Reference histomorphometric data of healthy human kidneys are largely lacking because of laborious quantitation requirements. Correlating histomorphometric features with clinical parameters through machine learning approaches can provide valuable information about natural population variance. We leveraged deep learning (DL), computational image analysis, and feature analysis to associate the relationship of histomorphometry with patient age, sex, serum creatinine (SCr), and eGFR in a multinational set of reference kidney tissue sections.
We found the size and density of glomeruli, tubules, and arteries/arterioles varied significantly among healthy humans, with potentially large differences between geographically diverse patients. Glomerular size was significantly correlated with SCr and eGFR. Slight, albeit significant, differences in renal vasculature were observed between sexes. Glomerulosclerosis percentage increased, and cortical density of arteries/arterioles decreased, as a function of increasing age.
Using DL, we automated precise measurements of kidney histomorphometric features. In the reference kidney tissue, several histomorphometric features demonstrated significant correlation to patient demographics, SCr, and eGFR. DL tools can increase the efficiency and rigor of histomorphometric analysis.
Select References
N. Lucarelli†, B. Ginley§, J. Zee, S. MimarΩ, A. S. PaulΩ, S. Jain, S. S. Han, L. Rodrigeus, T. Ozrazgat-Baslanti, M. L. Wong, G. Nadkarni, W. L. Clapp, K. Y. Jen, and P. Sarder, “Correlating deep learning-based automated reference kidney histomorphometry with patient demographics and creatinine,” Kidney 360, vol. 4, no. 12, pp. 1726-1737, Dec. 2023. [Selected to be on the cover of the respective issue.]
Underline indicates corresponding author.
* indicates equal contribution.
Ω indicates Dr. Sarder’s faculty trainees.
§ indicates post doctoral associates.
† indicates Dr. Sarder’s graduate students.
‡ indicates Dr. Sarder’s undergraduate students.