Background: Pediatric kidney transplant recipients require periodic biopsy for active surveillance to prolong allograft half‐life, and non‐invasive MR imaging markers are needed but understudied. Here we aimed to determine the feasibility of MR diffusion tensor imaging (DTI) on pediatric kidney transplant recipients, compare transplanted kidneys DTI values to healthy controls, and correlate DTI values with allograft histopathology. Methods: Single‐center prospective study of pediatric (< 18 years of age) kidney transplant recipients undergoing biopsies and healthy controls between February 2020 and October 2023. MRI DTI‐derived metrics (fractional anisotropy [FA] and track length) of the kidney cortex were obtained for all participants. Transplant recipients versus controls, rejection versus non‐rejection, and high chronic allograft damage index (CADI) versus low were compared using two‐sample t‐test or Wilcoxon rank‐sum test. Results: Fifteen transplant recipients (4F/11M, median 16 [IQR 13–18] years old) and 15 healthy controls (9F/6M, median 15 [IQR 12–22] years old, 30 kidney units) were evaluated. DTI was technically appropriate in all cases. Smaller FA values and longer track length were found in allografts (FA in allografts (median [IQR]: 0.25 [0.25–0.28]) vs. controls (0.28 [0.27–0.33], p = 0.003) and track length in allografts (mean: 19.36 ± 5.21) vs. controls (12.80 ± 3.34, p ‐value < 0.001). FA and track length between allografts with and without rejection, and/or with high vs. low CADI score were not significantly different. Conclusion: DTI in pediatric kidney transplants is feasible and showed differences in FA and track length values when compared to controls. However, in our limited dataset, DTI did not find differences within the allograft group.

A large dataset of pediatric US measurements and natural language processing was used to calculate kidney length and volume percentiles, resulting in increased normative value precision and highlighting growth patterns.

Background: Differentiating acute kidney injury (AKI) from chronic kidney disease (CKD) in children remains a critical unmet need due to the limitations of current clinical and biochemical markers. Conventional ultrasound lacks the sensitivity to discern subtle parenchymal alterations. This study explores the application of ultrasound radiomics—a novel, non-invasive, and quantitative image analysis method—for distinguishing AKI from CKD in pediatric patients. Methods: In this retrospective cross-sectional pilot study, kidney ultrasound images were obtained from 31 pediatric subjects: 8 with oliguric AKI, 14 with CKD, and 9 healthy controls. Renal parenchyma was manually segmented, and 124 advanced texture features were extracted using the open-source ©PyFeats. Features encompassed multiple categories (e.g., GLCM, GLSZM, WP). Statistical comparisons evaluated intergroup differences. Principal Component Analysis identified the top 10 most informative features, which were used to train supervised machine learning models. Model performance used five-fold cross-validation. Results: Radiomic analysis revealed significant intergroup differences (p < 0.05). CKD cases exhibited increased echogenicity and heterogeneity, particularly in GLCM and GLSZM features, consistent with chronic fibrosis. AKI cases displayed more homogeneous texture, likely reflecting edema or acute inflammation. While echogenicity separated diseased from healthy kidneys, it lacked specificity between AKI and CKD. Among ML models, XGBoost achieved the highest macro-averaged F1 score (0.90), followed closely by SVM and Random Forest, demonstrating strong classification performance. Conclusions: Radiomics-based texture analysis of grayscale ultrasound images effectively differentiated AKI from CKD in this pilot study, offering a promising, non-invasive imaging biomarker for pediatric kidney disease. These preliminary findings justify prospective validation in larger, multicenter cohorts.