Abstract
Approximately 20% of children with posterior urethral valves (PUV) develop chronic kidney disease (CKD). However, our ability to predict which children will develop CKD is limited. Radiomics is a imaging analysis technique that enables the transformation of medical images into high-dimensional, quantitative descriptors that may capture subtle tissue heterogeneity not appreciable by visual inspection alone. We developed a radiomics-based model using post-natal renal ultrasounds to predict CKD progression in children with PUV. We created a retrospective cohort of children with PUV who were treated at three institutions from 1990 and 2022. CKD progression was defined as initiation of dialysis or ≥ 50% decline in estimated glomerular filtration rate (eGFR). A radiomic feature extraction was performed on the first available post-natal ultrasound. The 8 most meaningful radiomic features were used to create a survival model. Patients were stratified into high-risk and low-risk groups based on predicted risk scores. A total of 257 patients were included. The radiomics model performed moderately well with C-index of 0.69. Time-dependent ROC analysis showed AUCs of 0.714 at 2 years, 0.724 at 3 years, and 0.653 at 5 years. After risk stratification, specificity of the model for the high-risk (top 10%) group was 95%. Kaplan-Meier analysis of the high-risk (top 20%) group demonstrated significantly greater and earlier CKD progression compared to the low-risk (bottom 80%) group. Our radiomics-based model derived from post-natal renal ultrasounds demonstrates moderate ability to predict CKD progression. Integrating this with clinical data may improve early risk-stratification and patient counseling.
Links to Paper and Supplementary Materials
Main Paper (Open Access Version): https://papers.miccai.org/miccai-2026-sat/paper/PedAItrics_010.pdf
SharedIt Link: Not yet available
SpringerLink (DOI): Not yet available
Supplementary Material: Not Submitted
Link to Open Review
BibTex
@InProceedings{LogJos_Radiomic_MICCAISAT2026,
author = { Logan, Joseph AND Jeong, Stacy AND Heller, Nick AND Dortche, Kristina AND Klock, Julie AND Rickard, Mandy AND Erdman, Lauren AND Lorenzo, Armando AND Hannick, Jessica AND Woo, Lynn AND Tasian, Greg AND Weaver, John},
title = { { Radiomic Prediction of Chronic Kidney Disease Progression in Children with Posterior Urethral Valves } },
booktitle = {Medical Image Computing and Computer Assisted Intervention -- MICCAI 2026 Workshops and Challenges},
year = {2026},
publisher = {Springer Nature Switzerland},
volume = {LNCS 17257},
month = {pending},
page = {pending}
}