Sensitivity Reduced on Low-Dose Pediatric CT Scans for Small Lung Nodules
By Elana Gotkine HealthDay Reporter
MONDAY, Oct. 21, 2024 -- Two lung-nodule computer-aided detection (CAD) systems demonstrated reduced sensitivity on low- versus standard-dose computed tomography (CT) scans for small nodules in pediatric patients, according to a study published online Oct. 9 in the American Journal of Roentgenology.
Russell C. Hardie, Ph.D., from the University of Dayton in Ohio, and colleagues conducted a retrospective study of 73 patients (mean age, 14.7 years) who underwent clinical standard-dose and investigational low-dose chest CT examinations within the same encounter. Two publicly available lung-nodule CAD systems that had been trained using adult data -- FlyerScan and Medical Open Network for Artificial Intelligence (MONAI) -- were used to process both CT scans. The sensitivities for 247 nodules measuring 3 to 30 mm were calculated when operating at a fixed frequency of two false-positives per scan.
The researchers found that the detection sensitivities were 76.9 and 66.8 percent on standard-dose and low-dose scans for FlyerScan, respectively, and 67.6 and 62.3 percent, respectively, for MONAI. For standard- versus low-dose scans, the number of detected nodules was 33 versus 24 (FlyerScan) and 16 versus 13 (MONAI) for 3-mm nodules; 46 versus 42 (FlyerScan) and 39 versus 30 (MONAI) for 4-mm nodules; 38 versus 33 (FlyerScan) and 32 versus 31 (MONAI) for 5-mm nodules; and 27 versus 20 (FlyerScan) and 24 versus 24 (MONAI) for 6-mm nodules. Detection did not show a consistent pattern between standard- and low-dose scans for either system for nodules measuring ≥7 mm.
"The findings indicate the need for caution when using low-dose protocols in combination with CAD systems to help detect small lung nodules in pediatric patients," the authors write.
Abstract/Full Text (subscription or payment may be required)
Disclaimer: Statistical data in medical articles provide general trends and do not pertain to individuals. Individual factors can vary greatly. Always seek personalized medical advice for individual healthcare decisions.
© 2025 HealthDay. All rights reserved.
Posted October 2024
Read this next
Random Forest AI Model Superior for Inpatient Mortality Prognostication in Cirrhosis
THURSDAY, July 24, 2025 -- For inpatients with cirrhosis, a machine learning (ML) model using random forest (RF) analysis is superior for prediction of inpatient mortality...
Inflammation and Nutrition-Based Scores Tied to Prognosis of Low-Risk Myelodysplastic Syndrome
THURSDAY, July 24, 2025 -- The Prognostic Nutritional Index (PNI) and systemic oxidative stress (SOS) score are independently associated with poorer prognosis of low-risk...
Few School Principals Report District-Mandated Mental Health Screening
THURSDAY, July 24, 2025 -- Few school principals report district-mandated mental health screening in schools, according to a study published online July 18 in JAMA Network...
More news resources
- FDA Medwatch Drug Alerts
- Daily MedNews
- News for Health Professionals
- New Drug Approvals
- New Drug Applications
- Drug Shortages
- Clinical Trial Results
- Generic Drug Approvals
Subscribe to our newsletter
Whatever your topic of interest, subscribe to our newsletters to get the best of Drugs.com in your inbox.