{"id":"W4404163952","doi":"10.1038/s41598-024-77582-5","title":"Deep learning for 3D vascular segmentation in hierarchical phase contrast tomography: a case study on kidney","year":2024,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Common Fund; National Institute of Diabetes and Digestive and Kidney Diseases; Canadian Institute for Advanced Research; Bundesministerium für Gesundheit; NIH Office of the Director; National Cancer Institute; Royal Academy of Engineering; National Institutes of Health; Bundesministerium für Bildung und Forschung; European Synchrotron Radiation Facility; Wellcome Trust; Medical Research Council; Silicon Valley Community Foundation","keywords":"Contrast (vision); Phase contrast microscopy; Segmentation; Computer science; Computed tomography; Tomography; Artificial intelligence; Kidney; Radiology; Medicine; Internal medicine; Physics","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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.003370495,0.0001636972,0.0001935559,0.0007300308,0.0002745461,0.001082609,0.0002221274,0.0000509003,0.00003858672],"category_scores_gemma":[0.0004331116,0.0001462562,0.0001226035,0.001265363,0.0001330227,0.0005770428,0.00008918679,0.000273867,0.000007983904],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008648704,"about_ca_system_score_gemma":0.0001677916,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004411531,"about_ca_topic_score_gemma":0.00001766823,"domain_scores_codex":[0.9969317,0.000213121,0.0006202236,0.00113943,0.0007603955,0.0003351077],"domain_scores_gemma":[0.9987296,0.0001754805,0.0001182586,0.0006100867,0.0001045442,0.0002619826],"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":[0.00002266534,0.002152152,0.002106115,0.0001745661,0.0001149046,0.07118984,0.01538673,0.0002188891,0.02846792,0.0003530676,0.006540408,0.8732727],"study_design_scores_gemma":[0.005195218,0.003461186,0.0004058227,0.0007044057,0.0001559313,0.007503281,0.005764992,0.8531402,0.09094816,0.01351177,0.01780629,0.001402743],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1377962,0.00008387334,0.8577914,0.0001189037,0.002279225,0.001434011,9.217227e-7,0.0004200783,0.00007537803],"genre_scores_gemma":[0.9141409,0.000001997051,0.08484536,0.0001975148,0.00005755742,0.0004922256,0.00004593343,0.0000183581,0.0002001768],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.87187,"threshold_uncertainty_score":0.9999543,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01971920979423411,"score_gpt":0.3348917664889597,"score_spread":0.3151725566947256,"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."}}