One of the largest problems for the transplantation medicine is the lack of donor grafts.¹ Compared to 2010, the rate of postmortem organ donations in Germany has decreased by 29% in 2019, which corresponds to 1210 organs. Despite an improvement with respect to 2017, the need for organs in 2019 (9271 organs required) far exceeds the number of available donor organs (3767 organs transplanted).² This high demand for donor organs shows in particular the need to increase the number of successfully transplanted organs. Optimal use of the few donor organs is urgently required not only with regard to the individual person to be treated but also from a social and political point of view. The most frequently transplanted organs are kidney, liver, heart, and lung. However, in Germany, the discrepancy between supply and demand in kidney transplantation is alarming. A total of 2291 kidneys has been available for transplantation in 2018, compared to 7526 open transplant recipients at the end of the year.³ Apart from this shortage, the rejection rate for available kidney transplants has been 14.8% in 2019.² Due to the lack of an accurate predictive organ evaluation strategy, certain organs were rejected although they would still have been suitable for transplantation.^{4 – 7} The decision to accept or reject an organ for transplantation depends primarily on the expertise of the transplant team rather than on an objective measurement. In addition in the years 2014 to 2019, intra- or postoperative complications of kidney transplantations requiring a second kidney transplantation have been between 15.3% and 20.4%.^2,3,8 Therefore, an optical evaluation tool to monitor organ quality before transplantation would be of great interest.

Facing an ongoing organ shortage in transplant medicine, strategies to increase the use of organs from marginal donors by objective organ assessment are being fostered. In this context, normothermic machine perfusion provides a platform for ex vivo organ evaluation during preservation. Consequently, analytical tools are emerging to determine organ quality. In this study, hyperspectral imaging (HSI) in the wavelength range of 550–995 nm was applied. Classification of 26 kidneys based on HSI was established using KidneyResNet, a convolutional neural network (CNN) based on the ResNet-18 architecture, to predict inulin clearance behavior. HSI preprocessing steps were implemented, including automated region of interest (ROI) selection, before executing the KidneyResNet algorithm. Training parameters and augmentation methods were investigated concerning their influence on the prediction. When classifying individual ROIs, the optimized KidneyResNet model achieved 84% and 62% accuracy in the validation and test set, respectively. With a majority decision on all ROIs of a kidney, the accuracy increased to 96% (validation set) and 100% (test set). These results demonstrate the feasibility of HSI in combination with KidneyResNet for non-invasive prediction of ex vivo kidney function. This knowledge of preoperative renal quality may support the organ acceptance decision.

The lack of donor grafts is a severe problem in transplantation medicine. Hence, the improved preservation of existing and the usage of organs that were deemed untransplantable is as urgent as ever. The development of novel preservation techniques has come into focus. A promising alternative to traditional cold storage is normothermic machine perfusion (NMP), which provides the benefit of improving the organs’ viability and of assessing the organs’ status under physiological conditions. For this purpose, methods for evaluating organ parameters have yet to be developed. In a previous study, we determined the tissue oxygen saturation (StO₂) of kidneys during NMP with hyperspectral imaging (HSI) based on a discrete wavelength (DW) algorithm. The aim of the current study was to identify a more accurate algorithm for StO₂calculation. A literature search revealed three candidates to test: a DW algorithm and two full spectral algorithms – area under a curve and partial least square regression (PLSR). After obtaining suitable calibration data to train each algorithm, they were evaluated during NMP. The wavelength range from 590 to 800 nm was found to be appropriate for analyzing StO₂of kidneys during NMP. The PLSR method shows good results in analyzing the tissues’ oxygen status in perfusion experiments.

Normothermic machine perfusion (NMP) offers a unique opportunity to objectively assess donor organ quality. This study describes the evaluation of inulin clearance as a potential marker for the ex vivo function of porcine kidneys during NMP. The function assessment was performed in both kidneys from slaughterhouse pigs (n = 20) and kidneys from pigs in a laboratory setting (n = 28). The kidneys were exposed to different warm ischemia times (WIT). After a period of static cold storage, the kidneys underwent a 4-hour NMP with autologous whole blood. Inulin clearance, hemodynamic parameters, and urine output were measured. Based on the inulin excretion behavior laboratory pig kidneys were assigned to three classes (functional, limited functional, and nonfunctional), slaughterhouse pig kidneys to two classes (limited functional and nonfunctional), respectively. Contrary to the marginal kidneys of the slaughterhouse pigs, the functional variation of kidneys of the laboratory pigs was associated with the WIT. A correlation between functional kidneys and a WIT less than 25 min was shown. Because none of the slaughterhouse pig kidneys could be assigned to the functional class, only the laboratory pig kidneys were used for examinations with functional markers. Renal blood flow and urine output during NMP correlated significantly (p < 0.01) with ex vivo kidney function. This study demonstrated that inulin is a marker of high quality for the evaluation of suggested kidney function after NMP with whole blood. Furthermore, surrogate markers measured during NMP can be used to describe and predict the physiologic behavior of kidneys before transplantation.

The preservation of kidneys using normothermic machine perfusion (NMP) prior to transplantation has the potential for predictive evaluation of organ quality. Investigations concerning the quantitative assessment of physiological tissue parameters and their dependence on organ function lack in this context. In this study, hyperspectral imaging (HSI) in the wavelength range of 500–995 nm was conducted for the determination of tissue water content (TWC) in kidneys. The quantitative relationship between spectral data and the reference TWC values was established by partial least squares regression (PLSR). Different preprocessing methods were applied to investigate their influence on predicting the TWC of kidneys. In the full wavelength range, the best models for absorbance and reflectance spectra provided R_p² values of 0.968 and 0.963, as well as root-mean-square error of prediction (RMSEP) values of 2.016 and 2.155, respectively. Considering an optimal wavelength range (800–980 nm), the best model based on reflectance spectra (R_p² value of 0.941, RMSEP value of 3.202). Finally, the visualization of TWC distribution in all pixels of kidneys’ HSI image was implemented. The results show the feasibility of HSI for a non-invasively and accurate TWC prediction in kidneys, which could be used in the future to assess the quality of kidneys during the preservation period.

Establishing an objective quality assessment of an organ prior to transplantation can help prevent unnecessary discard of the organ and reduce the probability of functional failure. In this regard, normothermic machine perfusion (NMP) offers new possibilities for organ evaluation. However, to date, few studies have addressed the identification of markers and analytical tools to determine graft quality. In this study, function and injury markers were measured in blood and urine during NMP of 26 porcine kidneys and correlated with ex vivo inulin clearance behavior. Significant differentiation of kidneys according to their function could be achieved by oxygen consumption, oxygen delivery, renal blood flow, arterial pressure, intrarenal resistance, kidney temperature, relative urea concentration, and urine production. In addition, classifications were accomplished with supervised learning methods and histological analysis to predict renal function ex vivo. Classificators (support vector machines, k-nearest-neighbor, logistic regression and naive bayes) based on relevant markers in urine and blood achieved 75% and 83% accuracy in the validation and test set, respectively. A correlation between histological damage and function could not be detected. The measurement of blood and urine markers provides information of preoperative renal quality, which can used in future to establish an objective quality assessment.