{"id":"W4402963270","doi":"10.48550/arxiv.2407.18555","title":"How to Segment in 3D Using 2D Models: Automated 3D Segmentation of Prostate Cancer Metastatic Lesions on PET Volumes Using Multi-angle Maximum Intensity Projections and Diffusion Models","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Canadian Institutes of Health Research","keywords":"Prostate cancer; Segmentation; Intensity (physics); Diffusion; 3d model; Prostate; Medicine; Nuclear medicine; Computer science; Biomedical engineering; Artificial intelligence; Cancer; Physics; Optics; Internal medicine","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":[0.001027374,0.001156621,0.001034435,0.00148759,0.0005336577,0.002503562,0.0009925975,0.002537045,0.001182657],"category_scores_gemma":[0.002538491,0.001235584,0.002014364,0.0009797105,0.0008117635,0.001561014,0.001081404,0.001190109,0.001344906],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007083933,"about_ca_system_score_gemma":0.001503123,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005498709,"about_ca_topic_score_gemma":0.008427951,"domain_scores_codex":[0.9993997,0.0001267767,0.00003993183,0.0001655556,0.0002157659,0.00005235153],"domain_scores_gemma":[0.9994248,0.0002182886,0.00008751863,0.0001207242,0.0001125492,0.00003600678],"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":[0.0002350228,0.0001134823,0.003185714,0.0005108995,0.0002429733,0.0005110591,0.0006478034,0.39912,0.1051294,0.0114783,0.007522248,0.471303],"study_design_scores_gemma":[0.00001297859,0.00003522784,0.0006717525,0.00004451666,0.00003735182,0.0003834139,0.00007424444,0.9619425,0.02191999,0.008960146,0.005860717,0.00005702832],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01017492,0.0004573092,0.9870055,0.0003685225,0.0000405771,0.00005420342,0.0001331205,0.001294915,0.000470988],"genre_scores_gemma":[0.1263269,0.001375991,0.8690264,0.0002764848,0.00005527477,0.0001290996,0.0006946556,0.0007883736,0.001326954],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005498709,"threshold_uncertainty_score":0.0109334,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1088348815255766,"score_gpt":0.2831537181547549,"score_spread":0.1743188366291783,"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."}}