Search

Background: Pre-transplant procurement biopsy interpretation is challenging, also because of the low number of renal pathology experts. Artificial intelligence (AI) can assist by aiding pathologists with kidney donor biopsy assessment. Herein we present the "Galileo" AI tool, designed specifically to assist the on-call pathologist with interpreting pre-implantation kidney biopsies., Methods: A multicenter cohort of whole slide images acquired from core-needle and wedge biopsies of the kidney was collected. A deep learning algorithm was trained to detect the main findings evaluated in the pre-implantation setting (normal glomeruli, globally sclerosed glomeruli, ischemic glomeruli, arterioles and arteries). The model obtained on the Aiforia Create platform was validated on an external dataset by three independent pathologists to evaluate the performance of the algorithm., Results: Galileo demonstrated a precision, sensitivity, F1 score and total area error of 81.96%, 94.39%, 87.74%, 2.81% and 74.05%, 71.03%, 72.5%, 2% in the training and validation sets, respectively. Galileo was significantly faster than pathologists, requiring 2 min overall in the validation phase (vs 25, 22 and 31 min by 3 separate human readers, p < 0.001). Galileo-assisted detection of renal structures and quantitative information was directly integrated in the final report., Conclusions: The Galileo AI-assisted tool shows promise in speeding up pre-implantation kidney biopsy interpretation, as well as in reducing inter-observer variability. This tool may represent a starting point for further improvements based on hard endpoints such as graft survival., (© 2024. The Author(s).)

Introduction: Artificial intelligence (AI) integration in nephropathology has been growing rapidly in recent years, facing several challenges including the wide range of histological techniques used, the low occurrence of certain diseases, and the need for data sharing. This narrative review retraces the history of AI in nephropathology and provides insights into potential future developments., Methods: Electronic searches in PubMed-MEDLINE and Embase were made to extract pertinent articles from the literature. Works about automated image analysis or the application of an AI algorithm on non-neoplastic kidney histological samples were included and analyzed to extract information such as publication year, AI task, and learning type. Prepublication servers and reviews were not included., Results: Seventy-six (76) original research articles were selected. Most of the studies were conducted in the United States in the last 7 years. To date, research has been mainly conducted on relatively easy tasks, like single-stain glomerular segmentation. However, there is a trend towards developing more complex tasks such as glomerular multi-stain classification., Conclusion: Deep learning has been used to identify patterns in complex histopathology data and looks promising for the comprehensive assessment of renal biopsy, through the use of multiple stains and virtual staining techniques. Hybrid and collaborative learning approaches have also been explored to utilize large amounts of unlabeled data. A diverse team of experts, including nephropathologists, computer scientists, and clinicians, is crucial for the development of AI systems for nephropathology. Collaborative efforts among multidisciplinary experts result in clinically relevant and effective AI tools., (© 2023. The Author(s).)

Introduction: Digital pathology can improve the technical and interpretative workflows in nephropathology by creating hub-spoke networks and virtuous collaboration projects among centers in different geographical regions. New high-resolution fast-scanning instruments combined with currently existing equipment were tested in a nephropathology hub to evaluate possible upgrading in the routine processing phases., Methods: The scanning performance of two different instruments (Aperio vs hybrid MIDI II) was evaluated and a comparative quality control check was performed on obtained whole slide images., Results: Both with default and custom settings for light microscopy, MIDI II proved to be faster, with only slightly more time required to prepare the scan and larger final file size as compared to Aperio (p < 0.001). No differences were noted in the number of out-of-focus slides per case (p = 0.75). Regarding immunofluorescence, the new scanner required longer preparation time (p = 0.001) with comparable scanning times and final file size (p = 0.169 and p = 0.177, respectively). Quality control showed differences in 3 quality features related to white background and blurriness (p < 0.001). No major discordances in the final diagnosis were recorded after comparing the report obtained with slides scanned using the two instruments, with only one case (4%) showing minor disagreement., Conclusion: The present report describes the experience of a hub nephropathology center adopting next generation digital pathology tools for the routine assessment of renal biopsies, highlighting the need for a complementary approach towards a philosophy of interoperability., (© 2023. The Author(s) under exclusive licence to Italian Society of Nephrology.)

Background: Membranous nephropathy (MN) can be idiopathic (iMN) or manifest as a result of systemic underlying conditions as a secondary epiphenomenon. For the prognostic and predictive consequences of this discrimination, the routine use of reliable markers is crucial. This large MN series aimed to evaluate the routine and standardized immunohistochemical (IHC) employment of a panel of 3 biomarkers-phospholipase A2 receptor (PLA2R), thrombospondin type-1 domain-containing 7A (THSD7A), and immunoglobulin (Ig)G4-in the differential diagnosis of MN forms, contributing to the validation of the technique and the correct interpretation of reproducible patterns of reactivity., Methods: We classified 95 patients with a biopsy proven diagnosis of MN as primary (n = 72) or secondary (n = 23) cases based on clinical data. After performing an IHC assay directed against PLA2R, THSD7A and IgG4 antigens, samples were interpreted by three different nephropathologists to assess the positivity/negativity of the staining according to new interpretation criteria., Results: Useful interpretation criteria were introduced to exclude false positive patterns of reactivity and to identify only true granular membranous or mesangial deposits in MN. The IHC directed against PLA2R resulted positive in 51 iMN cases and negative in 21, while 4/23 secondary forms were considered positive. Based on these data the technique showed a sensitivity of 71% and specificity of 83%. On the other hand, the IHC analysis for IgG4 resulted positive in 44 cases of iMN and negative in 28 cases, while only 4/23 secondary forms were positive (same cases positive to PLA2R). Finally, THSD7A was found to be positive only in 1 case, which was negative to PLA2R and IgG4. The combination of the results allowed a classification of the series into two major groups: "double-positive" (PLA2R+/IgG4+/THSD7A-) and "triple-negative" (PLA2R-/IgG4-/THSD7A-) cases., Conclusions: Based on these data, the diagnostic performance of the three biomarkers used in a "tandem fashion" can reach 79% sensitivity and 83% specificity, significantly reducing the risk of a false-positive or false-negative result and improving the routine characterization of this frequent glomerulonephritis.