Statistical analysis of ADCs and clinical biomarkers in detecting acute renal transplant rejection

A DEEP LEARNING-BASED CAD SYSTEM FOR RENAL ALLOGRAFT ASSESSMENT: DIFFUSION, BOLD, AND CLINICAL BIOMARKERS

Recently, studies for non-invasive renal transplant evaluation have been explored to control allograft rejection. In this paper, a computer-aided diagnostic system has been developed to accommodate with an early-stage renal transplant status assessment, called RT-CAD. Our model of this system integrated multiple sources for a more accurate diagnosis: two image-based sources and two clinical-based sources. The image-based sources included apparent diffusion coefficients (ADCs) and the amount of deoxygenated hemoglobin (R2*). More specifically, these ADCs were extracted from 47 diffusion weighted magnetic resonance imaging (DW-MRI) scans at 11 different b-values (b0, b50, b100, …, b1000 s/mm²), while the R2* values were extracted from 30 blood oxygen level-dependent MRI (BOLD-MRI) scans at 5 different echo times (2ms, 7ms, 12ms, 17ms, and 22ms). The clinical sources included serum creatinine (SCr) and creatinine clearance (CrCl). First, the kidney was segmented through the RT-CAD system using a geometric deformable model called a level-set method. Second, both ADCs and R2* were estimated for common patients (N = 30) and then were integrated with the corresponding SCr and CrCl. Last, these integrated biomarkers were considered the discriminatory features to be used as trainers and testers for future deep learning-based classifiers such as stacked auto-encoders (SAEs). We used a k-fold cross-validation criteria to evaluate the RT-CAD system diagnostic performance, which achieved the following scores: 93.3%, 90.0%, and 95.0% in terms of accuracy, sensitivity, and specificity in differentiating between acute renal rejection (AR) and non-rejection (NR). The reliability and completeness of the RT-CAD system was further accepted by the area under the curve score of 0.92. The conclusions ensured that the presented RT-CAD system has a high reliability to diagnose the status of the renal transplant in a non-invasive way.

MRI for diagnosis of post-renal transplant complications: current state-of-the-art and future perspectives

Kidney transplantation has developed into a widespread procedure to treat end stage renal failure, with transplantation results improving over the years. Postoperative complications have decreased over the past decades, but are still an important cause of morbidity and mortality. Early accurate diagnosis and treatment is the key to prevent renal allograft impairment or even graft loss. Ideally, a diagnostic tool should be able to detect post-transplant renal dysfunction, differentiate between the different causes and monitor renal function during and after therapeutic interventions. Non-invasive imaging modalities for diagnostic purposes show promising results. Magnetic resonance imaging (MRI) techniques have a number of advantages, such as the lack of ionizing radiation and the possibility to obtain relevant tissue information without contrast, reducing the risk of contrast-induced nephrotoxicity. However, most techniques still lack the specificity to distinguish different types of parenchymal diseases. Despite some promising outcomes, MRI is still barely used in the post-transplantation diagnostic process. The aim of this review is to survey the current literature on the relevance and clinical applicability of diagnostic MRI modalities for the detection of various types of complications after kidney transplantation.

Consensus-based technical recommendations for clinical translation of renal diffusion-weighted MRI

Objectives

Standardization is an important milestone in the validation of DWI-based parameters as imaging biomarkers for renal disease. Here, we propose technical recommendations on three variants of renal DWI, monoexponential DWI, IVIM and DTI, as well as associated MRI biomarkers (ADC, D, D*, f, FA and MD) to aid ongoing international efforts on methodological harmonization.

Materials and methods

Reported DWI biomarkers from 194 prior renal DWI studies were extracted and Pearson correlations between diffusion biomarkers and protocol parameters were computed. Based on the literature review, surveys were designed for the consensus building. Survey data were collected via Delphi consensus process on renal DWI preparation, acquisition, analysis, and reporting. Consensus was defined as ≥ 75% agreement.

Results

Correlations were observed between reported diffusion biomarkers and protocol parameters. Out of 87 survey questions, 57 achieved consensus resolution, while many of the remaining questions were resolved by preference (65–74% agreement). Summary of the literature and survey data as well as recommendations for the preparation, acquisition, processing and reporting of renal DWI were provided.

Discussion

The consensus-based technical recommendations for renal DWI aim to facilitate inter-site harmonization and increase clinical impact of the technique on a larger scale by setting a framework for acquisition protocols for future renal DWI studies. We anticipate an iterative process with continuous updating of the recommendations according to progress in the field.

Electronic supplementary material

The online version of this article (10.1007/s10334-019-00790-y) contains supplementary material, which is available to authorized users.

EARLY ASSESSMENT OF RENAL TRANSPLANTS USING BOLD-MRI: PROMISING RESULTS

Non-invasive evaluation of renal transplant function is essential to minimize and manage renal rejection. A computer-assisted diagnostic (CAD) system was developed to evaluate kidney function post-transplantation. The developed CAD system utilizes the amount of blood-oxygenation extracted from 3D (2D + time) blood oxygen level-dependent magnetic resonance imaging (BOLD-MRI) to estimate renal function. BOLD-MRI scans were acquired at five different echo-times (2, 7, 12, 17, and 22) ms from 15 transplant patients. The developed CAD system first segments kidneys using the level-sets method followed by estimation of the amount of deoxyhemoglobin, also known as apparent relaxation rate (R2*). These R2* estimates were used as discriminatory features (global features (mean R2*) and local features (pixel-wise R2*)) to train and test state-of-the-art machine learning classifiers to differentiate between non-rejection (NR) and acute renal rejection. Using a leave-one-out cross-validation approach along with an artificial neural network (ANN) classifier, the CAD system demonstrated 93.3% accuracy, 100% sensitivity, and 90% specificity in distinguishing AR from non-rejection . These preliminary results demonstrate the efficacy of the CAD system to detect renal allograft status non-invasively.

Acute renal impairment characterization using diffusion magnetic resonance imaging: Validation by histology

Diffusion magnetic resonance imaging has been demonstrated to be a simple, noninvasive and accurate method for the detection of renal microstructure and microcirculation, which are closely linked to renal function. Moreover, serum endothelin-1 (ET-1) was also reported as a good indicator of early renal injury. The aim of this study was to evaluate the feasibility and capability of diffusion MRI and ET-1 to detect acute kidney injury by an operation simulating high-pressure renal pelvic perfusion, which is commonly used during ureteroscopic lithotripsy. Histological findings were used as a reference. Fourteen New Zealand rabbits in an experimental group and 14 in a control group were used in this study. Diffusion tensor imaging and intravoxel incoherent motion diffusion-weighted imaging were acquired by a 3.0 T MRI scanner. Significant corticomedullary differences were found in the values of the apparent diffusion coefficient (ADC), pure tissue diffusion, volume fraction of pseudo-diffusion (fp) and fractional anisotropy (FA) (P < 0.05 for all) in both preoperation and postoperation experimental groups. Compared with the control group, the values of cortical fp_mean , medullary ADC_mean and FA_mean decreased significantly (P < 0.05) after the operation in the experimental group. Also, the change rate of medullary ADC_mean in the experimental group was more pronounced than that in the control group (P = 0.018). No significant change was found in serum ET-1 concentration after surgery in either the experimental (P = 0.80) or control (P = 0.17) groups. In the experimental group, histological changes were observed in the medulla, while no visible change was found in the cortex. This study demonstrated the feasibility of diffusion MRI to detect the changes of renal microstructure and microcirculation in acute kidney injury, with the potential to evaluate renal function. Moreover, the sensitivity of diffusion MRI to acute kidney injury appears to be superior to that of serum ET-1.

Renal Allograft Rejection: Noninvasive Ultrasound- and MRI-Based Diagnostics

To date, allogeneic kidney transplantation remains the best available therapeutic option for patients with end-stage renal disease regarding overall survival and quality of life. Despite the advancements in immunosuppressive drugs and protocols, episodes of acute allograft rejection, a sterile inflammatory process, continue to endanger allograft survival. Since effective treatment for acute rejection episodes is available, instant diagnosis of this potentially reversible graft injury is imperative. Although histological examination by invasive core needle biopsy of the graft remains the gold standard for the diagnosis of ongoing rejection, it is always associated with the risk of causing substantial graft injury as a result of the biopsy procedure itself. At the same time, biopsies are not immediately feasible for a considerable number of patients taking anticoagulants due to the high risk of complications such as bleeding and uneven distribution of pathological changes within the graft. This can result in the wrong diagnosis due to the small size of the tissue sample taken. Therefore, there is a need for a tool that overcomes these problems by being noninvasive and capable of assessing the whole organ at the same time for specific and fast detection of acute allograft rejection. In this article, we review current state-of-the-art approaches for noninvasive diagnostics of acute renal transplant inflammation, i.e., rejection. We especially focus on nonradiation-based methods using magnetic resonance imaging (MRI) and ultrasound.