Deep Learning–Based Segmentation and Quantification in Experimental Kidney Histopathology

Abstract

BackgroundNephropathologic analyses provide important outcomes-related data in experiments with the animal models that are essential for understanding kidney disease pathophysiology. Precision medicine increases the demand for quantitative, unbiased, reproducible, and efficient histopathologic analyses, which will require novel high-throughput tools. A deep learning technique, the convolutional neural network, is increasingly applied in pathology because of its high performance in tasks like histology segmentation.MethodsWe investigated use of a convolutional neural network architecture for accurate segmentation of periodic acid–Schiff-stained kidney tissue from healthy mice and five murine disease models and from other species used in preclinical research. We trained the convolutional neural network to segment six major renal structures: glomerular tuft, glomerulus including Bowman’s capsule, tubules, arteries, arterial lumina, and veins. To achieve high accuracy, we performed a large number of expert-based annotations, 72,722 in total.ResultsMulticlass segmentation performance was very high in all disease models. The convolutional neural network allowed high-throughput and large-scale, quantitative and comparative analyses of various models. In disease models, computational feature extraction revealed interstitial expansion, tubular dilation and atrophy, and glomerular size variability. Validation showed a high correlation of findings with current standard morphometric analysis. The convolutional neural network also showed high performance in other species used in research—including rats, pigs, bears, and marmosets—as well as in humans, providing a translational bridge between preclinical and clinical studies.ConclusionsWe developed a deep learning algorithm for accurate multiclass segmentation of digital whole-slide images of periodic acid–Schiff-stained kidneys from various species and renal disease models. This enables reproducible quantitative histopathologic analyses in preclinical models that also might be applicable to clinical studies.

How will artificial intelligence and bioinformatics change our understanding of IgA Nephropathy in the next decade?

“…This CNN can perform semantic segmentation in multiple murine models of kidney diseases, as well as healthy kidneys from multiple species including humans. This approach enabled quantitative measurements of the segmented histological compartments, enabling high-throughput reproducible quantitative analysis of kidney histology that showed good correlation with other standard measurements [97].…”

“…Detection and segmentation of glomeruli in digital pictures of histological specimens or whole slide images (WSI) was one of the first and commonly used tasks, shown to be feasible in multiple stains [70,[93][94][95]. More recently, semantic multiclass segmentation of kidney histology was developed by several groups [72,96,97].…”

“…Recently, another ML model for IgAN was built to predict whether a given patient will develop ESKD or a decline in glomerular filtration rate within 5 years [104]. The variables with the highest importance were interstitial fibrosis and tubular atrophy (IFTA), serum albumin, and the percentage of globally sclerotic glomeruli [104] highlighting the importance of exact and reproducible quantification of kidney biopsy features [96,97].…”

Deep learning driven quantification of interstitial fibrosis in kidney biopsies

“…We must however acknowledge that the nephropathologist’s clinical impression and diagnosis is based on contextual factors above and beyond visual inspection of a lesion in isolation.Nevertheless, by identifying WSI regions using CAMs that are highly indicative of a class label, our approach provides a quantitative basis by which to interpret the model-based predictions rather than viewing DL methods as black-box approaches. As such, our approach stands in contrast to other methods that rely on expert-driven annotations and segmentation algorithms that attempt to quantify histological regions and derive information for pathologic assessment (12, 15-18).…”

“…Specifically, DL techniques such as convolutional neural networks have been widely used for the analysis of histopathological images. In the context of kidney diseases, researchers have been able to produce highly accurate methods to evaluate disease grade, segment various kidney structures, as well as predict clinical phenotypes (10-18). While this body of work is highly valuable, almost all of it focuses on analyzing high-resolution whole slide images (WSIs) by breaking them down into smaller patches (or tiles) or resizing the images to a lower resolution, and associating them with various outputs of interest.…”