Search

Kidney fibrosis constitutes the shared final pathway of nearly all chronic nephropathies, but biomarkers for the non-invasive assessment of kidney fibrosis are currently not available. To address this, we characterize five candidate biomarkers of kidney fibrosis: Cadherin-11 (CDH11), Sparc-related modular calcium binding protein-2 (SMOC2), Pigment epithelium-derived factor (PEDF), Matrix-Gla protein, and Thrombospondin-2. Gene expression profiles in single-cell and single-nucleus RNA-sequencing (sc/snRNA-seq) datasets from rodent models of fibrosis and human chronic kidney disease (CKD) were explored, and Luminex-based assays for each biomarker were developed. Plasma and urine biomarker levels were measured using independent prospective cohorts of CKD: the Boston Kidney Biopsy Cohort, a cohort of individuals with biopsy-confirmed semiquantitative assessment of kidney fibrosis, and the Seattle Kidney Study, a cohort of patients with common forms of CKD. Ordinal logistic regression and Cox proportional hazards regression models were used to test associations of biomarkers with interstitial fibrosis and tubular atrophy and progression to end-stage kidney disease and death, respectively. Sc/snRNA-seq data confirmed cell-specific expression of biomarker genes in fibroblasts. After multivariable adjustment, higher levels of plasma CDH11, SMOC2, and PEDF and urinary CDH11 and PEDF were significantly associated with increasing severity of interstitial fibrosis and tubular atrophy in the Boston Kidney Biopsy Cohort. In both cohorts, higher levels of plasma and urinary SMOC2 and urinary CDH11 were independently associated with progression to end-stage kidney disease. Higher levels of urinary PEDF associated with end-stage kidney disease in the Seattle Kidney Study, with a similar signal in the Boston Kidney Biopsy Cohort, although the latter narrowly missed statistical significance. Thus, we identified CDH11, SMOC2, and PEDF as promising non-invasive biomarkers of kidney fibrosis.

The largest bottleneck to the development of convolutional neural network (CNN) models in the computational pathology domain is the collection and curation of diverse training datasets. Training CNNs requires large cohorts of image data, and model generalizability is dependent on training data heterogeneity. Including data from multiple centers enhances the generalizability of CNN based models, but this is hindered by the logistical challenges of sharing medical data. In this paper we explore the feasibility of training our recently developed cloud-based segmentation tool (Histo-Cloud) using federated learning. We show that a federated trained model to segment interstitial fibrosis and tubular atrophy (IFTA) using datasets from three institutions is comparable to a model trained by pooling the data on one server when tested on a fourth (holdout) institution’s data. Further, training a model to segment glomeruli for a federated dataset (split by staining) demonstrates similar performance.

Segmentation of histology tissue whole side images is an important step for tissue analysis. Given enough annotated training data modern neural networks are capable accurate reproducible segmentation, however, the annotation of training datasets is time consuming. Techniques such as human in the loop annotation attempt to reduce this annotation burden, but still require a large amount of initial annotation. Semi-supervised learning, a technique which leverages both labeled and unlabeled data to learn features has shown promise for easing the burden of annotation. Towards this goal, we employ a recently published semi-supervised method:datasetGANfor the segmentation of glomeruli from renal biopsy images. We compare the performance of models trained usingdatasetGANand traditional annotation and show thatdatasetGANsignificantly reduces the amount of annotation required to develop a highly performing segmentation model. We also explore the usefulness of usingdatasetGANfor transfer learning and find that this greatly enhances the performance when a limited number of whole slide images are used for training.

Histologic examination of interstitial fibrosis and tubular atrophy (IFTA) is critical to determine the extent of irreversible kidney injury in renal disease. The current clinical standard involves pathologist's visual assessment of IFTA, which is prone to inter-observer variability. To address this diagnostic variability, we designed two case studies (CSs), including seven pathologists, using HistomicsTK- a distributed system developed by Kitware Inc. (Clifton Park, NY). Twenty-five whole slide images (WSIs) were classified into a training set of 21 and a validation set of four. The training set was composed of seven unique subsets, each provided to an individual pathologist along with four common WSIs from the validation set. In CS 1, all pathologists individually annotated IFTA in their respective slides. These annotations were then used to train a deep learning algorithm to computationally segment IFTA. In CS 2, manual and computational annotations from CS 1 were first reviewed by the annotators to improve concordance of IFTA annotation. Both the manual and computational annotation processes were then repeated as in CS1. The inter-observer concordance in the validation set was measured by Krippendorff's alpha (KA). The KA for the seven pathologists in CS1 was 0.62 with CI [0.57, 0.67], and after reviewing each other's annotations in CS2, 0.66 with CI [0.60, 0.72]. The respective CS1 and CS2 KA were 0.58 with CI [0.52, 0.64] and 0.63 with CI [0.56, 0.69] when including the deep learner as an eighth annotator. These results suggest that our designed annotation framework refines agreement of spatial annotation of IFTA and demonstrates a human-AI approach to significantly improve the development of computational models.

Convolutional neural networks, the state of the art for image segmentation, have been successfully applied to histology images by many computational researchers. However, the translatability of this technology to clinicians and biological researchers is limited due to the complex and undeveloped user interface of the code, as well as the extensive computer setup required. We have developed a plugin for segmentation of whole slide images (WSIs) with an easy to use graphical user interface. This plugin runs a state-of-the-art convolutional neural network for segmentation of WSIs in the cloud. Our plugin is built on the open source tool HistomicsTK by Kitware Inc. (Clifton Park, NY), which provides remote data management and viewing abilities for WSI datasets. The ability to access this tool over the internet will facilitate widespread use by computational non-experts. Users can easily upload slides to a server where our plugin is installed and perform the segmentation analysis remotely. This plugin is open source and once trained, has the ability to be applied to the segmentation of any pathological structure. For a proof of concept, we have trained it to segment glomeruli from renal tissue images, demonstrating it on holdout tissue slides.

BACKGROUND: Pathologists use visual classification of glomerular lesions to assess samples from patients with diabetic nephropathy (DN). The results may vary among pathologists. Digital algorithms may reduce this variability and provide more consistent image structure interpretation. METHODS: We developed a digital pipeline to classify renal biopsies from patients with DN. We combined traditional image analysis with modern machine learning to efficiently capture important structures, minimize manual effort and supervision, and enforce biologic prior information onto our model. To computationally quantify glomerular structure despite its complexity, we simplified it to three components consisting of nuclei, capillary lumina and Bowman spaces; and Periodic Acid-Schiff positive structures. We detected glomerular boundaries and nuclei from whole slide images using convolutional neural networks, and the remaining glomerular structures using an unsupervised technique developed expressly for this purpose. We defined a set of digital features which quantify the structural progression of DN, and a recurrent network architecture which processes these features into a classification. RESULTS: Our digital classification agreed with a senior pathologist whose classifications were used as ground truth with moderate Cohen’s kappa κ = 0.55 and 95% confidence interval [0.50, 0.60]. Two other renal pathologists agreed with the digital classification with κ(1) = 0.68, 95% interval [0.50, 0.86] and κ(2) = 0.48, 95% interval [0.32, 0.64]. Our results suggest computational approaches are comparable to human visual classification methods, and can offer improved precision in clinical decision workflows. We detected glomerular boundaries from whole slide images with 0.93±0.04 balanced accuracy, glomerular nuclei with 0.94 sensitivity and 0.93 specificity, and glomerular structural components with 0.95 sensitivity and 0.99 specificity. CONCLUSIONS: Computationally derived, histologic image features hold significant diagnostic information that may augment clinical diagnostics.

Neural networks promise to bring robust, quantitative analysis to medical fields. However, their adoption is limited by the technicalities of training these networks and the required volume and quality of human-generated annotations. To address this gap in the field of pathology, we have created an intuitive interface for data annotation and the display of neural network predictions within a commonly used digital pathology whole-slide viewer. This strategy used a 'human-in-the-loop' to reduce the annotation burden. We demonstrate that segmentation of human and mouse renal micro compartments is repeatedly improved when humans interact with automatically generated annotations throughout the training process. Finally, to show the adaptability of this technique to other medical imaging fields, we demonstrate its ability to iteratively segment human prostate glands from radiology imaging data.

Background and Aims Thrombotic microangiopathies (TMAs) manifest themselves in arteries, arterioles and glomeruli. Nephropathologists need to differentiate TMAs from mimickers like hypertensive nephropathy and vasculitis which can be problematic due to interobserver disagreement and poorly defined diagnostic criteria over a wide spectrum of morphological changes with partial overlap. As a first step towards a machine learning analysis of TMAs, we developed a computer vision model for segmenting arteries, arterioles and glomeruli in TMA and mimickers. Method We manually segmented n=939 arteries, n=6,023 arterioles, n=4,507 glomeruli on whole slide images (WSIs) of 34 renal biopsies and their HE, PAS, trichrome and Jones sections (19 TMA, 11 hypertensive nephropathy, 4 vasculitis with preglomerular involvement). As a segmentation model we used DeepLab V3, pretrained on 61,734 segmented glomeruli from 768 WSIs. 58 randomly chosen WSIs served as the intrainstitutional holdout testing set after training of the model on the remaining slides. Automatic segmentation accuracies were reported as Cohen’s kappa, intersection over union (IoU) and Matthews correlation coefficient (MCC) against the nephropathologist’s segmentation as ground truth. Results Over all classes (artery, arteriole, glomerulus) Cohen’s kappa was 0.86. IoU was 0.716 for artery, 0.491 for arteriole and 0.829 for glomerulus. MCC was 0.837 for artery, 0.664 for arteriole and 0.907 for glomerulus. Conclusion We achieved good automatic segmentation of arteries, arterioles and glomeruli, even with severe pathological distortion on routine histopathological slides. We will further improve this segmentation technology in order to enable the bulk analysis of these descisive tissue compartments in large clinicopathological repositories of native kidney biopsies with TMA using supervised and unsupervised machine learning algorithms.

Generative modeling using GANs has gained traction in machine learning literature, as training does not require labeled datasets. This is perfect for applications in biological datasets, where large labeled datasets are often difficult and expensive to acquire. However, generative models offer no easy way to encode real images into feature-sets, something that is desirable for network explainability and may yield potentially informative image features. For this reason, we test a VAE-GAN architecture for label-free modeling of glomerular structural features. We show that this network can generate realistic looking synthetic images, and be used to interpolate between images. To prove the biological relevance of the network encodings, we classify small-labeled sets of encoded glomeruli by biopsy Tervaert class and for the presence of sclerosis, obtaining a Cohen’s kappa values of 0.87 and 0.78 respectfully.

The adoption of deep learning techniques in medical applications has thus far been limited by the availability of the large labeled datasets required to robustly train neural networks, as well as difficulty interpreting these networks. However, recent techniques for unsupervised training of neural networks promise to address these issues, leveraging only structure to model input data. We propose the use of a variational autoencoder (VAE) which utilizes data from an animal model to augment the training set and non-linear dimensionality reduction to map this data to human sets. This architecture utilizes variational inference, performed on latent parameters, to statistically model the probability distribution of training data in a latent feature space. We show the feasibility of VAEs, using images of mouse and human renal glomeruli from various pathological stages of diabetic nephropathy (DN), to model the progression of structural changes which occur in DN. When plotted in a 2-dimentional latent space, human and mouse glomeruli, show separation with some overlap, suggesting that the data is continuous, and can be statistically correlated. When DN stage is plotted in this latent space, trends in disease pathology are visualized.

Clinical pathology relies on manual compartmentalization and quantification of biological structures, which is time consuming and often error-prone. Application of computer vision segmentation algorithms to histopathological image analysis, in contrast, can offer fast, reproducible, and accurate quantitative analysis to aid pathologists. Algorithms tunable to different biologically relevant structures can allow accurate, precise, and reproducible estimates of disease states. In this direction, we have developed a fast, unsupervised computational method for simultaneously separating all biologically relevant structures from histopathological images in multi-scale. Segmentation is achieved by solving an energy optimization problem. Representing the image as a graph, nodes (pixels) are grouped by minimizing a Potts model Hamiltonian, adopted from theoretical physics, modeling interacting electron spins. Pixel relationships (modeled as edges) are used to update the energy of the partitioned graph. By iteratively improving the clustering, the optimal number of segments is revealed. To reduce computational time, the graph is simplified using a Cantor pairing function to intelligently reduce the number of included nodes. The classified nodes are then used to train a multiclass support vector machine to apply the segmentation over the full image. Accurate segmentations of images with as many as 106 pixels can be completed only in 5 sec, allowing for attainable multi-scale visualization. To establish clinical potential, we employed our method in renal biopsies to quantitatively visualize for the first time scale variant compartments of heterogeneous intra- and extraglomerular structures simultaneously. Implications of the utility of our method extend to fields such as oncology, genomics, and non-biological problems.

Neutrophil extracellular traps (NETs) are extracellular defense mechanisms used by neutrophils, where chromatin is expelled together with histones and granular/cytoplasmic proteins. They have become an immunology hotspot, implicated in infections, but also in a diverse array of diseases such as systemic lupus erythematosus, diabetes, and cancer. However, the precise assessment of in vivo relevance in different disease settings has been hampered by limited tools to quantify occurrence of extracellular traps in experimental models and human samples. To expedite progress towards improved quantitative tools, we have developed computational pipelines to identify extracellular traps from an in vitro human samples visualized using the ImageStream® platform (Millipore Sigma, Darmstadt, Germany), and confocal images of an in vivo mouse disease model of aspergillus fumigatus pneumonia. Our two in vitro methods, tested on n = 363/n =145 images respectively, achieved holdout sensitivity/specificity 0.98/0.93 and 1/0.92. Our unsupervised method for thin lung tissue sections in murine fungal pneumonia achieved sensitivity/specificity 0.99/0.98 in n = 14 images. Our supervised method for thin lung tissue classified NETs with sensitivity/specificity 0.86/0.90. We expect that our approach will be of value for researchers, and have application in infectious and inflammatory diseases.

Blood smear is a crucial diagnostic aid. Quantification of both solitary and overlapping erythrocytes within these smears, directly from their whole slide images (WSIs), remains a challenge. Existing software designed to accomplish the computationally extensive task of hematological WSI analysis is too expensive and is widely unavailable. We have thereby developed a fully automated software targeted for erythrocyte detection and quantification from WSIs. We define an optimal region within the smear, which contains cells that are neither too scarce/damaged nor too crowded. We detect the optimal regions within the smear and subsequently extract all the cells from these regions, both solitary and overlapped, the latter of which undergoes a clump splitting before extraction. The performance was systematically tested on 28 WSIs of blood smears obtained from 13 different species from three classes of the subphylum vertebrata including birds, mammals, and reptiles. These data pose as an immensely variant erythrocyte database with diversity in size, shape, intensity, and textural features. Our method detected [Formula: see text] more cells than that detected from the traditional monolayer and resulted in a testing accuracy of 99.14% for the classification into their respective class (bird, mammal, or reptile) and a testing accuracy of 84.73% for the classification into their respective species. The results suggest the potential employment of this software for the diagnosis of hematological disorders, such as sickle cell anemia.