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 X

Kidney Week

Abstract: SA-PO0566

Magnetic Resonance Fingerprinting (MRF) and Radiomics Analysis of Noncystic Kidney Parenchyma (NCKP) in ADPKD

Session Information

Category: Genetic Diseases of the Kidneys

  • 1201 Genetic Diseases of the Kidneys: Monogenic Kidney Diseases

Authors

  • Kremer, Linnea E., The University of Chicago Division of the Biological Sciences, Chicago, Illinois, United States
  • Kretzler, Madison E, Case Western Reserve University, Cleveland, Ohio, United States
  • MacAskill, Christina J., Case Western Reserve University, Cleveland, Ohio, United States
  • Smothers, Jacob B, Case Western Reserve University, Cleveland, Ohio, United States
  • Flask, Chris, University Hospitals Health System, Cleveland, Ohio, United States
  • Dell, Katherine MacRae, University Hospitals Health System, Cleveland, Ohio, United States
  • Prasad, Pottumarthi V., Endeavor Health, Evanston, Illinois, United States
  • Armato, Sam, The University of Chicago Division of the Biological Sciences, Chicago, Illinois, United States
  • Chapman, Arlene B., The University of Chicago Division of the Biological Sciences, Chicago, Illinois, United States
Background

MRF is a rapid quantitative MR technique that generates simultaneously collected and co-registered T1 and T2 quantitative maps in a single breath-hold. Radiomics analysis of NCKP has previously been shown to predict kidney function decline and classify risk in ADPKD patients. The primary goal of this pilot study was to compare radiomic features from MRF T1 and T2 maps of NCKP in ADPKD patients (children and young adults (n=18)) with normal kidney function, with those of healthy volunteers (n=11). Radiomic features were analyzed in relation to the established ADPKD imaging biomarker, height-corrected total kidney volume (htTKV), as well as body surface area-corrected TKV (BSA-TKV).

Methods

Manual kidney segmentations were completed from T1 maps (segmentations were applied to co-registered T2 maps). Cysts were removed from ADPKD patient's T1 maps to obtain NCKP. Radiomic features were extracted from T1 and T2 maps and different schemes were utilized to classify ADPKD patients from healthy volunteers using receiver operating characteristic (ROC) analysis: mean T1 and T2, radiomic features (first-order and gray-level co-occurrence matrix texture features) from T1 and T2 maps, htTKV, and BSA-TKV.

Results

The area under the receiver operating characteristic curve (AUC) values of differentiating ADPKD vs. controls for volumetric biomarkers were: htTKV (AUC=0.723) and BSA-TKV (AUC=0.857). NCKP Mean T2 (AUC=0.960) and radiomic features from the T1 maps (AUC=0.961) distinguished ADPKD most reliably.

Conclusion

Radiomic features from MRF T1 maps and mean T2 classified ADPKD status from healthy volunteers, indicating changes in the NCKP may successfully identify ADPKD individuals prior to cyst development.

ROC curves for classification utilizing htTKV, BSA-TKV, and NCKP features from T1 or T2 maps.

Funding

  • NIDDK Support

Digital Object Identifier (DOI)