PROJECT 2 ABSTRACT ?DERIVATION AND VALIDATION OF IMAGING BIOMARKERS FOR CKD PROGRESSION? There is a need for biomarkers that can identify children with Congenital Anomalies of the Kidneys and Urinary Tract (CAKUT) early in life at high risk of future CKD progression. Early identification of children who are at highest risk of CKD progression would help guide trials of therapies for those most likely to benefit from early treatment and spare those patients at low risk of progression potential treatment-associated harms. Two potential biomarkers of CKD progression that are available immediately after birth are renal parenchymal area (RPA) and kidney echogenicity. RPA is the gross area of the kidney in maximal longitudinal length minus the area of the collecting system. RPA ?corrects? for a dilated collecting system, which is present in many children with CAKUT, and thus better estimates the functional area of the kidney than the currently used measurement of kidney length. RPA may measure the functional reserve of the kidneys, with smaller areas associated with lower nephron mass and greater probability of CKD progression. Kidney echogenicity is easily assessed on ultrasound and may predict CKD progression independent of RPA. If RPA estimates the quantity of the kidney parenchyma, echogenicity measures the quality of the remaining nephron mass. However, because kidney echogenicity is currently subjectively assessed and ways to measure kidney echogenicity have not been developed, its present utility as a clinical biomarker of CKD progression is limited. This proposed research will develop a method to objectively measure kidney echogenicity and then, using the Chronic Kidney Disease in Children (CKiD) study, will validate RPA and kidney echogenicity as two novel anatomic biomarkers of CKD progression among children with CAKUT. The advantages of these biomarkers are that they may predict CKD progression prior to the appearance of later serum or urine biomarkers, such as nadir creatinine or proteinuria, and can be measured non-invasively immediately after birth on routine clinical imaging. We will evaluate the use of RPA as a predictor of kidney function decline, and will develop an automated method to reliably and accurately measure kidney echogenicity among a cohort of 100 children without and with CKD at CHOP, and then will use ROC analysis to validate these imaging biomarkers of CKD progression among children with CAKUT enrolled in CKiD.

Agency
National Institute of Health (NIH)
Institute
National Institute of Diabetes and Digestive and Kidney Diseases (NIDDK)
Type
Specialized Center (P50)
Project #
5P50DK114786-04
Application #
10003860
Study Section
Special Emphasis Panel (ZDK1)
Project Start
2017-09-18
Project End
2022-08-31
Budget Start
2020-09-01
Budget End
2021-08-31
Support Year
4
Fiscal Year
2020
Total Cost
Indirect Cost
Name
Children's Hospital of Philadelphia
Department
Type
DUNS #
073757627
City
Philadelphia
State
PA
Country
United States
Zip Code
19146
Li, Hongming; Fan, Yong (2018) Identification of Temporal Transition of Functional States Using Recurrent Neural Networks from Functional MRI. Med Image Comput Comput Assist Interv 11072:232-239
Li, Hongming; Fan, Yong (2018) NON-RIGID IMAGE REGISTRATION USING SELF-SUPERVISED FULLY CONVOLUTIONAL NETWORKS WITHOUT TRAINING DATA. Proc IEEE Int Symp Biomed Imaging 2018:1075-1078
Li, Hongming; Satterthwaite, Theodore D; Fan, Yong (2018) BRAIN AGE PREDICTION BASED ON RESTING-STATE FUNCTIONAL CONNECTIVITY PATTERNS USING CONVOLUTIONAL NEURAL NETWORKS. Proc IEEE Int Symp Biomed Imaging 2018:101-104
Zhu, Xiaofeng; Zhang, Weihong; Fan, Yong et al. (2018) A Robust Reduced Rank Graph Regression Method for Neuroimaging Genetic Analysis. Neuroinformatics 16:351-361
Zheng, Qiang; Tasian, Gregory; Fan, Yong (2018) TRANSFER LEARNING FOR DIAGNOSIS OF CONGENITAL ABNORMALITIES OF THE KIDNEY AND URINARY TRACT IN CHILDREN BASED ON ULTRASOUND IMAGING DATA. Proc IEEE Int Symp Biomed Imaging 2018:1487-1490
Zheng, Qiang; Warner, Steven; Tasian, Gregory et al. (2018) A Dynamic Graph Cuts Method with Integrated Multiple Feature Maps for Segmenting Kidneys in 2D Ultrasound Images. Acad Radiol 25:1136-1145
Li, Hongming; Galperin-Aizenberg, Maya; Pryma, Daniel et al. (2018) Unsupervised machine learning of radiomic features for predicting treatment response and overall survival of early stage non-small cell lung cancer patients treated with stereotactic body radiation therapy. Radiother Oncol 129:218-226
Li, Hongming; Zhu, Xiaofeng; Fan, Yong (2018) Identification of Multi-scale Hierarchical Brain Functional Networks Using Deep Matrix Factorization. Med Image Comput Comput Assist Interv 11072:223-231
Li, Hongming; Fan, Yong (2018) Brain Decoding from Functional MRI Using Long Short-Term Memory Recurrent Neural Networks. Med Image Comput Comput Assist Interv 11072:320-328