,0.00005782031],"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":[0.0002082498,0.0002255955,0.001404372,0.0001559164,0.0002015848,0.00009649895,0.0001500735,0.4003149,0.03432358,0.01033247,0.001877419,0.5507094],"study_design_scores_gemma":[0.000006618165,0.000039439,0.0002090824,0.000003232543,0.000009890253,0.00002741074,0.000007639374,0.9884885,0.004286535,0.006566362,0.0003455445,0.000009822341],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01000723,0.0001362396,0.9888374,0.00006720986,0.00001197721,0.00003337518,0.0000149236,0.0006472969,0.0002443636],"genre_scores_gemma":[0.4006151,0.0003010298,0.5961179,0.0001822456,0.0000679523,0.0002061417,0.0002869568,0.000320123,0.001902611],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002846514,"threshold_uncertainty_score":0.0127371,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01077902215612788,"score_gpt":0.2725020064135906,"score_spread":0.2617229842574627,"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."}}