ASN's Mission

To create a world without kidney diseases, the ASN Alliance for Kidney Health elevates care by educating and informing, driving breakthroughs and innovation, and advocating for policies that create transformative changes in kidney medicine throughout the world.

learn more

Contact ASN

1401 H St, NW, Ste 900, Washington, DC 20005

email@asn-online.org

202-640-4660

The Latest on Twitter

Kidney Week

Abstract: TH-PO866

MR Imaging-Based Kidney Parameters in the Population-Based German National Cohort Study

Session Information

Category: CKD (Non-Dialysis)

  • 2201 CKD (Non-Dialysis): Epidemiology‚ Risk Factors‚ and Prevention

Authors

  • Sekula, Peggy, Medical Center - University of Freiburg, Freiburg, Germany
  • Lipovsek, Jan, Medical Center - University of Freiburg, Freiburg, Germany
  • Kellner, Elias, Medical Center - University of Freiburg, Freiburg, Germany
  • Kottgen, Anna, Medical Center - University of Freiburg, Freiburg, Germany

Group or Team Name

  • on behalf of the Project Team
Background

Chronic kidney disease (CKD) affects around 10% of adults worldwide. Imaging is an emerging and complementary approach to derive markers of kidney function, CKD and CKD progression. The goal of our project was to derive novel imaging markers of the kidneys through automated kidney segmentation from whole-body MR images of a subgroup of participants of the large, population-based German National Cohort (NAKO/GNC) study, and to examine their distributions and associations with other characteristics.

Methods

Using MR images of 11207 GNC participants and functionalities of the imaging platform NORA (www.nora-imaging.org), a workflow to train a convolutional neural network was developed to automatically segment different kidney compartments (cortex, hilus, medulla). Volumetric parameters (mL) for compartments and total kidney volume (TKV) were normalised to body-surface-area (BSA, m2) and related to demographic variables and estimated glomerular filtration rate (eGFR) based on serum creatinine and cystatin C.

Results

Quality control left data of 9955 participants for analysis. The mean (SD) TKV was 339 (+/-56) mL for men and 276 (+/-46) mL for women. On average, right kidneys were 5% smaller than left kidneys. The compartment volumes showed different patterns across age, with medullary volume decreasing and hilus increasing. In multivariable linear regression analyses (Table), BSA-corrected TKV was positively associated with age, sex, height and body mass index (BMI). The inclusion of eGFR strongly improved the proportion of explained variance in BSA-corrected TKV and compartments (R2=33-36%). For example, per 1 mL/min/1.73m2 higher eGFR, the BSA-corrected TKV was higher by 0.99 mL/m2.

Conclusion

The developed framework allows for robust segmentation of kidneys from MR images of a large cohort study. TKV and compartment volumes of the kidney show correlations with various participants’ characteristics that are consistent with prior knowledge and with eGFR.

BSA-corrected marker:TKV (R2=33%)Cortex (R2=35%)Medulla (R2=36%)Hilus (R2=30%)
Variable:Effect estimateP-valueEffect estimateP-valueEffect estimateP-valueEffect estimateP-value
Age, years0.478.4E-450.472.1E-780.008.4E-010.314.8E-176
Sex, male8.801.4E-2511.44.1E-71-2.554.5E-143.742.5E-45
Height, cm0.164.7E-040.118.8E-040.051.2E-020.106.9E-13
BMI (kg/ m2)0.171.0E-020.614.8E-36-0.457.3E-640.251.1E-33
eGFR (mL/min/1.73m2)0.998.5E-3000.661.3E-2500.324.3E-2060.116.4E-45

Bold P-values <0.05

Funding

  • Government Support – Non-U.S.