{"id":"W4387211564","doi":"10.1007/978-3-031-43901-8_43","title":"MDViT: Multi-domain Vision Transformer for Small Medical Image Segmentation Datasets","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"AI in cancer detection","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":false,"ca_institutions":"Simon Fraser University; University of British Columbia","funders":"","keywords":"Computer science; Segmentation; Artificial intelligence; Inference; Convolutional neural network; Machine learning; Transfer of learning; Transformer; Domain (mathematical analysis); Pattern recognition (psychology); Image segmentation; Data mining","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":[0.00199803,0.0005483803,0.000490476,0.0008348922,0.0003752335,0.0005055816,0.003015321,0.0004993851,0.0000287222],"category_scores_gemma":[0.0001442866,0.0005143919,0.0001811926,0.0007010262,0.00061869,0.001237537,0.0006154589,0.0007691121,0.00008665174],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005271811,"about_ca_system_score_gemma":0.0007137958,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004298897,"about_ca_topic_score_gemma":0.0006794644,"domain_scores_codex":[0.9950277,0.00004969241,0.0006914565,0.001915745,0.001552121,0.0007632668],"domain_scores_gemma":[0.9974267,0.0007598788,0.000273386,0.001067308,0.0001986909,0.000274048],"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":[0.00002032485,0.00003911521,0.000004436683,0.0001205075,0.00001638413,0.00007174732,0.0005357378,0.001750899,0.001476654,0.002518887,0.0002101365,0.9932352],"study_design_scores_gemma":[0.001504024,0.000538604,0.00008050152,0.0007102991,0.00001820473,0.00009873728,7.298761e-7,0.9009089,0.009092381,0.08064355,0.005373369,0.00103067],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00002038059,0.00009296737,0.9923527,0.002220303,0.003586917,0.001086684,0.0001242705,0.0003422568,0.0001735636],"genre_scores_gemma":[0.001451944,0.0001071252,0.9951642,0.001983353,0.000674292,0.00009830498,0.0001723552,0.0000871938,0.0002612694],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9922045,"threshold_uncertainty_score":0.9997308,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02643911004692714,"score_gpt":0.3025782687703767,"score_spread":0.2761391587234495,"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."}}