{"id":"W4387642557","doi":"10.1007/978-3-031-45673-2_25","title":"Leveraging Self-attention Mechanism in Vision Transformers for Unsupervised Segmentation of Optical Coherence Microscopy White Matter Images","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Cell Image Analysis Techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Computer science; Artificial intelligence; Segmentation; Ground truth; Deep learning; Unsupervised learning; Pattern recognition (psychology); Image segmentation; Computer vision","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":[0.0004412586,0.0002478491,0.0002866055,0.0003900518,0.00005159452,0.00006897386,0.000355037,0.0002389508,0.00001115209],"category_scores_gemma":[0.00001464978,0.0002471865,0.0001332106,0.0001870987,0.000175436,0.00002192893,0.0001408933,0.0001739342,0.000003704622],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007149781,"about_ca_system_score_gemma":0.00009585066,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001302065,"about_ca_topic_score_gemma":0.00004842514,"domain_scores_codex":[0.9983197,0.00001938512,0.000393548,0.0007344236,0.0002630511,0.0002698958],"domain_scores_gemma":[0.9993639,0.00004410925,0.0001317796,0.0002720189,0.0001483422,0.00003984119],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00002517627,0.00002858631,0.0006232948,0.0001149626,0.0000167423,0.000003770502,0.0001257976,0.0004863487,0.9736721,0.00001499613,0.00003379008,0.02485444],"study_design_scores_gemma":[0.0004115829,0.0002601243,0.0006027375,0.0002750313,0.00003281889,0.000005298381,0.000002603662,0.0124968,0.9813185,0.004249695,0.00002281305,0.0003219955],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01838136,0.0000500554,0.9805634,0.0001352305,0.00008790745,0.0005388838,0.000007369649,0.00002450638,0.0002113051],"genre_scores_gemma":[0.6880323,0.0001584501,0.3106643,0.0004153854,0.00009434827,0.00004467185,0.0001881651,0.00005898961,0.0003433888],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6698991,"threshold_uncertainty_score":0.999998,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00845448943267093,"score_gpt":0.2708489934243807,"score_spread":0.2623945039917098,"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."}}