Search

Abstract Background A significant barrier to biomarker development in the field of acute kidney injury (AKI) is the use of kidney function to identify candidates. Progress in imaging technology makes it possible to detect early structural changes prior to a decline in kidney function. Early identification of those who will advance to chronic kidney disease (CKD) would allow for the initiation of interventions to halt progression. The goal of this study was to use a structural phenotype defined by magnetic resonance imaging and histology to advance biomarker discovery during the transition from AKI to CKD. Methods Urine was collected and analyzed from adult C57Bl/6 male mice at four days and 12 weeks after folic acid-induced AKI. Mice were euthanized 12 weeks after AKI and structural metrics were obtained from cationic ferritin-enhanced-MRI (CFE-MRI) and histologic assessment. The fraction of proximal tubules, number of atubular glomeruli (ATG), and area of scarring were measured histologically. The correlation between the urinary biomarkers at the AKI or CKD and CFE-MRI derived features was determined, alone or in combination with the histologic features, using principal components. Results Using principal components derived from structural features, twelve urinary proteins were identified at the time of AKI that predicted structural changes 12 weeks after injury. The raw and normalized urinary concentrations of IGFBP-3 and TNFRII strongly correlated to the structural findings from histology and CFE-MRI. Urinary fractalkine concentration at the time of CKD correlated with structural findings of CKD. Conclusions We have used structural features to identify several candidate urinary proteins that predict whole kidney pathologic features during the transition from AKI to CKD, including IGFBP-3, TNFRII, and fractalkine. In future work, these biomarkers must be corroborated in patient cohorts to determine their suitability to predict CKD after AKI.

Medical imaging-based biomarkers derived from small objects (e.g., cell nuclei) play a crucial role in medical applications. However, detecting and segmenting small objects (a.k.a. blobs) remains a challenging task. In this research, we propose a novel 3D small blob detector called BlobCUT. BlobCUT is an unpaired image-to-image (I2I) translation model that falls under the Contrastive Unpaired Translation paradigm. It employs a blob synthesis module to generate synthetic 3D blobs with corresponding masks. This is incorporated into the iterative model training as the ground truth. The I2I translation process is designed with two constraints: (1) a convexity consistency constraint that relies on Hessian analysis to preserve the geometric properties and (2) an intensity distribution consistency constraint based on Kullback-Leibler divergence to preserve the intensity distribution of blobs. BlobCUT learns the inherent noise distribution from the target noisy blob images and performs image translation from the noisy domain to the clean domain, effectively functioning as a denoising process to support blob identification. To validate the performance of BlobCUT, we evaluate it on a 3D simulated dataset of blobs and a 3D MRI dataset of mouse kidneys. We conduct a comparative analysis involving six state-of-the-art methods. Our findings reveal that BlobCUT exhibits superior performance and training efficiency, utilizing only 56.6% of the training time required by the state-of-the-art BlobDetGAN. This underscores the effectiveness of BlobCUT in accurately segmenting small blobs while achieving notable gains in training efficiency.

Abstract Preterm birth is a leading cause of neonatal morbidity. Survivors have a greater risk for kidney dysfunction and hypertension. Little is known about the molecular changes that occur in the kidney of individuals born preterm. Here, we demonstrate that mice delivered two days prior to full term gestation undergo premature cessation of nephrogenesis, resulting in a lower glomerular density. Kidneys from preterm and term groups exhibited differences in gene expression profiles at 20- and 27-days post-conception, including significant differences in the expression of fat-soluble vitamin-related genes. Kidneys of the preterm mice exhibited decreased proportions of endothelial cells and a lower expression of genes promoting angiogenesis compared to the term group. Kidneys from the preterm mice also had altered nephron progenitor subpopulations, early Six2 depletion, and altered Jag1 expression in the nephrogenic zone, consistent with premature differentiation of nephron progenitor cells. In conclusion, preterm birth alone was sufficient to shorten the duration of nephrogenesis and cause premature differentiation of nephron progenitor cells. These candidate genes and pathways may provide targets to improve kidney health in preterm infants.

Generative Adversarial Networks (GANs) are a class of deep learning models being applied to image processing. GANs have demonstrated state-of-the-art performance in applications such as image generation and image-to-image translation, just to name a few. However, with this success comes the realization that the training of GANs takes a long time and is often limited by available computing resources. In this research, we propose to construct a Coreset using Fréchet Descriptor Distances (FDD-Coreset) to accelerate the training of GAN for blob identification. We first propose a Fréchet Descriptor Distance (FDD) to measure the difference between each pair of blob images based on the statistics derived from blob distribution. The Coreset is then employed using our proposed FDD metric to select samples from the entire dataset for GAN training. A 3D-simulated dataset of blobs and a 3D MRI dataset of human kidneys are studied. Using computation time and eight performance metrics, the GAN trained on the FDD-Coreset is compared against the model trained on the entire dataset and an Inception and Euclidean Distance-based Coreset (IED-Coreset). We conclude that the FDD-Coreset not only significantly reduces the training time, but also achieves higher denoising performance and maintains approximate performance of blob identification compared with training on the entire dataset.

ABSTRACT IMPACT: Chronic kidney disease (CKD) affects ˜15% of the US population and the majority of patients are diagnosed too late to benefit from early intervention. We are developing a new diagnostic imaging tool (RadioCF-PET) for the kidney to enable early detection of diseases and to monitor overall kidney health. OBJECTIVES/GOALS: Nephron mass, or the number of functioning nephrons, is a measure of the functional capacity of the kidney. RadioCF-PET may enable early detection of nephron loss in patients with or at risk of CKD before changes are clinically detectable, facilitating early interventions to improve outcomes in these patients. METHODS/STUDY POPULATION: RadioCF-PET, labeled with Cu-64, has the advantage of using sub pharmacological doses for imaging, carrying low risk and can be used with the FDA’s exploratory IND (eIND) mechanism for early in human testing. We are developing the technology to be used in pre-eIND toxicology and pharmacology studies. We are also developing other aspects of translational science to propel this technology toward translation, including: market analysis, critical path to market, customer discovery, and commercialization strategy. RESULTS/ANTICIPATED RESULTS: Milestone 1: Apply technology in mouse model study and in human kidneys rejected for transplant. Anticipated Result 1: PET signal from RadioCF-PET correlates with glomerular density in healthy and diseased model male mice (R2 = 0.98). RadioCF-PET signal correlates with glomerular number in a donated human kidney (R2= 0.78). Milestone 2: Application to federal funding (STTR) and gap funding mechanisms to enable pre-eIND studies. Anticipated Result 1: Application for funding will aid to clarify and validate our market analysis and commercialization strategy. Milestone 3: Continued research and development with the technology in new studies. Other Anticipated Results: Future work with RadioCF-PET will enhance technology performance in preparation for pre-eIND studies. DISCUSSION/SIGNIFICANCE OF FINDINGS: We foresee a large clinical and commercial potential for RadioCF-PET to provide precise, early monitoring in patients at risk for or with CKD. The two biggest hurdles for clinical translation are validating safety and proving efficacy. This work targets both issues to facilitate RadioCF-PET toward clinical translation.