{"id":"W2054516549","doi":"10.1155/2013/980769","title":"Automatic Segmentation of Lung Carcinoma Using 3D Texture Features in 18-FDG PET/CT","year":2013,"lang":"en","type":"article","venue":"International Journal of Molecular Imaging","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":36,"is_retracted":false,"has_abstract":true,"ca_institutions":"Princess Margaret Cancer Centre; Sunnybrook Health Science Centre; Health Sciences Centre; McGill University","funders":"","keywords":"Artificial intelligence; Voxel; Segmentation; Ground truth; Positron emission tomography; Thresholding; Pattern recognition (psychology); Medicine; Hounsfield scale; Sørensen–Dice coefficient; Nuclear medicine; Computer science; Image segmentation; Radiology; Computed tomography; Image (mathematics)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001000717,0.0003050286,0.0005434567,0.002728646,0.0003019837,0.001074561,0.0003643463,0.0007064783,0.0003396225],"category_scores_gemma":[0.003054878,0.0004381342,0.0006474383,0.0008900342,0.0003925373,0.0004787621,0.000461937,0.0002193228,0.0003158844],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006090762,"about_ca_system_score_gemma":0.0004434908,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004676471,"about_ca_topic_score_gemma":0.005696514,"domain_scores_codex":[0.999268,0.0002126305,0.00005754589,0.0001134299,0.0002915846,0.00005676182],"domain_scores_gemma":[0.9993988,0.0003102594,0.00008370236,0.00006532637,0.0001168464,0.00002492987],"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":[0.001263603,0.000166391,0.06919766,0.0002617111,0.0001357611,0.0008009817,0.0004408821,0.1547104,0.3358317,0.0009867909,0.0007321182,0.435472],"study_design_scores_gemma":[0.00004477032,0.0002012561,0.07741743,0.0000336676,0.000059882,0.001209776,0.0001571383,0.8622912,0.05594603,0.001589989,0.0009714305,0.00007749381],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7605239,0.0006959541,0.2371037,0.00008250331,0.00001839348,0.0001585086,0.0002257739,0.0005083592,0.0006829066],"genre_scores_gemma":[0.8987268,0.0002059269,0.100412,0.00003248599,0.00001041815,0.00005834755,0.0002183326,0.00005777314,0.0002780062],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004676471,"threshold_uncertainty_score":0.009298503,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005692390877067885,"score_gpt":0.305973318859074,"score_spread":0.3002809279820061,"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."}}