{"id":"W4410348173","doi":"10.1111/jmi.13419","title":"Development of a deep learning method for phase retrieval image enhancement in phase contrast microcomputed tomography","year":2025,"lang":"en","type":"article","venue":"Journal of Microscopy","topic":"Advanced X-ray Imaging Techniques","field":"Physics and Astronomy","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Light Source (Canada); University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada; National Research Council","keywords":"Convolutional neural network; Contrast (vision); Artificial intelligence; Computer science; Contrast-to-noise ratio; Smoothing; Deep learning; Computer vision; Noise (video); Pattern recognition (psychology); Signal-to-noise ratio (imaging); Phase (matter); Materials science; Image quality; Image (mathematics); Physics; Telecommunications","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007568615,0.0001730404,0.0004840296,0.0003886739,0.00007686969,0.00003854056,0.0002277021,0.00003373318,0.00003254019],"category_scores_gemma":[0.00002453724,0.0001678437,0.0001824597,0.0003402405,0.00004606045,0.0001812845,0.00004873073,0.0003037681,3.970227e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008184174,"about_ca_system_score_gemma":0.0001656052,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003780401,"about_ca_topic_score_gemma":7.153458e-7,"domain_scores_codex":[0.9984603,0.00006434578,0.000930601,0.00016799,0.0001225153,0.0002542446],"domain_scores_gemma":[0.9986809,0.0001436348,0.0007004734,0.0001057312,0.0003169677,0.00005228799],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0007573263,0.0008384871,0.0002955552,0.00004545931,0.0001354548,0.000002118171,0.0005858814,0.00002056068,0.8984192,0.000100494,0.0001466126,0.09865288],"study_design_scores_gemma":[0.007616136,0.0002910792,0.00003175778,0.0003144537,0.00004761686,0.000001610779,0.0004213949,0.001105511,0.9805153,0.0009496749,0.008572659,0.0001328128],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2815969,0.000198693,0.7177376,0.00004638773,0.00007846623,0.0002664352,0.00000713868,0.000008942396,0.00005946942],"genre_scores_gemma":[0.2477537,0.000004800592,0.7521133,0.00002936523,0.00004196633,0.000009336431,0.000009623728,0.00001217766,0.00002575226],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.09852006,"threshold_uncertainty_score":0.6844466,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008735570120578035,"score_gpt":0.3772564751348345,"score_spread":0.3685209050142564,"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."}}