Acute kidney injury (AKI) poses an increased risk factor for new AKI episodes, progression to chronic kidney disease, and death. A worsened evolution has been linked to an incomplete renal repair beyond the apparent functional recovery based on plasma creatinine (pCr) normalization. However, structural sequelae pass largely unnoticed due to the absence of specific diagnostic tools. The urinary kidney injury molecule 1 (KIM-1) participates in renal tissue damage and repair and is proposed as a biomarker of early and subclinical AKI. Thus, we study in this paper the evolution of KIM-1 urinary excretion alongside renal tissue sequelae after an intrinsic AKI episode induced by cisplatin in Wistar rats. Creatinine clearance, pCr, proteinuria and the fractional excretion of Na⁺ and glucose were used to monitor renal function. Renal tissue damage was blindly scored in kidney specimens stained with hematoxylin–eosin and periodic acid–Schiff. KIM-1 urinary excretion and renal mRNA expression were also assessed. Finally, we analyzed urinary KIM-1 in patients apparently recovered from AKI. Our results show that, after the normalization of the standard markers of glomerular filtration and tubular function, the extent of persistent histological findings of tissue repair correlates with the renal expression and urinary level of KIM-1 in rats. In addition, KIM-1 is also elevated in the urine of a significant fraction of patients apparently recovered from an AKI. Besides its potential utility in the early and subclinical diagnosis of renal damage, this study suggests a new application of urinary KIM-1 in the non-invasive follow-up of renal repair after AKI.

Acute kidney injury (AKI) is a syndrome of sudden renal excretory dysfunction with severe health consequences. AKI etiology influences prognosis, with pre-renal showing a more favorable evolution than intrinsic AKI. Because the international diagnostic criteria (i.e., based on plasma creatinine) provide no etiological distinction, anamnestic and additional biochemical criteria complement AKI diagnosis. Traditional, etiology-defining biochemical parameters, including the fractional excretion of sodium, the urinary-to-plasma creatinine ratio and the renal failure index are individually limited by confounding factors such as diuretics. To minimize distortion, we generated a composite biochemical criterion based on the congruency of at least two of the three biochemical ratios. Patients showing at least two ratios indicative of intrinsic AKI were classified within this category, and those with at least two pre-renal ratios were considered as pre-renal AKI patients. In this study, we demonstrate that the identification of intrinsic AKI by a collection of urinary injury biomarkers reflective of tubular damage, including NGAL and KIM-1, more closely and robustly coincide with the biochemical than with the anamnestic classification. Because there is no gold standard method for the etiological classification of AKI, the mutual reinforcement provided by the biochemical criterion and urinary biomarkers supports an etiological diagnosis based on objective diagnostic parameters.

(1) Background: Simultaneous evaluation of acute and chronic lesions is critical for staging renal disease, yet manual assessment suffers from high inter-observer variability and heavy workloads. While deep learning models excel at structural segmentation, none currently consolidate the concurrent quantification of key AKI-to-CKD transition markers on standard-stained tissue slides. (2) Methods: We developed a U-Net-based convolutional neural network for the pixel-wise segmentation and quantification of inflammation-associated interstitial fibrosis and tubular atrophy (i-IFTA), focal inflammatory infiltrates and tubular dilation in haematoxylin–eosin-stained whole-slide images (WSIs) from rat models of renal injury. (3) Results: The model demonstrated robust pixel-wise segmentation in H&E-stained rodent renal tissue (overall accuracy: 88.26%, macro-averaged Dice coefficient: 0.843; per-class Dice ranging from 0.727 for focal infiltrates to 0.920 for unaltered tissue). While comparative evaluation against human annotators was performed on a limited patch subset, the model exhibited agreement trends close to expert pathologists and superior to junior annotators. The end-to-end WSI inference pipeline generates full-slide visual overlays and automated WSI-level quantitative area measurements in a mean time of 103.57 s per WSI on GPU hardware. (4) Conclusions: This model offers an objective and automated framework for quantifying key structural and inflammatory lesions in rodent renal tissue. By enabling rapid WSI-level quantitative area measurements, it establishes a solid foundation for preclinical histopathological assessment and provides high potential for future translation into human clinical pathology.

Simultaneous evaluation of acute and chronic lesions is critical for staging renal disease, yet manual assessment suffers from high inter-observer variability and heavy workloads. While deep learning models excel at structural segmentation, none currently consolidate the concurrent quantification of key AKI-to-CKD transition markers in standard stains. We developed a modified U-Net convolutional neural network for the pixel-wise segmentation and quantification of inflammation-associated interstitial fibrosis and tubular atrophy (i-IFTA), focal inflammatory infiltrates and tubular dilation in haematoxylin-eosin-stained whole-slide images (WSIs) from rat models of renal injury. The model achieved an overall test accuracy of 90.21% (weighted F1-score: 90.22%). Per-class F1-scores ranged from 0.73 for focal infiltrates to 0.94 for unaltered tissue, mirroring biological class distributions. Expert pathologists validated the high quality of the boundaries, which was comparable to junior-level annotations. The end-to-end inference pipeline successfully generates full-slide visual overlays and automated quantitative area metrics in a mean time of 215 seconds per WSI on standard CPU hardware. This model addresses a critical gap by simultaneously quantifying key structural and inflammatory lesions in H&E tissue. By reducing evaluation times from hours to minutes, it offers a scalable, reproducible tool to standardize histopathological assessment.