{"id":"W4322491013","doi":"10.1016/j.mineng.2023.108027","title":"Processing of micro-CT images of granodiorite rock samples using convolutional neural networks (CNN), Part II: Semantic segmentation using a 2.5D CNN","year":2023,"lang":"en","type":"article","venue":"Minerals Engineering","topic":"Mineral Processing and Grinding","field":"Engineering","cited_by":24,"is_retracted":false,"has_abstract":false,"ca_institutions":"Object Research Systems (Canada)","funders":"BHP; University of Queensland","keywords":"Segmentation; Convolutional neural network; Artificial intelligence; Geology; Pattern recognition (psychology); Thresholding; Computer science; Mineralogy; 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":[0.0001754832,0.0008230692,0.0004257096,0.001320547,0.000248711,0.0007398292,0.0006121717,0.0006743615,0.003978285],"category_scores_gemma":[0.0003378609,0.000478977,0.0007521847,0.0009599124,0.0003255404,0.000448039,0.000512677,0.0005170373,0.001366672],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005315795,"about_ca_system_score_gemma":0.001037332,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01020548,"about_ca_topic_score_gemma":0.02042644,"domain_scores_codex":[0.9998645,0.000004734319,0.000007498238,0.00003213128,0.00005320468,0.00003793334],"domain_scores_gemma":[0.9998907,0.00001664689,0.0000153621,0.00001742132,0.00004910477,0.0000107676],"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":[0.0005573736,0.0001813216,0.008580117,0.0005002026,0.0001434444,0.0005386911,0.0001896685,0.06970245,0.3962502,0.001934076,0.007803664,0.5136187],"study_design_scores_gemma":[0.00002663501,0.0002054857,0.04375915,0.00008064076,0.0001151563,0.0009805195,0.0002936709,0.7095536,0.2248762,0.00315627,0.0168656,0.00008706365],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3599435,0.001270523,0.6145418,0.000559854,0.0001888789,0.0004338545,0.005815834,0.006810678,0.01043521],"genre_scores_gemma":[0.6049843,0.001114007,0.3716328,0.0002817328,0.00007004647,0.0002554441,0.009196851,0.0006138314,0.01185097],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01020548,"threshold_uncertainty_score":0.02029216,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03547706485828772,"score_gpt":0.2482560175694078,"score_spread":0.21277895271112,"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."}}