1
|
Layton AT. "Hi, how can i help you?": embracing artificial intelligence in kidney research. Am J Physiol Renal Physiol 2023; 325:F395-F406. [PMID: 37589052 DOI: 10.1152/ajprenal.00177.2023] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/21/2023] [Revised: 08/08/2023] [Accepted: 08/09/2023] [Indexed: 08/18/2023] Open
Abstract
In recent years, biology and precision medicine have benefited from major advancements in generating large-scale molecular and biomedical datasets and in analyzing those data using advanced machine learning algorithms. Machine learning applications in kidney physiology and pathophysiology include segmenting kidney structures from imaging data and predicting conditions like acute kidney injury or chronic kidney disease using electronic health records. Despite the potential of machine learning to revolutionize nephrology by providing innovative diagnostic and therapeutic tools, its adoption in kidney research has been slower than in other organ systems. Several factors contribute to this underutilization. The complexity of the kidney as an organ, with intricate physiology and specialized cell populations, makes it challenging to extrapolate bulk omics data to specific processes. In addition, kidney diseases often present with overlapping manifestations and morphological changes, making diagnosis and treatment complex. Moreover, kidney diseases receive less funding compared with other pathologies, leading to lower awareness and limited public-private partnerships. To promote the use of machine learning in kidney research, this review provides an introduction to machine learning and reviews its notable applications in renal research, such as morphological analysis, omics data examination, and disease diagnosis and prognosis. Challenges and limitations associated with data-driven predictive techniques are also discussed. The goal of this review is to raise awareness and encourage the kidney research community to embrace machine learning as a powerful tool that can drive advancements in understanding kidney diseases and improving patient care.
Collapse
Affiliation(s)
- Anita T Layton
- Department of Applied Mathematics, University of Waterloo, Waterloo, Ontario, Canada
- Department of Biology, University of Waterloo, Waterloo, Ontario, Canada
- Cheriton School of Computer Science, University of Waterloo, Waterloo, Ontario, Canada
- School of Pharmacology, University of Waterloo, Waterloo, Ontario, Canada
| |
Collapse
|
2
|
Shan T, Ying Y, Song G. Automatic Kidney Segmentation Method Based on an Enhanced Generative Adversarial Network. Diagnostics (Basel) 2023; 13:diagnostics13071358. [PMID: 37046576 PMCID: PMC10093289 DOI: 10.3390/diagnostics13071358] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/29/2022] [Revised: 02/17/2023] [Accepted: 02/20/2023] [Indexed: 04/14/2023] Open
Abstract
When deciding on a kidney tumor's diagnosis and treatment, it is critical to take its morphometry into account. It is challenging to undertake a quantitative analysis of the association between kidney tumor morphology and clinical outcomes due to a paucity of data and the need for the time-consuming manual measurement of imaging variables. To address this issue, an autonomous kidney segmentation technique, namely SegTGAN, is proposed in this paper, which is based on a conventional generative adversarial network model. Its core framework includes a discriminator network with multi-scale feature extraction and a fully convolutional generator network made up of densely linked blocks. For qualitative and quantitative comparisons with the SegTGAN technique, the widely used and related medical image segmentation networks U-Net, FCN, and SegAN are used. The experimental results show that the Dice similarity coefficient (DSC), volumetric overlap error (VOE), accuracy (ACC), and average surface distance (ASD) of SegTGAN on the Kits19 dataset reach 92.28%, 16.17%, 97.28%, and 0.61 mm, respectively. SegTGAN outscores all the other neural networks, which indicates that our proposed model has the potential to improve the accuracy of CT-based kidney segmentation.
Collapse
Affiliation(s)
- Tian Shan
- State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, China
- Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang 110169, China
- University of Chinese Academy of Sciences, Beijing 100049, China
| | - Yuhan Ying
- State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, China
- Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang 110169, China
- University of Chinese Academy of Sciences, Beijing 100049, China
| | - Guoli Song
- State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, China
- Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang 110169, China
| |
Collapse
|
3
|
Labriffe M, Woillard JB, Gwinner W, Braesen JH, Anglicheau D, Rabant M, Koshy P, Naesens M, Marquet P. Machine learning-supported interpretation of kidney graft elementary lesions in combination with clinical data. Am J Transplant 2022; 22:2821-2833. [PMID: 36062389 DOI: 10.1111/ajt.17192] [Citation(s) in RCA: 13] [Impact Index Per Article: 6.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/08/2022] [Revised: 08/22/2022] [Accepted: 08/25/2022] [Indexed: 01/25/2023]
Abstract
Interpretation of kidney graft biopsies using the Banff classification is still heterogeneous. In this study, extreme gradient boosting classifiers learned from two large training datasets (n = 631 and 304 cases) where the "reference diagnoses" were not strictly defined following the Banff rules but from central reading by expert pathologists and further interpreted consensually by experienced transplant nephrologists, in light of the clinical context. In three external validation datasets (n = 3744, 589, and 360), the classifiers yielded a mean ROC curve AUC (95%CI) of: 0.97 (0.92-1.00), 0.97 (0.96-0.97), and 0.95 (0.93-0.97) for antibody-mediated rejection (ABMR); 0.94 (0.91-0.96), 0.94 (0.92-0.95), and 0.91 (0.88-0.95) for T cell-mediated rejection; >0.96 (0.90-1.00) with all three for interstitial fibrosis-tubular atrophy. We also developed a classifier to discriminate active and chronic active ABMR with 95% accuracy. In conclusion, we built highly sensitive and specific artificial intelligence classifiers able to interpret kidney graft scoring together with a few clinical data and automatically diagnose rejection, with excellent concordance with the Banff rules and reference diagnoses made by a group of experts. Some discrepancies may point toward possible improvements that could be made to the Banff classification.
Collapse
Affiliation(s)
- Marc Labriffe
- Pharmacology & Transplantation, INSERM U1248, Université de Limoges, Limoges, France.,Department of Pharmacology, Toxicology and Pharmacovigilance, CHU de Limoges, Limoges, France
| | - Jean-Baptiste Woillard
- Pharmacology & Transplantation, INSERM U1248, Université de Limoges, Limoges, France.,Department of Pharmacology, Toxicology and Pharmacovigilance, CHU de Limoges, Limoges, France
| | - Wilfried Gwinner
- Nephrology, Internal Medicine, Hannover Medical School, Hannover, Germany
| | - Jan-Hinrich Braesen
- Institute for Pathology, Nephropathology Unit, Hannover Medical School, Germany
| | - Dany Anglicheau
- Université de Paris, Paris, France.,INSERM U1151, Paris, France.,Department of Nephrology and Kidney Transplantation, Necker Hospital, Assistance Publique-Hôpitaux de Paris, Paris, France
| | - Marion Rabant
- Department of Pathology, Necker Hospital, Assistance Publique-Hôpitaux de Paris, Paris, France
| | - Priyanka Koshy
- Department of Pathology, University Hospitals Leuven, Leuven, Belgium
| | - Maarten Naesens
- Nephrology and Renal Transplantation Research Group, Department of Microbiology, Immunology and Transplantation, KU Leuven, Leuven, Belgium.,Department of Nephrology and Renal Transplantation, University Hospitals Leuven, Leuven, Belgium
| | - Pierre Marquet
- Pharmacology & Transplantation, INSERM U1248, Université de Limoges, Limoges, France.,Department of Pharmacology, Toxicology and Pharmacovigilance, CHU de Limoges, Limoges, France
| |
Collapse
|
4
|
Identification of glomerulosclerosis using IBM Watson and shallow neural networks. J Nephrol 2022; 35:1235-1242. [PMID: 35041197 PMCID: PMC8765108 DOI: 10.1007/s40620-021-01200-0] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/10/2021] [Accepted: 11/03/2021] [Indexed: 11/26/2022]
Abstract
Background Advanced stages of different renal diseases feature glomerular sclerosis at a histological level which is observed by light microscopy on tissue samples obtained by performing a kidney biopsy. Computer-aided diagnosis (CAD) systems leverage the potential of artificial intelligence (AI) in healthcare to support physicians in the diagnostic process. Methods We propose a novel CAD system that processes histological images and discriminates between sclerotic and non-sclerotic glomeruli. To this goal, we designed, tested, and compared two artificial neural network (ANN) classifiers. The former implements a shallow ANN classifying hand-crafted features extracted from Regions of Interest (ROIs) by means of image-processing procedures. The latter, instead, employs the IBM Watson Visual Recognition System, which uses a deep artificial neural network making decisions taking the images as input, without the need to design any procedure for describing images with features. The input dataset consisted of 428 sclerotic glomeruli and 2344 non-sclerotic glomeruli derived from images of kidney biopsies scanned by the Aperio ScanScope System. Results Both AI approaches allowed to very accurately distinguish (mean MCC 0.95 and mean Accuracy 0.99) between sclerotic and non-sclerotic glomeruli. Although the systems may seem interchangeable, the approach based on feature extraction and classification would allow clinicians to gain information on the most discriminating features. In fact, further procedures could explain the classifier’s decision by analysing which subset of features impacted the most on the final decision. Conclusions We developed a customizable support system that can facilitate the work of renal pathologists both in clinical and research settings. Graphical abstract ![]()
Supplementary Information The online version contains supplementary material available at 10.1007/s40620-021-01200-0.
Collapse
|
5
|
Seyahi N, Ozcan SG. Artificial intelligence and kidney transplantation. World J Transplant 2021; 11:277-289. [PMID: 34316452 PMCID: PMC8290997 DOI: 10.5500/wjt.v11.i7.277] [Citation(s) in RCA: 9] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 02/28/2021] [Revised: 05/17/2021] [Accepted: 06/04/2021] [Indexed: 02/06/2023] Open
Abstract
Artificial intelligence and its primary subfield, machine learning, have started to gain widespread use in medicine, including the field of kidney transplantation. We made a review of the literature that used artificial intelligence techniques in kidney transplantation. We located six main areas of kidney transplantation that artificial intelligence studies are focused on: Radiological evaluation of the allograft, pathological evaluation including molecular evaluation of the tissue, prediction of graft survival, optimizing the dose of immunosuppression, diagnosis of rejection, and prediction of early graft function. Machine learning techniques provide increased automation leading to faster evaluation and standardization, and show better performance compared to traditional statistical analysis. Artificial intelligence leads to improved computer-aided diagnostics and quantifiable personalized predictions that will improve personalized patient care.
Collapse
Affiliation(s)
- Nurhan Seyahi
- Department of Nephrology, Istanbul University-Cerrahpaşa, Cerrahpaşa Medical Faculty, Istanbul 34098, Fatih, Turkey
| | - Seyda Gul Ozcan
- Department of Internal Medicine, Istanbul University-Cerrahpaşa, Cerrahpaşa Medical Faculty, Istanbul 34098, Fatih, Turkey
| |
Collapse
|
6
|
Ginley B, Jen KY, Han SS, Rodrigues L, Jain S, Fogo AB, Zuckerman J, Walavalkar V, Miecznikowski JC, Wen Y, Yen F, Yun D, Moon KC, Rosenberg A, Parikh C, Sarder P. Automated Computational Detection of Interstitial Fibrosis, Tubular Atrophy, and Glomerulosclerosis. J Am Soc Nephrol 2021; 32:837-850. [PMID: 33622976 PMCID: PMC8017538 DOI: 10.1681/asn.2020050652] [Citation(s) in RCA: 48] [Impact Index Per Article: 16.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/13/2020] [Accepted: 12/14/2020] [Indexed: 02/04/2023] Open
Abstract
BACKGROUND Interstitial 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. METHODS A 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. RESULTS The 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. CONCLUSIONS ML 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.
Collapse
Affiliation(s)
- Brandon Ginley
- Departments of Pathology and Anatomical Sciences, University at Buffalo - The State University of New York, Buffalo, New York
| | - Kuang-Yu Jen
- Department of Pathology and Laboratory Medicine, University of California at Davis, Sacramento, California
| | - Seung Seok Han
- Department of Internal Medicine, Seoul National University College of Medicine, Seoul, Korea
| | - Luís Rodrigues
- University Clinic of Nephrology, Faculty of Medicine, University of Coimbra, Coimbra, Portugal.,Nephrology Unit, Coimbra Hospital and University Center, Coimbra, Portugal
| | - Sanjay Jain
- Division of Nephrology, Department of Medicine, Washington University School of Medicine, St. Louis, Missouri
| | - Agnes B Fogo
- Departments of Pathology, Microbiology, and Immunology, and Medicine, Vanderbilt University, Nashville, Tennessee
| | - Jonathan Zuckerman
- Department of Pathology and Laboratory Medicine, David Geffen School of Medicine, University of California at Los Angeles, Los Angeles, California
| | - Vighnesh Walavalkar
- Department of Pathology, University of California at San Francisco, San Francisco, California
| | - Jeffrey C Miecznikowski
- Department of Biostatistics, University at Buffalo - The State University of New York, Buffalo, New York
| | - Yumeng Wen
- Division of Nephrology, Johns Hopkins University School of Medicine, Baltimore, Maryland
| | - Felicia Yen
- Department of Pathology and Laboratory Medicine, University of California at Davis, Sacramento, California
| | - Donghwan Yun
- Department of Internal Medicine, Seoul National University College of Medicine, Seoul, Korea
| | - Kyung Chul Moon
- Department of Pathology, Seoul National University College of Medicine, Seoul, Korea
| | - Avi Rosenberg
- Department of Pathology, Johns Hopkins University School of Medicine, Baltimore, Maryland
| | - Chirag Parikh
- Division of Nephrology, Johns Hopkins University School of Medicine, Baltimore, Maryland
| | - Pinaki Sarder
- Departments of Pathology and Anatomical Sciences, University at Buffalo - The State University of New York, Buffalo, New York.,Department of Biomedical Engineering, University at Buffalo - The State University of New York, Buffalo, New York
| |
Collapse
|
7
|
Cicalese PA, Mobiny A, Shahmoradi Z, Yi X, Mohan C, Van Nguyen H. Kidney Level Lupus Nephritis Classification Using Uncertainty Guided Bayesian Convolutional Neural Networks. IEEE J Biomed Health Inform 2021; 25:315-324. [PMID: 33206612 DOI: 10.1109/jbhi.2020.3039162] [Citation(s) in RCA: 11] [Impact Index Per Article: 3.7] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/10/2022]
Abstract
The kidney biopsy based diagnosis of Lupus Nephritis (LN) is characterized by low inter-observer agreement, with misdiagnosis being associated with increased patient morbidity and mortality. Although various Computer Aided Diagnosis (CAD) systems have been developed for other nephrohistopathological applications, little has been done to accurately classify kidneys based on their kidney level Lupus Glomerulonephritis (LGN) scores. The successful implementation of CAD systems has also been hindered by the diagnosing physician's perceived classifier strengths and weaknesses, which has been shown to have a negative effect on patient outcomes. We propose an Uncertainty-Guided Bayesian Classification (UGBC) scheme that is designed to accurately classify control, class I/II, and class III/IV LGN (3 class) at both the glomerular-level classification task (26,634 segmented glomerulus images) and the kidney-level classification task (87 MRL/lpr mouse kidney sections). Data annotation was performed using a high throughput, bulk labeling scheme that is designed to take advantage of Deep Neural Network's (or DNNs) resistance to label noise. Our augmented UGBC scheme achieved a 94.5% weighted glomerular-level accuracy while achieving a weighted kidney-level accuracy of 96.6%, improving upon the standard Convolutional Neural Network (CNN) architecture by 11.8% and 3.5% respectively.
Collapse
|
8
|
Lo YC, Chung IF, Guo SN, Wen MC, Juang CF. Cycle-consistent GAN-based stain translation of renal pathology images with glomerulus detection application. Appl Soft Comput 2021. [DOI: 10.1016/j.asoc.2020.106822] [Citation(s) in RCA: 10] [Impact Index Per Article: 3.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/29/2022]
|
9
|
Li F, Nan Y, Hou X, Xie C, Wang J, Lv C, Xie G. Correlation-Guided Network for Fine-Grained Classification of Glomerular lesions in Kidney Histopathology Images. ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. ANNUAL INTERNATIONAL CONFERENCE 2020; 2020:5781-5784. [PMID: 33019288 DOI: 10.1109/embc44109.2020.9176234] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/09/2022]
Abstract
Chronic Kidney Disease has become a worldwide public health problem which demands careful assessments by pathologists. In this paper, we propose a novel architecture for fine-grained classification of glomerular lesions in renal pathology images sampling from patients with IgA nephropathy. The adversarial correlation loss is innovatively presented to guide a parallel convolutional neural network. In this well- designed loss function, bias between the prediction and the label was take into account while the relationship among different categories is well-aligned. Glomerular lesions in this study are divided into five subcategories, Neg (Negative samples such as tubule and artery), SS (sclerosis involving a portion of the glomerular tuft), GS (sclerosis involving 100% of the tuft), C (build-up of more than two layers of cells within Bowman's space, often with fibrin and collagen deposition) and NOA (none of above). Our model with 93.0% accuracy and 92.9% Fl-score for these five categories has proved superior to other models through experimental results.
Collapse
|
10
|
Stewart D, Shepard B, Rosendale J, McGehee H, Hall I, Gupta G, Reddy K, Kasiske B, Andreoni K, Klassen D. Can Behavioral Research Improve Transplant Decision-Making? A Mock Offer Study on the Role of Kidney Procurement Biopsies. KIDNEY360 2020; 1:36-47. [PMID: 35372855 PMCID: PMC8808489 DOI: 10.34067/kid.0000212019] [Citation(s) in RCA: 8] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 10/14/2019] [Accepted: 12/11/2019] [Indexed: 11/27/2022]
Abstract
Background The use of procurement biopsies for assessing kidney quality has been implicated as a driver of the nearly 20% kidney discard rate in the United States. Yet in some contexts, biopsies may boost clinical confidence, enabling acceptance of kidneys that would otherwise be discarded. We leveraged a novel organ offer simulation platform to conduct a controlled experiment isolating biopsy effects on offer acceptance decisions. Methods Between November 26 and December 14, 2018, 41 kidney transplant surgeons and 27 transplant nephrologists each received the same 20 hypothetical kidney offers using a crossover design with weekend "washout" periods. Mini-study 1 included four, low serum creatinine (<1.5 mg/dl) donor offers with arguably "poor" biopsy findings that were based on real offers that were accepted with successful 3-year recipient outcome. For each of the four offers, two experimental variants-no biopsy and "good" biopsy-were also sent. Mini-study 2 included four AKI offers with no biopsy, each having an offer variant with "good" biopsy findings. Results Among low serum creatinine donor offers, we found approximately threefold higher odds of acceptance when arguably poor biopsy findings were hidden or replaced with good biopsy findings. Among AKI donor offers, we found nearly fourfold higher odds of acceptance with good biopsy findings compared with no biopsy. Biopsy information had profound but variable effects on decision making: more participants appeared to have been influenced by biopsies to rule out, versus rule in, transplantable kidneys. Conclusions The current use of biopsies in the United States appears skewed toward inducing kidney discard. Several areas for improvement, including reducing variation in offer acceptance decisions and more accurate interpretation of findings, have the potential to make better use of scarce, donated organs. Offer simulation studies are a viable research tool for understanding decision making and identifying ways to improve the transplant system.
Collapse
Affiliation(s)
- Darren Stewart
- Research Department, United Network for Organ Sharing, Richmond, Virginia
| | - Brian Shepard
- Chief Executive Officer, United Network for Organ Sharing, Richmond, Virginia
| | - John Rosendale
- Research Department, United Network for Organ Sharing, Richmond, Virginia
| | - Harrison McGehee
- Research Department, United Network for Organ Sharing, Richmond, Virginia
| | - Isaac Hall
- Division of Nephrology and Hypertension, Department of Internal Medicine, University of Utah School of Medicine, University of Utah, Salt Lake City, Utah
| | - Gaurav Gupta
- Division of Nephrology, Department of Internal Medicine, Virginia Commonwealth University, Richmond, Virginia
| | - Kunam Reddy
- Division of Transplant and Hepatobiliary Surgery, Mayo Clinic, Phoenix, Arizona
| | - Bertram Kasiske
- Hennepin Healthcare Research Institute, Scientific Registry of Transplant Recipients, and Department of Medicine, Hennepin Healthcare, Minneapolis, Minnesota; and
| | - Kenneth Andreoni
- Department of Surgery, University of Florida, Gainesville, Florida
| | - David Klassen
- Chief Executive Officer, United Network for Organ Sharing, Richmond, Virginia
| |
Collapse
|
11
|
Chagas P, Souza L, Araújo I, Aldeman N, Duarte A, Angelo M, Dos-Santos WLC, Oliveira L. Classification of glomerular hypercellularity using convolutional features and support vector machine. Artif Intell Med 2020; 103:101808. [PMID: 32143802 DOI: 10.1016/j.artmed.2020.101808] [Citation(s) in RCA: 32] [Impact Index Per Article: 8.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/29/2019] [Revised: 11/19/2019] [Accepted: 01/13/2020] [Indexed: 02/06/2023]
Abstract
Glomeruli are histological structures of the kidney cortex formed by interwoven blood capillaries, and are responsible for blood filtration. Glomerular lesions impair kidney filtration capability, leading to protein loss and metabolic waste retention. An example of lesion is the glomerular hypercellularity, which is characterized by an increase in the number of cell nuclei in different areas of the glomeruli. Glomerular hypercellularity is a frequent lesion present in different kidney diseases. Automatic detection of glomerular hypercellularity would accelerate the screening of scanned histological slides for the lesion, enhancing clinical diagnosis. Having this in mind, we propose a new approach for classification of hypercellularity in human kidney images. Our proposed method introduces a novel architecture of a convolutional neural network (CNN) along with a support vector machine, achieving near perfect average results on FIOCRUZ data set in a binary classification (lesion or normal). Additionally, classification of hypercellularity sub-lesions was also evaluated, considering mesangial, endocapilar and both lesions, reaching an average accuracy of 82%. Either in binary task or in the multi-classification one, our proposed method outperformed Xception, ResNet50 and InceptionV3 networks, as well as a traditional handcrafted-based method. To the best of our knowledge, this is the first study on deep learning over a data set of glomerular hypercellularity images of human kidney.
Collapse
Affiliation(s)
- Paulo Chagas
- IVISION Lab, Universidade Federal da Bahia, Bahia, Brazil.
| | - Luiz Souza
- IVISION Lab, Universidade Federal da Bahia, Bahia, Brazil.
| | - Ikaro Araújo
- PPGM, Universidade Federal da Bahia, Bahia, Brazil.
| | - Nayze Aldeman
- Departamento de Medicina Especializada - Universidade Federal do Piauí, Piauí, Brazil.
| | - Angelo Duarte
- Universidade Estadual de Feira de Santana, Bahia, Brazil.
| | - Michele Angelo
- Universidade Estadual de Feira de Santana, Bahia, Brazil.
| | | | | |
Collapse
|
12
|
Ginley B, Lutnick B, Jen KY, Fogo AB, Jain S, Rosenberg A, Walavalkar V, Wilding G, Tomaszewski JE, Yacoub R, Rossi GM, Sarder P. Computational Segmentation and Classification of Diabetic Glomerulosclerosis. J Am Soc Nephrol 2019; 30:1953-1967. [PMID: 31488606 DOI: 10.1681/asn.2018121259] [Citation(s) in RCA: 115] [Impact Index Per Article: 23.0] [Reference Citation Analysis] [Abstract] [Key Words] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/22/2018] [Accepted: 06/17/2019] [Indexed: 11/03/2022] Open
Abstract
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 κ1 = 0.68, 95% interval [0.50, 0.86] and κ2 = 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.
Collapse
Affiliation(s)
| | | | - Kuang-Yu Jen
- Department of Pathology and Laboratory Medicine, University of California, Davis Medical Center, Sacramento, California
| | - Agnes B Fogo
- Departments of Pathology, Microbiology, and Immunology and Medicine, Vanderbilt University, Nashville, Tennessee
| | - Sanjay Jain
- Division of Nephrology, Department of Medicine, Washington University School of Medicine, St. Louis, Missouri
| | - Avi Rosenberg
- Department of Pathology, Johns Hopkins University School of Medicine, Baltimore, Maryland
| | - Vighnesh Walavalkar
- Department of Pathology, University of California San Francisco, San Francisco, California; and
| | | | - John E Tomaszewski
- Departments of Pathology and Anatomical Sciences.,Biomedical Informatics, and
| | - Rabi Yacoub
- Division of Nephrology, Department of Medicine, University at Buffalo-The State University of New York, Buffalo, New York
| | - Giovanni Maria Rossi
- Department of Pathology, Johns Hopkins University School of Medicine, Baltimore, Maryland.,U.O. Nefrologia, Azienda Ospedaliero-Universitaria di Parma, Dipartimento di Medicina e Chirurgia, Università di Parma
| | - Pinaki Sarder
- Departments of Pathology and Anatomical Sciences, .,Biostatistics.,Biomedical Engineering, and
| |
Collapse
|
13
|
Hermsen M, de Bel T, den Boer M, Steenbergen EJ, Kers J, Florquin S, Roelofs JJTH, Stegall MD, Alexander MP, Smith BH, Smeets B, Hilbrands LB, van der Laak JAWM. Deep Learning-Based Histopathologic Assessment of Kidney Tissue. J Am Soc Nephrol 2019; 30:1968-1979. [PMID: 31488607 DOI: 10.1681/asn.2019020144] [Citation(s) in RCA: 192] [Impact Index Per Article: 38.4] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/13/2019] [Accepted: 07/01/2019] [Indexed: 01/15/2023] Open
Abstract
BACKGROUND The development of deep neural networks is facilitating more advanced digital analysis of histopathologic images. We trained a convolutional neural network for multiclass segmentation of digitized kidney tissue sections stained with periodic acid-Schiff (PAS). METHODS We trained the network using multiclass annotations from 40 whole-slide images of stained kidney transplant biopsies and applied it to four independent data sets. We assessed multiclass segmentation performance by calculating Dice coefficients for ten tissue classes on ten transplant biopsies from the Radboud University Medical Center in Nijmegen, The Netherlands, and on ten transplant biopsies from an external center for validation. We also fully segmented 15 nephrectomy samples and calculated the network's glomerular detection rates and compared network-based measures with visually scored histologic components (Banff classification) in 82 kidney transplant biopsies. RESULTS The weighted mean Dice coefficients of all classes were 0.80 and 0.84 in ten kidney transplant biopsies from the Radboud center and the external center, respectively. The best segmented class was "glomeruli" in both data sets (Dice coefficients, 0.95 and 0.94, respectively), followed by "tubuli combined" and "interstitium." The network detected 92.7% of all glomeruli in nephrectomy samples, with 10.4% false positives. In whole transplant biopsies, the mean intraclass correlation coefficient for glomerular counting performed by pathologists versus the network was 0.94. We found significant correlations between visually scored histologic components and network-based measures. CONCLUSIONS This study presents the first convolutional neural network for multiclass segmentation of PAS-stained nephrectomy samples and transplant biopsies. Our network may have utility for quantitative studies involving kidney histopathology across centers and provide opportunities for deep learning applications in routine diagnostics.
Collapse
Affiliation(s)
| | | | | | | | - Jesper Kers
- Department of Pathology, Amsterdam Infection & Immunity, Amsterdam Cardiovascular Sciences, Amsterdam UMC, and.,Center for Analytical Sciences Amsterdam, Van 't Hoff Institute for Molecular Sciences, University of Amsterdam, Amsterdam, The Netherlands.,The Ragon Institute of the Massachusetts General Hospital, Massachusetts Institute of Technology and Harvard University, Cambridge, Massachusetts
| | - Sandrine Florquin
- Department of Pathology, Amsterdam Infection & Immunity, Amsterdam Cardiovascular Sciences, Amsterdam UMC, and
| | - Joris J T H Roelofs
- Department of Pathology, Amsterdam Infection & Immunity, Amsterdam Cardiovascular Sciences, Amsterdam UMC, and
| | - Mark D Stegall
- Divisions of Transplantation surgery.,William J. von Liebig Center for Transplantation and Clinical Regeneration, Mayo Clinic, Rochester, Minnesota; and
| | - Mariam P Alexander
- William J. von Liebig Center for Transplantation and Clinical Regeneration, Mayo Clinic, Rochester, Minnesota; and.,Pathology, and
| | - Byron H Smith
- William J. von Liebig Center for Transplantation and Clinical Regeneration, Mayo Clinic, Rochester, Minnesota; and.,Biomedical Statistics and Informatics, and
| | | | - Luuk B Hilbrands
- Nephrology, Radboud University Medical Center, Nijmegen, The Netherlands
| | - Jeroen A W M van der Laak
- Departments of Pathology and .,Center for Medical Image Science and Visualization, Linköping University, Linköping, Sweden
| |
Collapse
|
14
|
Abdeltawab H, Shehata M, Shalaby A, Khalifa F, Mahmoud A, El-Ghar MA, Dwyer AC, Ghazal M, Hajjdiab H, Keynton R, El-Baz A. A Novel CNN-Based CAD System for Early Assessment of Transplanted Kidney Dysfunction. Sci Rep 2019; 9:5948. [PMID: 30976081 PMCID: PMC6459833 DOI: 10.1038/s41598-019-42431-3] [Citation(s) in RCA: 32] [Impact Index Per Article: 6.4] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/23/2018] [Accepted: 03/29/2019] [Indexed: 12/30/2022] Open
Abstract
This paper introduces a deep-learning based computer-aided diagnostic (CAD) system for the early detection of acute renal transplant rejection. For noninvasive detection of kidney rejection at an early stage, the proposed CAD system is based on the fusion of both imaging markers and clinical biomarkers. The former are derived from diffusion-weighted magnetic resonance imaging (DW-MRI) by estimating the apparent diffusion coefficients (ADC) representing the perfusion of the blood and the diffusion of the water inside the transplanted kidney. The clinical biomarkers, namely: creatinine clearance (CrCl) and serum plasma creatinine (SPCr), are integrated into the proposed CAD system as kidney functionality indexes to enhance its diagnostic performance. The ADC maps are estimated for a user-defined region of interest (ROI) that encompasses the whole kidney. The estimated ADCs are fused with the clinical biomarkers and the fused data is then used as an input to train and test a convolutional neural network (CNN) based classifier. The CAD system is tested on DW-MRI scans collected from 56 subjects from geographically diverse populations and different scanner types/image collection protocols. The overall accuracy of the proposed system is 92.9% with 93.3% sensitivity and 92.3% specificity in distinguishing non-rejected kidney transplants from rejected ones. These results demonstrate the potential of the proposed system for a reliable non-invasive diagnosis of renal transplant status for any DW-MRI scans, regardless of the geographical differences and/or imaging protocol.
Collapse
Affiliation(s)
- Hisham Abdeltawab
- Bioengineering Department, University of Louisville, Louisville, KY, USA
| | - Mohamed Shehata
- Bioengineering Department, University of Louisville, Louisville, KY, USA
| | - Ahmed Shalaby
- Bioengineering Department, University of Louisville, Louisville, KY, USA
| | - Fahmi Khalifa
- Bioengineering Department, University of Louisville, Louisville, KY, USA
| | - Ali Mahmoud
- Bioengineering Department, University of Louisville, Louisville, KY, USA
| | - Mohamed Abou El-Ghar
- Radiology Department, Urology and Nephrology Center, Mansoura University, Mansoura, Egypt
| | - Amy C Dwyer
- Kidney Disease Program, University of Louisville, Louisville, KY, USA
| | - Mohammed Ghazal
- Bioengineering Department, University of Louisville, Louisville, KY, USA.,Electrical and Computer Engineering Department, Abu Dhabi University, Abu Dhabi, UAE
| | - Hassan Hajjdiab
- Electrical and Computer Engineering Department, Abu Dhabi University, Abu Dhabi, UAE
| | - Robert Keynton
- Bioengineering Department, University of Louisville, Louisville, KY, USA
| | - Ayman El-Baz
- Bioengineering Department, University of Louisville, Louisville, KY, USA.
| |
Collapse
|
15
|
Lutnick B, Ginley B, Govind D, McGarry SD, LaViolette PS, Yacoub R, Jain S, Tomaszewski JE, Jen KY, Sarder P. An integrated iterative annotation technique for easing neural network training in medical image analysis. NAT MACH INTELL 2019; 1:112-119. [PMID: 31187088 PMCID: PMC6557463 DOI: 10.1038/s42256-019-0018-3] [Citation(s) in RCA: 68] [Impact Index Per Article: 13.6] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/12/2018] [Accepted: 01/07/2019] [Indexed: 01/29/2023]
Abstract
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.
Collapse
Affiliation(s)
- Brendon Lutnick
- Department of Pathology & Anatomical Sciences, SUNY Buffalo, New York, NY, USA
| | - Brandon Ginley
- Department of Pathology & Anatomical Sciences, SUNY Buffalo, New York, NY, USA
| | - Darshana Govind
- Department of Pathology & Anatomical Sciences, SUNY Buffalo, New York, NY, USA
| | - Sean D. McGarry
- Department of Biophysics, Medical College of Wisconsin, Wauwatosa, WI, USA
| | - Peter S. LaViolette
- Department of Radiology and Biomedical Engineering, Medical College of Wisconsin, Wauwatosa, WI, USA
| | - Rabi Yacoub
- Department of Medicine, Nephrology, SUNY Buffalo, New York, NY, USA
| | - Sanjay Jain
- Department of Medicine, Nephrology, Washington University School of Medicine, St Louis, MO, USA
| | - John E. Tomaszewski
- Department of Pathology & Anatomical Sciences, SUNY Buffalo, New York, NY, USA
| | - Kuang-Yu Jen
- Department of Pathology, University of California, Davis Medical Center, Sacramento, CA, USA
| | - Pinaki Sarder
- Department of Pathology & Anatomical Sciences, SUNY Buffalo, New York, NY, USA
| |
Collapse
|
16
|
Marsh JN, Matlock MK, Kudose S, Liu TC, Stappenbeck TS, Gaut JP, Swamidass SJ. Deep Learning Global Glomerulosclerosis in Transplant Kidney Frozen Sections. IEEE TRANSACTIONS ON MEDICAL IMAGING 2018; 37:2718-2728. [PMID: 29994669 PMCID: PMC6296264 DOI: 10.1109/tmi.2018.2851150] [Citation(s) in RCA: 92] [Impact Index Per Article: 15.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/08/2023]
Abstract
Transplantable kidneys are in very limited supply. Accurate viability assessment prior to transplantation could minimize organ discard. Rapid and accurate evaluation of intra-operative donor kidney biopsies is essential for determining which kidneys are eligible for transplantation. The criterion for accepting or rejecting donor kidneys relies heavily on pathologist determination of the percent of glomeruli (determined from a frozen section) that are normal and sclerotic. This percentage is a critical measurement that correlates with transplant outcome. Inter- and intra-observer variability in donor biopsy evaluation is, however, significant. An automated method for determination of percent global glomerulosclerosis could prove useful in decreasing evaluation variability, increasing throughput, and easing the burden on pathologists. Here, we describe the development of a deep learning model that identifies and classifies non-sclerosed and sclerosed glomeruli in whole-slide images of donor kidney frozen section biopsies. This model extends a convolutional neural network (CNN) pre-trained on a large database of digital images. The extended model, when trained on just 48 whole slide images, exhibits slide-level evaluation performance on par with expert renal pathologists. Encouragingly, the model's performance is robust to slide preparation artifacts associated with frozen section preparation. The model substantially outperforms a model trained on image patches of isolated glomeruli, in terms of both accuracy and speed. The methodology overcomes the technical challenge of applying a pretrained CNN bottleneck model to whole-slide image classification. The traditional patch-based approach, while exhibiting deceptively good performance classifying isolated patches, does not translate successfully to whole-slide image segmentation in this setting. As the first model reported that identifies and classifies normal and sclerotic glomeruli in frozen kidney sections, and thus the first model reported in the literature relevant to kidney transplantation, it may become an essential part of donor kidney biopsy evaluation in the clinical setting.
Collapse
|
17
|
CNN cascades for segmenting sparse objects in gigapixel whole slide images. Comput Med Imaging Graph 2018; 71:40-48. [PMID: 30472409 DOI: 10.1016/j.compmedimag.2018.11.002] [Citation(s) in RCA: 37] [Impact Index Per Article: 6.2] [Reference Citation Analysis] [Abstract] [Key Words] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/07/2017] [Revised: 11/12/2018] [Accepted: 11/13/2018] [Indexed: 01/26/2023]
Abstract
Due to the increasing availability of whole slide scanners facilitating digitization of histopathological tissue, large amounts of digital image data are being generated. Accordingly, there is a strong demand for the development of computer based image analysis systems. Here, we address application scenarios in histopathology consisting of sparse, small objects-of-interest occurring in the large gigapixel images. To tackle the thereby arising challenges, we propose two different CNN cascade approaches which are subsequently applied to segment the glomeruli in whole slide images of the kidney and compared with conventional fully-convolutional networks. To facilitate unbiased evaluation, eight-fold cross-validation is performed and finally means and standard deviations are reported. Overall, with the best performing cascade approach, single CNNs are outperformed and a pixel-level Dice similarity coefficient of 0.90 is obtained (precision: 0.89, recall: 0.92). Combined with qualitative and further object-level analyses the obtained results are assessed as excellent also compared to previous approaches. We can state that especially one of the proposed cascade networks proved to be a highly powerful tool providing the best segmentation accuracies and also keeping the computing time at the lowest level. This work facilitates accurate automated segmentation of renal whole slide images which consequently allows fully-automated big data analyses for the assessment of medical treatments. Furthermore, this approach can also easily be adapted to other similar biomedical application scenarios.
Collapse
|
18
|
Bukowy JD, Dayton A, Cloutier D, Manis AD, Staruschenko A, Lombard JH, Solberg Woods LC, Beard DA, Cowley AW. Region-Based Convolutional Neural Nets for Localization of Glomeruli in Trichrome-Stained Whole Kidney Sections. J Am Soc Nephrol 2018; 29:2081-2088. [PMID: 29921718 PMCID: PMC6065078 DOI: 10.1681/asn.2017111210] [Citation(s) in RCA: 75] [Impact Index Per Article: 12.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/21/2017] [Accepted: 05/17/2018] [Indexed: 12/12/2022] Open
Abstract
Background Histologic examination of fixed renal tissue is widely used to assess morphology and the progression of disease. Commonly reported metrics include glomerular number and injury. However, characterization of renal histology is a time-consuming and user-dependent process. To accelerate and improve the process, we have developed a glomerular localization pipeline for trichrome-stained kidney sections using a machine learning image classification algorithm.Methods We prepared 4-μm slices of kidneys from rats of various genetic backgrounds that were subjected to different experimental protocols and mounted the slices on glass slides. All sections used in this analysis were trichrome stained and imaged in bright field at a minimum resolution of 0.92 μm per pixel. The training and test datasets for the algorithm comprised 74 and 13 whole renal sections, respectively, totaling over 28,000 glomeruli manually localized. Additionally, because this localizer will be ultimately used for automated assessment of glomerular injury, we assessed bias of the localizer for preferentially identifying healthy or damaged glomeruli.Results Localizer performance achieved an average precision and recall of 96.94% and 96.79%, respectively, on whole kidney sections without evidence of bias for or against glomerular injury or the need for manual preprocessing.Conclusions This study presents a novel and robust application of convolutional neural nets for the localization of glomeruli in healthy and damaged trichrome-stained whole-renal section mounts and lays the groundwork for automated glomerular injury scoring.
Collapse
Affiliation(s)
- John D Bukowy
- Department of Physiology, Medical College of Wisconsin, Milwaukee, Wisconsin
| | - Alex Dayton
- Department of Physiology, Medical College of Wisconsin, Milwaukee, Wisconsin
| | - Dustin Cloutier
- Department of Physiology, Medical College of Wisconsin, Milwaukee, Wisconsin
| | - Anna D Manis
- Department of Physiology, Medical College of Wisconsin, Milwaukee, Wisconsin
| | | | - Julian H Lombard
- Department of Physiology, Medical College of Wisconsin, Milwaukee, Wisconsin
| | - Leah C Solberg Woods
- Molecular Medicine, Wake Forest University School of Medicine, Winston-Salem, North Carolina; and
| | - Daniel A Beard
- Department of Molecular and Integrative Physiology, University of Michigan, Ann Arbor, Michigan
| | - Allen W Cowley
- Department of Physiology, Medical College of Wisconsin, Milwaukee, Wisconsin;
| |
Collapse
|