{"id":"W3204235424","doi":"10.1007/978-3-030-87193-2_29","title":"Context-Aware Virtual Adversarial Training for Anatomically-Plausible Segmentation","year":2021,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Medical Imaging and Analysis","field":"Engineering","cited_by":9,"is_retracted":false,"has_abstract":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Computer science; Adversarial system; Segmentation; Artificial intelligence; Context (archaeology); Differentiable function; Constraint (computer-aided design); Deep neural networks; Function (biology); Artificial neural network; Machine learning; Pattern recognition (psychology); Mathematics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002937649,0.000255077,0.00038689,0.0002794619,0.00009933096,0.000139522,0.0003627515,0.0001860201,0.0001058055],"category_scores_gemma":[0.00008314744,0.000250663,0.0001265252,0.0001940306,0.0002119899,0.000128355,0.00007784549,0.0004016293,0.000006473473],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001737227,"about_ca_system_score_gemma":0.0001962892,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007559277,"about_ca_topic_score_gemma":0.00004936984,"domain_scores_codex":[0.9984515,0.000009212057,0.0003042949,0.0005039705,0.0004003019,0.0003306703],"domain_scores_gemma":[0.9992079,0.0003173856,0.00005652758,0.0002048509,0.00009270725,0.0001206134],"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":[0.000002899647,0.00000483142,0.0000132545,0.00004476383,0.00004042808,0.00001751498,0.0005578816,0.1618958,0.0006834301,0.0008265694,0.00007858367,0.835834],"study_design_scores_gemma":[0.0003926519,0.00003066446,0.000004247295,0.0002966163,0.00003495969,0.000008342891,0.000004293431,0.9927624,0.001900824,0.002865361,0.00138139,0.0003181823],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0004048889,0.0001911836,0.9973294,0.000163098,0.001208609,0.0001461458,0.00001838273,0.0001116759,0.0004266406],"genre_scores_gemma":[0.8012801,0.00005876786,0.1943425,0.001546372,0.001832454,0.00002311983,0.0001588072,0.00009039877,0.0006674473],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8355159,"threshold_uncertainty_score":0.9999946,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02042330283874575,"score_gpt":0.2515569942591869,"score_spread":0.2311336914204412,"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."}}