Application Value of a nomogram integrating contrast-enhanced CT radiomics and clinical indicators in evaluating lymph node metastasis in pediatric peripheral neuroblastoma
An AI-powered imaging tool boosts doctors' accuracy in staging a rare childhood cancer by 21%, helping ensure kids get right-level treatment planning.
A CT radiomics-based nomogram combining arterial phase features, delta-relative radiomics, and Ki-67 achieved AUC 0.937/0.829 for lymph node metastasis prediction in 225 pediatric neuroblastoma patients, improving radiologist accuracy by 21%. This near-term implementable AI-assist tool addresses a key staging challenge in a rare pediatric solid tumor.
What the study was
- Study design
- Retrospective radiomics model development + validation
- Population
- Children with pathologically confirmed neuroblastoma; n=225 (train 157, test 68)
- Sample size
- 225
- Category
- Diagnostics
- Maturity
- Exploratory
- Journal
- Cancer Imaging
Why it surfaced
Solid radiomics study in pediatric cancer (neuroblastoma), rare disease context with meaningful clinical staging need. AUC 0.829 in validation with human-machine comparison (+21% accuracy) is a good result. Retrospective single-center limits generalizability. Scored 6.
A plain-language summary of published research — not medical advice. Talk to a clinician about your own care.