{"id":"W2987112586","doi":"10.1101/845537","title":"Unsupervised domain adaptation for the automated segmentation of neuroanatomy in MRI: a deep learning approach","year":2019,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Montreal Neurological Institute and Hospital; McGill University","funders":"Fonds de Recherche du Québec - Santé; Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Segmentation; Artificial intelligence; Convolutional neural network; Generalizability theory; Domain adaptation; Domain (mathematical analysis); Pattern recognition (psychology); Neuroanatomy; Context (archaeology); Machine learning; Deep learning; Artificial neural network; Classifier (UML); Neuroscience","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001615297,0.000424482,0.0005058298,0.0004746852,0.0002168004,0.0003378066,0.001223517,0.0003191087,0.000005251186],"category_scores_gemma":[0.0002550636,0.0003981916,0.0001754652,0.001053999,0.00008326021,0.0004163827,0.0004135267,0.00077556,0.0000138593],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002008739,"about_ca_system_score_gemma":0.0004231039,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005170965,"about_ca_topic_score_gemma":0.000003072289,"domain_scores_codex":[0.9967405,0.0004939843,0.0007649062,0.0009622931,0.0005603289,0.0004779582],"domain_scores_gemma":[0.997229,0.0004293962,0.0007706939,0.001010618,0.000454601,0.0001057086],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001051313,0.0003047057,0.006484463,0.001078354,0.0002271892,0.0000124668,0.001796641,0.8727743,0.1035025,0.0134851,0.00005455597,0.0001745849],"study_design_scores_gemma":[0.00119108,0.00006051139,0.04519415,0.0001254526,0.00003321987,2.163414e-8,0.0001255427,0.9490123,0.003158509,0.000009724021,0.000682021,0.0004074327],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1079176,0.0005738391,0.888115,0.0002110874,0.0006333499,0.001880847,0.00001206242,0.0006359616,0.0000202793],"genre_scores_gemma":[0.8321853,0.00008654664,0.1670694,0.0001226146,0.00005901872,0.0004069445,0.000001391601,0.00006464651,0.000004215393],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7242677,"threshold_uncertainty_score":0.999847,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01795582615409673,"score_gpt":0.2317597577152414,"score_spread":0.2138039315611447,"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."}}