A large-scale retrospective study enabled deep-learning based pathological assessment of frozen procurement kidney biopsies to predict graft loss and guide organ utilization.

Lesion scores on procurement donor biopsies are commonly used to guide organ utilization for deceased-donor kidneys. However, frozen sections present challenges for histological scoring, leading to inter- and intra-observer variability and inappropriate discard. Therefore, we constructed deep-learning based models to recognize kidney tissue compartments in hematoxylin & eosin-stained sections from procurement needle biopsies performed nationwide in years 2011-2020. To do this, we extracted whole-slide abnormality features from 2431 kidneys and correlated with pathologists' scores and transplant outcomes. A Kidney Donor Quality Score (KDQS) was derived and used in combination with recipient demographic and peri-transplant characteristics to predict graft loss or assist organ utilization. The performance on wedge biopsies was additionally evaluated. Our model identified 96% and 91% of normal/sclerotic glomeruli respectively; 94% of arteries/arterial intimal fibrosis; 90% of tubules. Whole-slide features of Sclerotic Glomeruli (GS)%, Arterial Intimal Fibrosis (AIF)%, and Interstitial Space Abnormality (ISA)% demonstrated strong correlations with corresponding pathologists' scores of all 2431 kidneys, but had superior associations with post-transplant estimated glomerular filtration rates in 2033 and graft loss in 1560 kidneys. The combination of KDQS and other factors predicted one- and four-year graft loss in a discovery set of 520 kidneys and a validation set of 1040 kidneys. By using the composite KDQS of 398 discarded kidneys due to "biopsy findings", we suggest that if transplanted, 110 discarded kidneys could have had similar survival to that of other transplanted kidneys. Thus, our composite KDQS and survival prediction models may facilitate risk stratification and organ utilization while potentially reducing unnecessary organ discard.

Open-Source System for Real-Time Functional Assessment of In Vitro Filtration Barriers.

The integrity of the barrier between blood and the selective filtrate of solutes is important for homeostasis and its disruption contributes to many diseases. Microphysiological systems that incorporate synthetic or natural membranes with human cells can mimic biological filtration barriers, such as the glomerular filtration barrier in the kidney, and they can readily be used to study cellular filtration processes as well as drug effects and interactions. We present an affordable, open-source platform for the real-time monitoring of functional filtration status in engineered microphysiological systems. Using readily available components, our assay can linearly detect real-time concentrations of two target molecules, FITC-labeled inulin and Texas Red-labeled human-serum albumin, within clinically relevant ranges, and it can be easily modified for different target molecules of varying sizes and tags. We demonstrate the platform's ability to determine the concentration of our target molecules automatically and consistently. We show through an acellular context that the platform enables real-time tracking of size-dependent diffusion with minimal fluid volume loss and without manual extraction of media, making it suitable for continuous operational monitoring of filtration status in microphysiological system applications. The platform's affordability and integrability with microphysiological systems make it ideal for many precision medicine applications, including evaluation of drug nephrotoxicity and other forms of drug discovery.