scholarly journals A tool for federated training of segmentation models on whole slide images.

2021 ◽  
Author(s):  
Brendon R Lutnick ◽  
David Manthey ◽  
Jan U Becker ◽  
Jonathan E Zuckerman ◽  
Luis Rodrigues ◽  
...  
Keyword(s):  
Interstitial Fibrosis ◽  
Image Data ◽  
Medical Data ◽  
Training Data ◽  
Further Training ◽  
Tubular Atrophy ◽  
Data Heterogeneity ◽  
Computational Pathology ◽  
Segmentation Models ◽  
Whole Slide Images

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.

scholarly journals Automated Computational Detection of Interstitial Fibrosis, Tubular Atrophy, and Glomerulosclerosis

2021 ◽  
Vol 32 (4) ◽  
pp. 837-850 ◽  
Author(s):  
Brandon Ginley ◽  
Kuang-Yu Jen ◽  
Seung Seok Han ◽  
Luís Rodrigues ◽  
Sanjay Jain ◽  
...  
Keyword(s):  
Patient Outcome ◽  
Interstitial Fibrosis ◽  
Kidney Injury ◽  
Automated Identification ◽  
Statistical Tools ◽  
Tubular Atrophy ◽  
Biopsy Specimens ◽  
Chronic Kidney Injury ◽  
Modern Machine ◽  
Whole Slide Images

BackgroundInterstitial fibrosis, tubular atrophy (IFTA), and glomerulosclerosis are indicators of irrecoverable kidney injury. Modern machine learning (ML) tools have enabled robust, automated identification of image structures that can be comparable with analysis by human experts. ML algorithms were developed and tested for the ability to replicate the detection and quantification of IFTA and glomerulosclerosis that renal pathologists perform.MethodsA renal pathologist annotated renal biopsy specimens from 116 whole-slide images (WSIs) for IFTA and glomerulosclerosis. A total of 79 WSIs were used for training different configurations of a convolutional neural network (CNN), and 17 and 20 WSIs were used as internal and external testing cases, respectively. The best model was compared against the input of four renal pathologists on 20 new testing slides. Further, for 87 testing biopsy specimens, IFTA and glomerulosclerosis measurements made by pathologists and the CNN were correlated to patient outcome using classic statistical tools.ResultsThe best average performance across all image classes came from a DeepLab version 2 network trained at 40× magnification. IFTA and glomerulosclerosis percentages derived from this CNN achieved high levels of agreement with four renal pathologists. The pathologist- and CNN-based analyses of IFTA and glomerulosclerosis showed statistically significant and equivalent correlation with all patient-outcome variables.ConclusionsML algorithms can be trained to replicate the IFTA and glomerulosclerosis assessment performed by renal pathologists. This suggests computational methods may be able to provide a standardized approach to evaluate the extent of chronic kidney injury in situations in which renal-pathologist time is restricted or unavailable.

scholarly journals A User-Friendly Tool For Cloud-Based Whole Slide Image Segmentation, With Examples From Renal Histopathology

2021 ◽  
Author(s):  
Brendon Lutnick ◽  
David Manthey ◽  
Jan Becker ◽  
Brandon Ginley ◽  
Katharina Moos ◽  
...  
Keyword(s):  
Best Practices ◽  
Interstitial Fibrosis ◽  
Histological Structure ◽  
Murine Models ◽  
Tubular Atrophy ◽  
Model Research ◽  
Slide Image ◽  
Vascular Structures ◽  
User Friendly ◽  
Whole Slide Images

Abstract We have developed Histo-Cloud, a tool for segmentation of whole slide images (WSIs) that has an easy-to-use graphical user interface. This tool runs a state-of-the-art convolutional neural network (CNN) for segmentation of WSIs in the cloud and allows the extraction of features from segmented regions for further analysis. By segmenting glomeruli, interstitial fibrosis and tubular atrophy, and vascular structures from renal and non-renal WSIs, we demonstrate the scalability, best practices for transfer learning, and effects of dataset variability. Finally, we demonstrate an application for animal model research, analyzing glomerular features in murine models of aging, diabetic nephropathy, and HIV associated nephropathy. The ability to access this tool over the internet will facilitate widespread use by computational non-experts. Histo-Cloud is open source and adaptable for segmentation of any histological structure regardless of stain.

scholarly journals U-Infuse: Democratization of Customizable Deep Learning for Object Detection

Sensors ◽  
2021 ◽  
Vol 21 (8) ◽  
pp. 2611
Author(s):  
Andrew Shepley ◽  
Greg Falzon ◽  
Christopher Lawson ◽  
Paul Meek ◽  
Paul Kwan
Keyword(s):  
Deep Learning ◽  
Intellectual Property ◽  
Object Detection ◽  
Image Data ◽  
Learning Technologies ◽  
Training Data ◽  
Learning Models ◽  
Ecological Data ◽  
Single Class ◽  
Large Numbers

Image data is one of the primary sources of ecological data used in biodiversity conservation and management worldwide. However, classifying and interpreting large numbers of images is time and resource expensive, particularly in the context of camera trapping. Deep learning models have been used to achieve this task but are often not suited to specific applications due to their inability to generalise to new environments and inconsistent performance. Models need to be developed for specific species cohorts and environments, but the technical skills required to achieve this are a key barrier to the accessibility of this technology to ecologists. Thus, there is a strong need to democratize access to deep learning technologies by providing an easy-to-use software application allowing non-technical users to train custom object detectors. U-Infuse addresses this issue by providing ecologists with the ability to train customised models using publicly available images and/or their own images without specific technical expertise. Auto-annotation and annotation editing functionalities minimize the constraints of manually annotating and pre-processing large numbers of images. U-Infuse is a free and open-source software solution that supports both multiclass and single class training and object detection, allowing ecologists to access deep learning technologies usually only available to computer scientists, on their own device, customised for their application, without sharing intellectual property or sensitive data. It provides ecological practitioners with the ability to (i) easily achieve object detection within a user-friendly GUI, generating a species distribution report, and other useful statistics, (ii) custom train deep learning models using publicly available and custom training data, (iii) achieve supervised auto-annotation of images for further training, with the benefit of editing annotations to ensure quality datasets. Broad adoption of U-Infuse by ecological practitioners will improve ecological image analysis and processing by allowing significantly more image data to be processed with minimal expenditure of time and resources, particularly for camera trap images. Ease of training and use of transfer learning means domain-specific models can be trained rapidly, and frequently updated without the need for computer science expertise, or data sharing, protecting intellectual property and privacy.

Identifying patients with CKD risk at the time of nephrectomy: When to initiate nephrology consult

2021 ◽  
pp. 239936932110319
Author(s):  
Yihe Yang ◽  
Zachary Kozel ◽  
Purva Sharma ◽  
Oksana Yaskiv ◽  
Jose Torres ◽  
...  
Keyword(s):  
Risk Factors ◽  
Multivariate Analysis ◽  
Radical Nephrectomy ◽  
Mixed Model ◽  
Linear Mixed Model ◽  
Interstitial Fibrosis ◽  
Kidney Neoplasm ◽  
Tubular Atrophy ◽  
Independent Risk Factors

Introduction: The prevalence of chronic kidney disease (CKD) is high among kidney neoplasm patients because of the overlapping risk factors. Our purpose is to identify kidney cancer survivors with higher CKD risk. Methods: We studied a retrospective cohort of 361 kidney tumor patients with partial or radical nephrectomy. Linear mixed model was performed. Results: Of patients with follow-up >3 months, 84% were identified retrospectively to fulfill criteria for CKD diagnosis, although CKD was documented in only 15%. Urinalysis was performed in 205 (57%) patients at the time of nephrectomy. Multivariate analysis showed interstitial fibrosis and tubular atrophy (IFTA) >25% ( p = 0.005), severe arteriolar sclerosis ( p = 0.013), female gender ( p = 0.024), older age ( p = 0.012), BMI ⩾ 25 kg/m2 ( p < 0.001), documented CKD ( p < 0.001), baseline eGFR ⩽ 60 ml/min/1.73 m2 ( p < 0.001), and radical nephrectomy ( p < 0.001) were independent risk factors of lower eGFR at baseline and during follow-up. Average eGFR decreased within 3 months post nephrectomy. However, patients with different risk levels showed different eGFR time trend pattern at longer follow-ups. Multivariate analysis of time × risk factor interaction showed BMI, radical nephrectomy and baseline eGFR had time-dependent impact. BMI ⩾ 25 kg/m2 and radical nephrectomy were associated with steeper eGFR decrease slope. In baseline eGFR > 90 ml/min/1.73 m2 group, eGFR rebounded to pre-nephrectomy levels during extended follow-up. In partial nephrectomy patients with baseline eGFR ⩾ 90 ml/min/1.73 m2 ( n = 61), proteinuria ( p < 0.001) and BMI ( p < 0.001) were independent risk factors of decreased eGFR during follow up. Conclusions: As have been suggested by others and confirmed by our study, proteinuria and CKD are greatly under-recognized. Although self-evident as a minimum workup for nephrectomy patients to include SCr, eGFR, urinalysis, and proteinuria, the need for uniform applications of this practice should be reinforced. Non-neoplastic histology evaluation is valuable and should include an estimate of global sclerosis% (GS) and IFTA%. Patients with any proteinuria and/or eGFR ⩽ 60 at the time of nephrectomy or in follow-up with urologists, and/or >25% GS or IFTA, should be referred for early nephrology consultation.

scholarly journals Experiments of Image Classification Using Dissimilarity Spaces Built with Siamese Networks

Sensors ◽  
2021 ◽  
Vol 21 (5) ◽  
pp. 1573
Author(s):  
Loris Nanni ◽  
Giovanni Minchio ◽  
Sheryl Brahnam ◽  
Gianluca Maguolo ◽  
Alessandra Lumini
Keyword(s):  
Vector Space ◽  
Image Classification ◽  
Ad Hoc ◽  
Feature Space ◽  
Medical Data ◽  
Training Data ◽  
Data Sets ◽  
Large Set ◽  
Clustering Methods ◽  
Siamese Networks

Traditionally, classifiers are trained to predict patterns within a feature space. The image classification system presented here trains classifiers to predict patterns within a vector space by combining the dissimilarity spaces generated by a large set of Siamese Neural Networks (SNNs). A set of centroids from the patterns in the training data sets is calculated with supervised k-means clustering. The centroids are used to generate the dissimilarity space via the Siamese networks. The vector space descriptors are extracted by projecting patterns onto the similarity spaces, and SVMs classify an image by its dissimilarity vector. The versatility of the proposed approach in image classification is demonstrated by evaluating the system on different types of images across two domains: two medical data sets and two animal audio data sets with vocalizations represented as images (spectrograms). Results show that the proposed system’s performance competes competitively against the best-performing methods in the literature, obtaining state-of-the-art performance on one of the medical data sets, and does so without ad-hoc optimization of the clustering methods on the tested data sets.

scholarly journals Performance Evaluation of Deep CNN-Based Crack Detection and Localization Techniques for Concrete Structures

Sensors ◽  
2021 ◽  
Vol 21 (5) ◽  
pp. 1688
Author(s):  
Luqman Ali ◽  
Fady Alnajjar ◽  
Hamad Al Jassmi ◽  
Munkhjargal Gochoo ◽  
Wasif Khan ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Crack Detection ◽  
Concrete Structures ◽  
Model Performance ◽  
Training Data ◽  
Computational Time ◽  
Data Heterogeneity ◽  
Public Datasets ◽  
Detection And Localization

This paper proposes a customized convolutional neural network for crack detection in concrete structures. The proposed method is compared to four existing deep learning methods based on training data size, data heterogeneity, network complexity, and the number of epochs. The performance of the proposed convolutional neural network (CNN) model is evaluated and compared to pretrained networks, i.e., the VGG-16, VGG-19, ResNet-50, and Inception V3 models, on eight datasets of different sizes, created from two public datasets. For each model, the evaluation considered computational time, crack localization results, and classification measures, e.g., accuracy, precision, recall, and F1-score. Experimental results demonstrated that training data size and heterogeneity among data samples significantly affect model performance. All models demonstrated promising performance on a limited number of diverse training data; however, increasing the training data size and reducing diversity reduced generalization performance, and led to overfitting. The proposed customized CNN and VGG-16 models outperformed the other methods in terms of classification, localization, and computational time on a small amount of data, and the results indicate that these two models demonstrate superior crack detection and localization for concrete structures.

scholarly journals Cellular Mechanisms of Tissue Fibrosis. 3. Novel mechanisms of kidney fibrosis

2013 ◽  
Vol 304 (7) ◽  
pp. C591-C603 ◽  
Author(s):  
Gabriela Campanholle ◽  
Giovanni Ligresti ◽  
Sina A. Gharib ◽  
Jeremy S. Duffield
Keyword(s):  
Chronic Kidney Disease ◽  
Kidney Disease ◽  
Interstitial Fibrosis ◽  
Kidney Injury ◽  
Innate Immune ◽  
Cellular Mechanisms ◽  
Tubular Atrophy ◽  
Kidney Fibrosis ◽  
Capillary Rarefaction ◽  
Peritubular Capillaries

Chronic kidney disease, defined as loss of kidney function for more than three months, is characterized pathologically by glomerulosclerosis, interstitial fibrosis, tubular atrophy, peritubular capillary rarefaction, and inflammation. Recent studies have identified a previously poorly appreciated, yet extensive population of mesenchymal cells, called either pericytes when attached to peritubular capillaries or resident fibroblasts when embedded in matrix, as the progenitors of scar-forming cells known as myofibroblasts. In response to sustained kidney injury, pericytes detach from the vasculature and differentiate into myofibroblasts, a process not only causing fibrosis, but also directly contributing to capillary rarefaction and inflammation. The interrelationship of these three detrimental processes makes myofibroblasts and their pericyte progenitors an attractive target in chronic kidney disease. In this review, we describe current understanding of the mechanisms of pericyte-to-myofibroblast differentiation during chronic kidney disease, draw parallels with disease processes in the glomerulus, and highlight promising new therapeutic strategies that target pericytes or myofibroblasts. In addition, we describe the critical paracrine roles of epithelial, endothelial, and innate immune cells in the fibrogenic process.

Early Urinary CCL2 is Associated With the Later Development of Interstitial Fibrosis and Tubular Atrophy in Renal Allografts

2010 ◽  
Vol 90 (4) ◽  
pp. 394-400 ◽  
Author(s):  
Julie Ho ◽  
David N. Rush ◽  
Ian W. Gibson ◽  
Martin Karpinski ◽  
Leroy Storsley ◽  
...  
Keyword(s):  
Interstitial Fibrosis ◽  
Tubular Atrophy ◽  
Renal Allografts

scholarly journals Is mycophenolate mofetil combined with low-dose prednisone a treatment option for advanced IgA nephropathy? A 10-year follow-up case and brief literature review

2018 ◽  
Vol 16 ◽  
pp. 205873921880268
Author(s):  
Qijun Wan ◽  
Yongcheng He ◽  
Hongtao Chen ◽  
Hongping Liu ◽  
Saodong Luan ◽  
...  
Keyword(s):  
Mycophenolate Mofetil ◽  
Iga Nephropathy ◽  
Treatment Option ◽  
Low Dose ◽  
Interstitial Fibrosis ◽  
Immunosuppressive Treatment ◽  
Channel Blockers ◽  
Tubular Atrophy ◽  
Dose Prednisone

IgA nephropathy (IgAN) is now widely recognized as the most common primary glomerulonephritis worldwide, especially in China. The immunosuppressive treatment option for IgAN is still controversial. Previously, we proved that mycophenolate mofetil (MMF; Shanghai Roche, China) combined with low-dose prednisone was an effective and safe option for biopsy-proven mild to moderate IgAN patients in a short term of follow-up. This article we first reported the safety and efficacy of this regimen in a 42-year-old male biopsy-proven advanced 10-year follow-up IgAN case (Lee’s Class V; the patient was biopsied 10 years ago, so the Oxford Mesangial hypercellularity Endocapillary hypercellularity Segmental glomerulosclerosis Tubular atrophy/interstitial fibrosis (MEST) classification was not used). The mycophenolate and prednisone were only given for a limited time. The other main medications included calcium channel blockers and antiplatelet agents. Clinical and laboratory indexes were aperiodic assessed during the 10-year follow-up. The serum creatinine decreased from 356 to around 210 μmol/L and urine excretion protein reduced from 3.4 g/d to about 0.5 g/d after 6 months of the initiation of this regimen, respectively. These perfect treatment effects could maintain well during the whole follow-up period. No obvious complications were observed.

Sign in / Sign up

Export Citation Format

Share Document