{"id":"W4414000490","doi":"10.18280/jesa.580708","title":"Development of a Comprehensive Lung Scan Dataset for Machine Learning-Based Lung Cancer Detection","year":2025,"lang":"en","type":"article","venue":"Journal Européen des Systèmes Automatisés","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Lung cancer; Artificial intelligence; Computed tomography; Computer science; Medical physics; Machine learning; Medicine; Radiology; Oncology","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"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":[0.001970197,0.0008521362,0.0008450099,0.002317782,0.0006198127,0.0009578847,0.002147146,0.001270523,0.002676474],"category_scores_gemma":[0.004292425,0.0003387008,0.0009425379,0.001581771,0.0003869916,0.0009056385,0.00170771,0.001361659,0.002354876],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007812466,"about_ca_system_score_gemma":0.001903047,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004649215,"about_ca_topic_score_gemma":0.008506448,"domain_scores_codex":[0.9983406,0.0002518875,0.0002145203,0.000398591,0.0006589153,0.000135336],"domain_scores_gemma":[0.9974251,0.00038771,0.0001777258,0.000757408,0.001064929,0.0001872217],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001376383,0.001946151,0.104602,0.002475233,0.0006092112,0.002644698,0.0003968462,0.04206032,0.1338037,0.007524789,0.1688642,0.5336964],"study_design_scores_gemma":[0.0004656204,0.001693975,0.1656124,0.0007197513,0.00041657,0.00928552,0.0009909641,0.2487551,0.214065,0.01051049,0.3470216,0.0004629832],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"dataset","genre_scores_codex":[0.3457401,0.003963206,0.3978004,0.002231886,0.001162754,0.004663303,0.2092801,0.02087618,0.0142821],"genre_scores_gemma":[0.2865953,0.001027189,0.3109812,0.0005951288,0.0001729007,0.003179824,0.3936114,0.0006494336,0.003187608],"genre_candidate":"dataset","genre_consensus":null,"teacher_disagreement_score":0.004649215,"threshold_uncertainty_score":0.01041955,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01702928177129294,"score_gpt":0.3242731429030553,"score_spread":0.3072438611317623,"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."}}