{"id":"W4416965864","doi":"10.1109/access.2025.3639971","title":"ISMDNet: Multi-Material Decomposition Using Deep Learning and Inverse Transform Sampling in Spectral Photon Counting CT","year":2025,"lang":"en","type":"article","venue":"IEEE Access","topic":"Advanced X-ray and CT Imaging","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Khalifa University of Science, Technology and Research; Terry Fox Foundation","keywords":"Deep learning; Imaging phantom; Pattern recognition (psychology); Sampling (signal processing); Energy (signal processing); Iterative reconstruction; Singular value decomposition; Attenuation","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":[0.0005354071,0.0007279668,0.0004219114,0.0006039056,0.000182288,0.0005611735,0.001136214,0.0007625558,0.001237852],"category_scores_gemma":[0.001123708,0.0003255199,0.0005416596,0.0004280132,0.0003373126,0.0008205809,0.0009269296,0.001024908,0.0004207084],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007214758,"about_ca_system_score_gemma":0.0009423206,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004674012,"about_ca_topic_score_gemma":0.007353163,"domain_scores_codex":[0.9998678,0.00002540249,0.000006735516,0.00003468322,0.00004807351,0.00001722729],"domain_scores_gemma":[0.9998237,0.00007252792,0.00002222071,0.00002039907,0.00004567622,0.00001558462],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002048746,0.0001501809,0.002305948,0.000190531,0.00009026634,0.0002162036,0.00006321156,0.6294064,0.02021005,0.00574653,0.006078898,0.335337],"study_design_scores_gemma":[0.000005972958,0.00002022577,0.0001201723,0.000006013303,0.000005505654,0.00003090591,0.000004956069,0.9943119,0.003604684,0.001098673,0.0007867247,0.000004323255],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04498109,0.0007509471,0.948826,0.0003119247,0.00007014709,0.00007872196,0.0003927343,0.002540123,0.002048309],"genre_scores_gemma":[0.4756024,0.0005778435,0.5151968,0.0004773334,0.00003910013,0.0001733201,0.001980021,0.0002911722,0.005662038],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004674012,"threshold_uncertainty_score":0.009293616,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01885710239122024,"score_gpt":0.3207657690072034,"score_spread":0.3019086666159831,"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."}}