{"id":"W4385340330","doi":"10.1038/s41598-023-38490-2","title":"A weak-labelling and deep learning approach for in-focus object segmentation in 3D widefield microscopy","year":2023,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Image Processing Techniques and Applications","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Helmholtz-Zentrum Dresden-Rossendorf; Sächsisches Staatsministerium für Wissenschaft und Kunst; Bundesministerium für Bildung und Forschung; Freistaat Sachsen; Deutsche Forschungsgemeinschaft; Helmholtz-Gemeinschaft","keywords":"Computer science; Focus (optics); Artificial intelligence; Microscopy; Segmentation; Deep learning; Pixel; Artificial neural network; Computer vision; USable; Pattern recognition (psychology); Optics","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000718677,0.00007370603,0.00009184176,0.000231775,0.0001244061,0.0001615722,0.00004221889,0.00004591672,0.000002146756],"category_scores_gemma":[0.00003950286,0.00007973167,0.0000159519,0.0006712518,0.00003408224,0.0001150716,0.00002214342,0.0001062822,0.00000144551],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003325852,"about_ca_system_score_gemma":0.00001287501,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001800181,"about_ca_topic_score_gemma":0.00001889939,"domain_scores_codex":[0.9991691,0.000007003335,0.0002466977,0.000295726,0.00008468219,0.0001967506],"domain_scores_gemma":[0.9997424,0.00002442173,0.00004468542,0.0001424333,0.00002376897,0.00002227205],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000007179062,0.00006373797,0.01660403,0.0006449814,0.00001031996,0.00004422423,0.003973751,0.1018457,0.7484382,0.00009725105,0.002115257,0.1261553],"study_design_scores_gemma":[0.0002349484,0.00001612978,0.0006125086,0.0001149121,0.000009555122,0.00004118359,0.0006023604,0.7787353,0.2066263,0.008336799,0.004373258,0.0002966608],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5314538,0.0007438095,0.4634636,0.00004734513,0.0005270606,0.00083095,0.000001057001,0.0007055336,0.002226832],"genre_scores_gemma":[0.9095153,0.00004191043,0.08959667,0.000003341521,0.00001601141,0.0002839585,0.00005392748,0.00002054425,0.000468298],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6768897,"threshold_uncertainty_score":0.3251363,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01418036438877116,"score_gpt":0.2705064738530114,"score_spread":0.2563261094642402,"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."}}