{"id":"W4401938832","doi":"10.1101/2024.08.25.609595","title":"Vasculature segmentation in 3D hierarchical phase-contrast tomography images of human kidneys","year":2024,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute of Diabetes and Digestive and Kidney Diseases; NIH Office of the Director; National Institutes of Health; Common Fund; Royal Academy of Engineering; European Synchrotron Radiation Facility; National Institute of Neurological Disorders and Stroke; National Institute of Mental Health; Medical Research Council; Canadian Institute for Advanced Research; Silicon Valley Community Foundation","keywords":"Phase contrast microscopy; Contrast (vision); Segmentation; Computed tomography; Tomography; Artificial intelligence; Computer vision; Computer science; Radiology; Medicine; Physics; Optics","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":[0.001990784,0.0007551847,0.0006569195,0.002375512,0.0005390728,0.001639061,0.0007785747,0.001906219,0.001326544],"category_scores_gemma":[0.004989305,0.0007540175,0.0009829885,0.001635023,0.0006263953,0.001081847,0.001002929,0.0008248102,0.0008304359],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000717999,"about_ca_system_score_gemma":0.001333691,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003715349,"about_ca_topic_score_gemma":0.009275849,"domain_scores_codex":[0.999092,0.0002378918,0.00005158494,0.0002212981,0.0002875959,0.0001096166],"domain_scores_gemma":[0.9985695,0.0006533155,0.0001663627,0.0002376666,0.0002883846,0.00008469544],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0008732171,0.0002741031,0.01387134,0.0009061491,0.0003282454,0.0007725901,0.0005958907,0.2235614,0.3457006,0.009446015,0.01328036,0.39039],"study_design_scores_gemma":[0.00005265967,0.0001847118,0.02062227,0.00009911425,0.0001011026,0.0013965,0.0002458957,0.7601464,0.1914293,0.01470322,0.0109235,0.000095391],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3058477,0.00188297,0.6811602,0.001147827,0.0000930446,0.0002153983,0.001795352,0.004568311,0.003289184],"genre_scores_gemma":[0.4051607,0.001141982,0.5862102,0.0002826125,0.00006646591,0.0001152273,0.003805752,0.0009162722,0.00230082],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003715349,"threshold_uncertainty_score":0.01052839,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01094446270577964,"score_gpt":0.269280079755584,"score_spread":0.2583356170498043,"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."}}