Open Collections

Singla, Rohit Kumar

University of British Columbia

Chronic kidney disease impacts 1 in 10 adults globally, with exponential increases in hospitalization, adverse cardiovascular events and mortality risk. Those who reach end-stage kidney disease require renal replacement therapy, a significant burden on a patient’s quality of life and on the Canadian healthcare budget. Serum and urine biomarkers of kidney disease are insensitive, potentially producing false negative re- sults, whereas tissue biopsy is an invasive procedure that is not routinely performed and comes with complications such as bleeding and infection. There is a need for non-invasive characterization of the kidney. This thesis investigates several methods of kidney tissue characterization, ranging from the macro whole-organ scale to the microstructural scale, using ultrasound imaging methods and machine learning. It presents an open detailed high quality data set for kidney segmentation, with a demonstration of how automatic morphological measurements can be obtained in clinical ultrasound settings using machine learning. This automated measurement is comparable to human experts. It contributes how physics-based data augmentation techniques can improve the robustness of such algorithms, showing that a time-gain compensation augmentation reduces algorithmic uncertainty. It then investigates the speckle properties of transplanted kidneys, showing such properties are patient- and machine-agnostic. This study also identifies the Nakagami distribution as the best model of speckle in the kidney. Subsequent work demonstrates that ultrasound images alone can be used to predict kidney decline in transplant recipients, with speckle parameters being amongst the most prognostic. Finally, quantitative ultra- sound parameters are measured in a murine study. The results show the versatility and accuracy of quantitative ultrasound to characterize the kidney, and enabling a non-invasive method for quantifying kidney disease.

Text

2023-05-18

Attribution-NoDerivatives 4.0 International

http://hdl.handle.net/2429/84672

Biomedical Engineering

University of British Columbia

UBCV

http://creativecommons.org/licenses/by-nd/4.0/