1
|
Hosseini MS, Bejnordi BE, Trinh VQH, Chan L, Hasan D, Li X, Yang S, Kim T, Zhang H, Wu T, Chinniah K, Maghsoudlou S, Zhang R, Zhu J, Khaki S, Buin A, Chaji F, Salehi A, Nguyen BN, Samaras D, Plataniotis KN. Computational pathology: A survey review and the way forward. J Pathol Inform 2024; 15:100357. [PMID: 38420608 PMCID: PMC10900832 DOI: 10.1016/j.jpi.2023.100357] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/15/2023] [Revised: 12/21/2023] [Accepted: 12/23/2023] [Indexed: 03/02/2024] Open
Abstract
Computational Pathology (CPath) is an interdisciplinary science that augments developments of computational approaches to analyze and model medical histopathology images. The main objective for CPath is to develop infrastructure and workflows of digital diagnostics as an assistive CAD system for clinical pathology, facilitating transformational changes in the diagnosis and treatment of cancer that are mainly address by CPath tools. With evergrowing developments in deep learning and computer vision algorithms, and the ease of the data flow from digital pathology, currently CPath is witnessing a paradigm shift. Despite the sheer volume of engineering and scientific works being introduced for cancer image analysis, there is still a considerable gap of adopting and integrating these algorithms in clinical practice. This raises a significant question regarding the direction and trends that are undertaken in CPath. In this article we provide a comprehensive review of more than 800 papers to address the challenges faced in problem design all-the-way to the application and implementation viewpoints. We have catalogued each paper into a model-card by examining the key works and challenges faced to layout the current landscape in CPath. We hope this helps the community to locate relevant works and facilitate understanding of the field's future directions. In a nutshell, we oversee the CPath developments in cycle of stages which are required to be cohesively linked together to address the challenges associated with such multidisciplinary science. We overview this cycle from different perspectives of data-centric, model-centric, and application-centric problems. We finally sketch remaining challenges and provide directions for future technical developments and clinical integration of CPath. For updated information on this survey review paper and accessing to the original model cards repository, please refer to GitHub. Updated version of this draft can also be found from arXiv.
Collapse
Affiliation(s)
- Mahdi S Hosseini
- Department of Computer Science and Software Engineering (CSSE), Concordia Univeristy, Montreal, QC H3H 2R9, Canada
| | | | - Vincent Quoc-Huy Trinh
- Institute for Research in Immunology and Cancer of the University of Montreal, Montreal, QC H3T 1J4, Canada
| | - Lyndon Chan
- The Edward S. Rogers Sr. Department of Electrical & Computer Engineering (ECE), University of Toronto, Toronto, ON M5S 3G4, Canada
| | - Danial Hasan
- The Edward S. Rogers Sr. Department of Electrical & Computer Engineering (ECE), University of Toronto, Toronto, ON M5S 3G4, Canada
| | - Xingwen Li
- The Edward S. Rogers Sr. Department of Electrical & Computer Engineering (ECE), University of Toronto, Toronto, ON M5S 3G4, Canada
| | - Stephen Yang
- The Edward S. Rogers Sr. Department of Electrical & Computer Engineering (ECE), University of Toronto, Toronto, ON M5S 3G4, Canada
| | - Taehyo Kim
- The Edward S. Rogers Sr. Department of Electrical & Computer Engineering (ECE), University of Toronto, Toronto, ON M5S 3G4, Canada
| | - Haochen Zhang
- The Edward S. Rogers Sr. Department of Electrical & Computer Engineering (ECE), University of Toronto, Toronto, ON M5S 3G4, Canada
| | - Theodore Wu
- The Edward S. Rogers Sr. Department of Electrical & Computer Engineering (ECE), University of Toronto, Toronto, ON M5S 3G4, Canada
| | - Kajanan Chinniah
- The Edward S. Rogers Sr. Department of Electrical & Computer Engineering (ECE), University of Toronto, Toronto, ON M5S 3G4, Canada
| | - Sina Maghsoudlou
- Department of Computer Science and Software Engineering (CSSE), Concordia Univeristy, Montreal, QC H3H 2R9, Canada
| | - Ryan Zhang
- The Edward S. Rogers Sr. Department of Electrical & Computer Engineering (ECE), University of Toronto, Toronto, ON M5S 3G4, Canada
| | - Jiadai Zhu
- The Edward S. Rogers Sr. Department of Electrical & Computer Engineering (ECE), University of Toronto, Toronto, ON M5S 3G4, Canada
| | - Samir Khaki
- The Edward S. Rogers Sr. Department of Electrical & Computer Engineering (ECE), University of Toronto, Toronto, ON M5S 3G4, Canada
| | - Andrei Buin
- Huron Digitial Pathology, St. Jacobs, ON N0B 2N0, Canada
| | - Fatemeh Chaji
- Department of Computer Science and Software Engineering (CSSE), Concordia Univeristy, Montreal, QC H3H 2R9, Canada
| | - Ala Salehi
- Department of Electrical and Computer Engineering, University of New Brunswick, Fredericton, NB E3B 5A3, Canada
| | - Bich Ngoc Nguyen
- University of Montreal Hospital Center, Montreal, QC H2X 0C2, Canada
| | - Dimitris Samaras
- Department of Computer Science, Stony Brook University, Stony Brook, NY 11794, United States
| | - Konstantinos N Plataniotis
- The Edward S. Rogers Sr. Department of Electrical & Computer Engineering (ECE), University of Toronto, Toronto, ON M5S 3G4, Canada
| |
Collapse
|
2
|
Border SP, Tomaszewski JE, Yoshida T, Kopp JB, Hodgin JB, Clapp WL, Rosenberg AZ, Buyon JP, Sarder P. Investigating quantitative histological characteristics in renal pathology using HistoLens. Sci Rep 2024; 14:17528. [PMID: 39080444 PMCID: PMC11289473 DOI: 10.1038/s41598-024-68406-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/12/2024] [Accepted: 07/23/2024] [Indexed: 08/02/2024] Open
Abstract
HistoLens is an open-source graphical user interface developed using MATLAB AppDesigner for visual and quantitative analysis of histological datasets. HistoLens enables users to interrogate sets of digitally annotated whole slide images to efficiently characterize histological differences between disease and experimental groups. Users can dynamically visualize the distribution of 448 hand-engineered features quantifying color, texture, morphology, and distribution across microanatomic sub-compartments. Additionally, users can map differentially detected image features within the images by highlighting affected regions. We demonstrate the utility of HistoLens to identify hand-engineered features that correlate with pathognomonic renal glomerular characteristics distinguishing diabetic nephropathy and amyloid nephropathy from the histologically unremarkable glomeruli in minimal change disease. Additionally, we examine the use of HistoLens for glomerular feature discovery in the Tg26 mouse model of HIV-associated nephropathy. We identify numerous quantitative glomerular features distinguishing Tg26 transgenic mice from wild-type mice, corresponding to a progressive renal disease phenotype. Thus, we demonstrate an off-the-shelf and ready-to-use toolkit for quantitative renal pathology applications.
Collapse
Affiliation(s)
- Samuel P Border
- Section of Quantitative Health, Division of Nephrology, Hypertension, and Renal Transplantation, Department of Medicine, University of Florida, 1600 SW Archer Rd., Gainesville, FL, 32608, USA
| | - John E Tomaszewski
- Department of Pathology & Anatomical Sciences, University at Buffalo, Buffalo, NY, USA
| | - Teruhiko Yoshida
- Kidney Disease Section, Kidney Diseases Branch, National Institute of Diabetes and Digestive and Kidney Diseases, National Institutes of Health, Bethesda, MD, USA
| | - Jeffrey B Kopp
- Kidney Disease Section, Kidney Diseases Branch, National Institute of Diabetes and Digestive and Kidney Diseases, National Institutes of Health, Bethesda, MD, USA
| | - Jeffrey B Hodgin
- Department of Pathology, University of Michigan, Ann Arbor, MI, USA
| | - William L Clapp
- Department of Pathology, Immunology and Laboratory Medicine, University of Florida, Gainesville, FL, USA
| | - Avi Z Rosenberg
- Department of Pathology, Johns Hopkins Medical Institutions, Baltimore, MD, USA
| | - Jill P Buyon
- New York University Grossman School of Medicine, New York, NY, USA
| | - Pinaki Sarder
- Section of Quantitative Health, Division of Nephrology, Hypertension, and Renal Transplantation, Department of Medicine, University of Florida, 1600 SW Archer Rd., Gainesville, FL, 32608, USA.
| |
Collapse
|
3
|
Hu D, Jiang Z, Shi J, Xie F, Wu K, Tang K, Cao M, Huai J, Zheng Y. Histopathology language-image representation learning for fine-grained digital pathology cross-modal retrieval. Med Image Anal 2024; 95:103163. [PMID: 38626665 DOI: 10.1016/j.media.2024.103163] [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: 05/30/2023] [Revised: 03/09/2024] [Accepted: 04/02/2024] [Indexed: 04/18/2024]
Abstract
Large-scale digital whole slide image (WSI) datasets analysis have gained significant attention in computer-aided cancer diagnosis. Content-based histopathological image retrieval (CBHIR) is a technique that searches a large database for data samples matching input objects in both details and semantics, offering relevant diagnostic information to pathologists. However, the current methods are limited by the difficulty of gigapixels, the variable size of WSIs, and the dependence on manual annotations. In this work, we propose a novel histopathology language-image representation learning framework for fine-grained digital pathology cross-modal retrieval, which utilizes paired diagnosis reports to learn fine-grained semantics from the WSI. An anchor-based WSI encoder is built to extract hierarchical region features and a prompt-based text encoder is introduced to learn fine-grained semantics from the diagnosis reports. The proposed framework is trained with a multivariate cross-modal loss function to learn semantic information from the diagnosis report at both the instance level and region level. After training, it can perform four types of retrieval tasks based on the multi-modal database to support diagnostic requirements. We conducted experiments on an in-house dataset and a public dataset to evaluate the proposed method. Extensive experiments have demonstrated the effectiveness of the proposed method and its advantages to the present histopathology retrieval methods. The code is available at https://github.com/hudingyi/FGCR.
Collapse
Affiliation(s)
- Dingyi Hu
- Beijing Advanced Innovation Center for Biomedical Engineering, School of Engineering Medicine, Beihang University, Beijing, 100191, China; Image Processing Center, School of Astronautics, Beihang University, Beijing, 100191, China
| | - Zhiguo Jiang
- Beijing Advanced Innovation Center for Biomedical Engineering, School of Engineering Medicine, Beihang University, Beijing, 100191, China; Image Processing Center, School of Astronautics, Beihang University, Beijing, 100191, China
| | - Jun Shi
- School of Software, Hefei University of Technology, Hefei 230601, China
| | - Fengying Xie
- Beijing Advanced Innovation Center for Biomedical Engineering, School of Engineering Medicine, Beihang University, Beijing, 100191, China; Image Processing Center, School of Astronautics, Beihang University, Beijing, 100191, China
| | - Kun Wu
- Beijing Advanced Innovation Center for Biomedical Engineering, School of Engineering Medicine, Beihang University, Beijing, 100191, China; Image Processing Center, School of Astronautics, Beihang University, Beijing, 100191, China
| | - Kunming Tang
- Beijing Advanced Innovation Center for Biomedical Engineering, School of Engineering Medicine, Beihang University, Beijing, 100191, China; Image Processing Center, School of Astronautics, Beihang University, Beijing, 100191, China
| | - Ming Cao
- Department of Pathology, the First People's Hospital of Wuhu, China
| | - Jianguo Huai
- Department of Pathology, the First People's Hospital of Wuhu, China
| | - Yushan Zheng
- Beijing Advanced Innovation Center for Biomedical Engineering, School of Engineering Medicine, Beihang University, Beijing, 100191, China.
| |
Collapse
|
4
|
Denic A, Buglioni A, Turkevi-Nagy S, Mejia MV, Smith BH, Park WD, Subramani R, Kukla A, Diwan TS, Grande JP, Stegall MD. Mesangial Expansion by Morphometry at 5 y After Kidney Transplantation: Incidence, Risk Factors, and Association With Graft Loss. Transplant Direct 2024; 10:e1652. [PMID: 38881746 PMCID: PMC11177838 DOI: 10.1097/txd.0000000000001652] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/20/2024] [Accepted: 03/06/2024] [Indexed: 06/18/2024] Open
Abstract
Background Mesangial expansion (ME) is an understudied histologic lesion in renal allografts. The current Banff mm score is not reproducible and may miss important ME features. The study aimed to improve the quantification of ME using morphometry, assess changes over time, and determine its association with allograft loss. Methods We studied ME in 1-y and 5-y surveillance biopsies in 835 kidney transplants performed between January 2000 and December 2013. ME was assessed using the Banff mm score by a central pathologist and by morphometry. We derived 3 different morphometric measures: (1) %ME mm (%glomeruli with ME in ≥2 lobules, like Banff mm); (2) %MEany (%glomeruli with any ME lesion); and (3) %ME area (sum of all ME areas/all glomerular tuft areas). Unadjusted and adjusted Cox models assessed the risk of death-censored allograft loss. Results From 1- to 5-y biopsies, the mean Banff mm score increased from 0.18 to 0.34, whereas %ME mm increased from 2.5% to 13.3%. Banff mm score had modest correlations with morphometric ME measures. Moderate-severe %ME mm was present in 20.1% of 5-y biopsies, whereas only 6.6% of Banff mm scores were. In general, higher ME on both 1- and 5-y biopsies was associated with a deceased donor, older recipient age, recipient diabetes/obesity (present in >50% of severely affected biopsies), higher hemoglobin A1c at 5 y posttransplant, and recurrent kidney disease. Higher ME on 5-y biopsies was associated with delayed graft function. A higher Banff mm score at 1-y biopsy and morphometry ME measures at 5-y biopsy were associated with rejection during the first year posttransplant. Morphometric ME measures were associated with allograft loss independent of Banff scores and all clinical characteristics, including kidney function and recurrent disease. The model with %MEany had the highest c-statistic (0.872). Conclusions Banff mm score underestimates the pervasiveness of ME in 5-y biopsies. ME is common and associated with alloimmune and nonalloimmune causes of graft loss.
Collapse
Affiliation(s)
- Aleksandar Denic
- Division of Nephrology and Hypertension, Mayo Clinic, Rochester, MN
| | - Alessia Buglioni
- Department of Laboratory Medicine and Pathology, Mayo Clinic, Rochester, MN
| | - Sandor Turkevi-Nagy
- Department of Pathology, Albert Szent-Györgyi Health Centre, University of Szeged, Szeged, Hungary
| | | | - Byron H Smith
- Division of Biomedical Statistics and Informatics, Mayo Clinic, Rochester, MN
| | - Walter D Park
- Departments of Surgery and Immunology, Mayo Clinic, Rochester, MN
| | - Rashmi Subramani
- Division of Nephrology and Hypertension, Mayo Clinic, Rochester, MN
| | - Aleksandra Kukla
- Division of Nephrology and Hypertension, Mayo Clinic, Rochester, MN
| | - Tayyab S Diwan
- Departments of Surgery and Immunology, Mayo Clinic, Rochester, MN
| | - Joseph P Grande
- Department of Laboratory Medicine and Pathology, Mayo Clinic, Rochester, MN
| | - Mark D Stegall
- Departments of Surgery and Immunology, Mayo Clinic, Rochester, MN
| |
Collapse
|
5
|
El-Achkar TM, Eadon MT, Kretzler M, Himmelfarb J. Precision Medicine in Nephrology: An Integrative Framework of Multidimensional Data in the Kidney Precision Medicine Project. Am J Kidney Dis 2024; 83:402-410. [PMID: 37839688 PMCID: PMC10922684 DOI: 10.1053/j.ajkd.2023.08.015] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/17/2023] [Revised: 08/20/2023] [Accepted: 08/25/2023] [Indexed: 10/17/2023]
Abstract
Chronic kidney disease (CKD) and acute kidney injury (AKI) are heterogeneous syndromes defined clinically by serial measures of kidney function. Each condition possesses strong histopathologic associations, including glomerular obsolescence or acute tubular necrosis, respectively. Despite such characterization, there remains wide variation in patient outcomes and treatment responses. Precision medicine efforts, as exemplified by the Kidney Precision Medicine Project (KPMP), have begun to establish evolving, spatially anchored, cellular and molecular atlases of the cell types, states, and niches of the kidney in health and disease. The KPMP atlas provides molecular context for CKD and AKI disease drivers and will help define subtypes of disease that are not readily apparent from canonical functional or histopathologic characterization but instead are appreciable through advanced clinical phenotyping, pathomic, transcriptomic, proteomic, epigenomic, and metabolomic interrogation of kidney biopsy samples. This perspective outlines the structure of the KPMP, its approach to the integration of these diverse datasets, and its major outputs relevant to future patient care.
Collapse
Affiliation(s)
- Tarek M El-Achkar
- Division of Nephrology, School of Medicine, Indiana University, and Richard L. Roudebush Veteran Affairs Medical Center, Indianapolis, Indiana
| | - Michael T Eadon
- Division of Nephrology, School of Medicine, Indiana University, and Richard L. Roudebush Veteran Affairs Medical Center, Indianapolis, Indiana
| | - Matthias Kretzler
- Department of Computational Medicine & Bioinformatics, and Division of Nephrology, Department of Internal Medicine, University of Michigan, Ann Arbor, Michigan
| | - Jonathan Himmelfarb
- Kidney Research Institute and Division of Nephrology, University of Washington, Seattle, Washington.
| |
Collapse
|
6
|
Chelebian E, Avenel C, Ciompi F, Wählby C. DEPICTER: Deep representation clustering for histology annotation. Comput Biol Med 2024; 170:108026. [PMID: 38308865 DOI: 10.1016/j.compbiomed.2024.108026] [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: 09/19/2023] [Revised: 01/24/2024] [Accepted: 01/24/2024] [Indexed: 02/05/2024]
Abstract
Automatic segmentation of histopathology whole-slide images (WSI) usually involves supervised training of deep learning models with pixel-level labels to classify each pixel of the WSI into tissue regions such as benign or cancerous. However, fully supervised segmentation requires large-scale data manually annotated by experts, which can be expensive and time-consuming to obtain. Non-fully supervised methods, ranging from semi-supervised to unsupervised, have been proposed to address this issue and have been successful in WSI segmentation tasks. But these methods have mainly been focused on technical advancements in algorithmic performance rather than on the development of practical tools that could be used by pathologists or researchers in real-world scenarios. In contrast, we present DEPICTER (Deep rEPresentatIon ClusTERing), an interactive segmentation tool for histopathology annotation that produces a patch-wise dense segmentation map at WSI level. The interactive nature of DEPICTER leverages self- and semi-supervised learning approaches to allow the user to participate in the segmentation producing reliable results while reducing the workload. DEPICTER consists of three steps: first, a pretrained model is used to compute embeddings from image patches. Next, the user selects a number of benign and cancerous patches from the multi-resolution image. Finally, guided by the deep representations, label propagation is achieved using our novel seeded iterative clustering method or by directly interacting with the embedding space via feature space gating. We report both real-time interaction results with three pathologists and evaluate the performance on three public cancer classification dataset benchmarks through simulations. The code and demos of DEPICTER are publicly available at https://github.com/eduardchelebian/depicter.
Collapse
Affiliation(s)
- Eduard Chelebian
- Department of Information Technology and SciLifeLab, Uppsala University, Uppsala, Sweden.
| | - Chirstophe Avenel
- Department of Information Technology and SciLifeLab, Uppsala University, Uppsala, Sweden
| | - Francesco Ciompi
- Department of Pathology, Radboud University Medical Center, Nijmegen, The Netherlands
| | - Carolina Wählby
- Department of Information Technology and SciLifeLab, Uppsala University, Uppsala, Sweden
| |
Collapse
|
7
|
Mimar S, Paul AS, Lucarelli N, Border S, Naglah A, Barisoni L, Hodgin J, Rosenberg AZ, Clapp W, Sarder P. ComPRePS: An Automated Cloud-based Image Analysis tool to democratize AI in Digital Pathology. PROCEEDINGS OF SPIE--THE INTERNATIONAL SOCIETY FOR OPTICAL ENGINEERING 2024; 12933:129330Z. [PMID: 38813089 PMCID: PMC11136532 DOI: 10.1117/12.3008469] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/31/2024]
Abstract
Artificial intelligence (AI) has extensive applications in a wide range of disciplines including healthcare and clinical practice. Advances in high-resolution whole-slide brightfield microscopy allow for the digitization of histologically stained tissue sections, producing gigapixel-scale whole-slide images (WSI). The significant improvement in computing and revolution of deep neural network (DNN)-based AI technologies over the last decade allow us to integrate massively parallelized computational power, cutting-edge AI algorithms, and big data storage, management, and processing. Applied to WSIs, AI has created opportunities for improved disease diagnostics and prognostics with the ultimate goal of enhancing precision medicine and resulting patient care. The National Institutes of Health (NIH) has recognized the importance of developing standardized principles for data management and discovery for the advancement of science and proposed the Findable, Accessible, Interoperable, Reusable, (FAIR) Data Principles1 with the goal of building a modernized biomedical data resource ecosystem to establish collaborative research communities. In line with this mission and to democratize AI-based image analysis in digital pathology, we propose ComPRePS: an end-to-end automated Computational Renal Pathology Suite which combines massive scalability, on-demand cloud computing, and an easy-to-use web-based user interface for data upload, storage, management, slide-level visualization, and domain expert interaction. Moreover, our platform is equipped with both in-house and collaborator developed sophisticated AI algorithms in the back-end server for image analysis to identify clinically relevant micro-anatomic functional tissue units (FTU) and to extract image features.
Collapse
Affiliation(s)
- Sayat Mimar
- Quantitative Health Section, Division of Nephrology, Hypertension, and Renal Transplantation, Department of Medicine, University of Florida, Gainesville, FL
| | - Anindya S. Paul
- Quantitative Health Section, Division of Nephrology, Hypertension, and Renal Transplantation, Department of Medicine, University of Florida, Gainesville, FL
| | - Nicholas Lucarelli
- Quantitative Health Section, Division of Nephrology, Hypertension, and Renal Transplantation, Department of Medicine, University of Florida, Gainesville, FL
| | - Samuel Border
- Quantitative Health Section, Division of Nephrology, Hypertension, and Renal Transplantation, Department of Medicine, University of Florida, Gainesville, FL
| | - Ahmed Naglah
- Quantitative Health Section, Division of Nephrology, Hypertension, and Renal Transplantation, Department of Medicine, University of Florida, Gainesville, FL
| | - Laura Barisoni
- Duke University, Department of Pathology, Division of AI & Computational Pathology, Durham, NC
| | - Jeffrey Hodgin
- Department of Pathology, University of Michigan, Ann Arbor, MI
| | - Avi Z Rosenberg
- Department of Pathology, Johns Hopkins University, Baltimore, MD
| | - William Clapp
- Department of Pathology, Immunology and Laboratory Medicine, University of Florida College of Medicine, Gainesville, FL
| | - Pinaki Sarder
- Quantitative Health Section, Division of Nephrology, Hypertension, and Renal Transplantation, Department of Medicine, University of Florida, Gainesville, FL
| |
Collapse
|
8
|
Lutnick B, Ramon AJ, Ginley B, Csiszer C, Kim A, Flament I, Damasceno PF, Cornibe J, Parmar C, Standish K, Carrasco-Zevallos O, Yip SS. Accelerating pharmaceutical R&D with a user-friendly AI system for histopathology image analysis. J Pathol Inform 2023; 14:100337. [PMID: 37860714 PMCID: PMC10582575 DOI: 10.1016/j.jpi.2023.100337] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/22/2023] [Revised: 08/08/2023] [Accepted: 09/19/2023] [Indexed: 10/21/2023] Open
Abstract
A system for analysis of histopathology data within a pharmaceutical R&D environment has been developed with the intention of enabling interdisciplinary collaboration. State-of-the-art AI tools have been deployed as easy-to-use self-service modules within an open-source whole slide image viewing platform, so that non-data scientist users (e.g., clinicians) can utilize and evaluate pre-trained algorithms and retrieve quantitative results. The outputs of analysis are automatically cataloged in the database to track data provenance and can be viewed interactively on the slide as annotations or heatmaps. Commonly used models for analysis of whole slide images including segmentation, extraction of hand-engineered features for segmented regions, and slide-level classification using multi-instance learning are included and new models can be added as needed. The source code that supports running inference with these models internally is backed up by a robust CI/CD pipeline to ensure model versioning, robust testing, and seamless deployment of the latest models. Examples of the use of this system in a pharmaceutical development workflow include glomeruli segmentation, enumeration of podocyte count from WT-1 immuno-histochemistry, measurement of beta-1 integrin target engagement from immunofluorescence, digital glomerular phenotyping from periodic acid-Schiff histology, PD-L1 score prediction using multi-instance learning, and the deployment of the open-source Segment Anything model to speed up annotation.
Collapse
Affiliation(s)
| | | | | | | | - Alex Kim
- Janssen R&D, Data Sciences, Raritan, NJ 08869, USA
| | - Io Flament
- Janssen R&D, Data Sciences, Raritan, NJ 08869, USA
| | | | | | | | | | | | | |
Collapse
|
9
|
Denic A, Gaddam M, Moustafa A, Mullan AF, Luehrs AC, Sharma V, Thompson RH, Smith ML, Alexander MP, Lerman LO, Barisoni L, Rule AD. Tubular and Glomerular Size by Cortex Depth as Predictor of Progressive CKD after Radical Nephrectomy for Tumor. J Am Soc Nephrol 2023; 34:1535-1545. [PMID: 37430426 PMCID: PMC10482069 DOI: 10.1681/asn.0000000000000180] [Citation(s) in RCA: 7] [Impact Index Per Article: 7.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/29/2023] [Accepted: 06/08/2023] [Indexed: 07/12/2023] Open
Abstract
SIGNIFICANCE STATEMENT Glomerular size differs by cortex depth. Larger nephrons are prognostic of progressive kidney disease, but it is unknown whether this risk differs by cortex depth or by glomeruli versus proximal or distal tubule size. We studied the average minor axis diameter in oval proximal and distal tubules separately and by cortex depth in patients who had radical nephrectomy to remove a tumor from 2019 to 2020. In adjusted analyses, larger glomerular volume in the middle and deep cortex predicted progressive kidney disease. Wider proximal tubular diameter did not predict progressive kidney disease independent of glomerular volume. Wider distal tubular diameter showed a gradient of strength of prediction of progressive kidney disease in the more superficial cortex than in the deep cortex. BACKGROUND Larger nephrons are prognostic of progressive kidney disease, but whether this risk differs by nephron segments or by depth in the cortex is unclear. METHODS We studied patients who underwent radical nephrectomy for a tumor between 2000 and 2019. Large wedge kidney sections were scanned into digital images. We estimated the diameters of proximal and distal tubules by the minor axis of oval tubular profiles and estimated glomerular volume with the Weibel-Gomez stereological model. Analyses were performed separately in the superficial, middle, and deep cortex. Cox proportional hazard models assessed the risk of progressive CKD (dialysis, kidney transplantation, sustained eGFR <10 ml/min per 1.73 m 2 , or a sustained 40% decline from the postnephrectomy baseline eGFR) with glomerular volume or tubule diameters. At each cortical depth, models were unadjusted, adjusted for glomerular volume or tubular diameter, and further adjusted for clinical characteristics (age, sex, body mass index, hypertension, diabetes, postnephrectomy baseline eGFR, and proteinuria). RESULTS Among 1367 patients were 62 progressive CKD events during a median follow-up of 4.5 years. Glomerular volume predicted CKD outcomes at all depths, but only in the middle and deep cortex after adjusted analyses. Proximal tubular diameter also predicted progressive CKD at any depth but not after adjusted analyses. Distal tubular diameter showed a gradient of more strongly predicting progressive CKD in the superficial than deep cortex, even in adjusted analysis. CONCLUSIONS Larger glomeruli are independent predictors of progressive CKD in the deeper cortex, whereas in the superficial cortex, wider distal tubular diameters are an independent predictor of progressive CKD.
Collapse
Affiliation(s)
- Aleksandar Denic
- Division of Nephrology and Hypertension, Mayo Clinic, Rochester, Minnesota
| | - Mrunanjali Gaddam
- Division of Nephrology and Hypertension, Mayo Clinic, Rochester, Minnesota
| | - Amr Moustafa
- Division of Nephrology and Hypertension, Mayo Clinic, Rochester, Minnesota
| | - Aidan F. Mullan
- Division of Biomedical Statistics and Informatics, Mayo Clinic, Rochester, Minnesota
| | - Anthony C. Luehrs
- Division of Biomedical Statistics and Informatics, Mayo Clinic, Rochester, Minnesota
| | - Vidit Sharma
- Department of Urology, Mayo Clinic, Rochester, Minnesota
| | | | - Maxwell L. Smith
- Department of Laboratory Medicine and Pathology, Mayo Clinic, Scottsdale, Arizona
| | - Mariam P. Alexander
- Department of Laboratory Medicine and Pathology, Mayo Clinic, Rochester, Minnesota
| | - Lilach O. Lerman
- Division of Nephrology and Hypertension, Mayo Clinic, Rochester, Minnesota
| | - Laura Barisoni
- Department of Pathology and Medicine, Duke University, Durham, North Carolina
| | - Andrew D. Rule
- Division of Nephrology and Hypertension, Mayo Clinic, Rochester, Minnesota
- Division of Epidemiology, Mayo Clinic, Rochester, Minnesota
| |
Collapse
|
10
|
Jain S, Pei L, Spraggins JM, Angelo M, Carson JP, Gehlenborg N, Ginty F, Gonçalves JP, Hagood JS, Hickey JW, Kelleher NL, Laurent LC, Lin S, Lin Y, Liu H, Naba A, Nakayasu ES, Qian WJ, Radtke A, Robson P, Stockwell BR, Van de Plas R, Vlachos IS, Zhou M, Börner K, Snyder MP. Advances and prospects for the Human BioMolecular Atlas Program (HuBMAP). Nat Cell Biol 2023; 25:1089-1100. [PMID: 37468756 PMCID: PMC10681365 DOI: 10.1038/s41556-023-01194-w] [Citation(s) in RCA: 30] [Impact Index Per Article: 30.0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/06/2023] [Accepted: 06/22/2023] [Indexed: 07/21/2023]
Abstract
The Human BioMolecular Atlas Program (HuBMAP) aims to create a multi-scale spatial atlas of the healthy human body at single-cell resolution by applying advanced technologies and disseminating resources to the community. As the HuBMAP moves past its first phase, creating ontologies, protocols and pipelines, this Perspective introduces the production phase: the generation of reference spatial maps of functional tissue units across many organs from diverse populations and the creation of mapping tools and infrastructure to advance biomedical research.
Collapse
Affiliation(s)
- Sanjay Jain
- Department of Medicine, Washington University School of Medicine, St Louis, MO, USA.
- Department of Pediatrics, Washington University School of Medicine, St Louis, MO, USA.
- Department of Pathology and Immunology, Washington University School of Medicine, St. Louis, MO, USA.
| | - Liming Pei
- Center for Mitochondrial and Epigenomic Medicine, Department of Pathology and Laboratory Medicine, Children's Hospital of Philadelphia, and Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA.
| | - Jeffrey M Spraggins
- Department of Cell and Developmental Biology and the Mass Spectrometry Research Center, Vanderbilt University School of Medicine, Nashville, TN, USA.
| | - Michael Angelo
- Department of Pathology, Stanford School of Medicine, Stanford, CA, USA
| | - James P Carson
- Texas Advanced Computing Center, University of Texas at Austin, Austin, TX, USA
| | - Nils Gehlenborg
- Department of Biomedical Informatics, Harvard Medical School, Boston, MA, USA
| | | | - Joana P Gonçalves
- Department of Intelligent Systems, Delft University of Technology, Delft, Netherlands
| | - James S Hagood
- Department of Pediatrics (Pulmonology) and Program for Rare and Interstitial Lung Disease, University of North Carolina at Chapel Hill, Chapel Hill, NC, USA
| | - John W Hickey
- Department of Microbiology and Immunology, Stanford University, Stanford, CA, USA
| | - Neil L Kelleher
- Departments of Medicine, Chemistry and Molecular Biosciences, Northwestern University, Evanston, IL, USA
| | - Louise C Laurent
- Department of Obstetrics, Gynecology, and Reproductive Sciences, University of California, San Diego, La Jolla, CA, USA
| | - Shin Lin
- Division of Cardiology, University of Washington School of Medicine, Seattle, WA, USA
| | - Yiing Lin
- Department of Surgery, Washington University School of Medicine, St Louis, MO, USA
| | - Huiping Liu
- Departments of Pharmacology, Medicine (Hematology and Oncology), Lurie Cancer Center, Northwestern University Feinberg School of Medicine, Chicago, IL, USA
| | - Alexandra Naba
- Department of Physiology and Biophysics, University of Illinois at Chicago, Chicago, IL, USA
| | - Ernesto S Nakayasu
- Biological Sciences Division, Pacific Northwest National Laboratory, Richland, WA, USA
| | - Wei-Jun Qian
- Biological Sciences Division, Pacific Northwest National Laboratory, Richland, WA, USA
| | - Andrea Radtke
- Lymphocyte Biology Section and Center for Advanced Tissue Imaging, Laboratory of Immune System Biology, NIAID, NIH, Bethesda, MD, USA
| | - Paul Robson
- The Jackson Laboratory for Genomic Medicine, Farmington, CT, USA
| | - Brent R Stockwell
- Department of Biological Sciences and Department of Chemistry, Columbia University, New York, NY, USA
| | - Raf Van de Plas
- Delft Center for Systems and Control, Delft University of Technology, Delft, Netherlands
| | - Ioannis S Vlachos
- Broad Institute of MIT and Harvard, Cambridge, MA, USA
- Spatial Technologies Unit, Harvard Medical School Initiative for RNA Medicine, Department of Pathology, Beth Israel Deaconess Medical Center, and Harvard Medical School, Boston, MA, USA
| | - Mowei Zhou
- Environmental Molecular Sciences Laboratory, Pacific Northwest National Laboratory, Richland, WA, USA
| | - Katy Börner
- Department of Intelligent Systems Engineering, Indiana University, Bloomington, IN, USA.
| | - Michael P Snyder
- Department of Genetics, Stanford School of Medicine, Stanford, CA, USA.
| |
Collapse
|
11
|
Asif A, Rajpoot K, Graham S, Snead D, Minhas F, Rajpoot N. Unleashing the potential of AI for pathology: challenges and recommendations. J Pathol 2023; 260:564-577. [PMID: 37550878 PMCID: PMC10952719 DOI: 10.1002/path.6168] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/16/2023] [Revised: 06/21/2023] [Accepted: 06/22/2023] [Indexed: 08/09/2023]
Abstract
Computational pathology is currently witnessing a surge in the development of AI techniques, offering promise for achieving breakthroughs and significantly impacting the practices of pathology and oncology. These AI methods bring with them the potential to revolutionize diagnostic pipelines as well as treatment planning and overall patient care. Numerous peer-reviewed studies reporting remarkable performance across diverse tasks serve as a testimony to the potential of AI in the field. However, widespread adoption of these methods in clinical and pre-clinical settings still remains a challenge. In this review article, we present a detailed analysis of the major obstacles encountered during the development of effective models and their deployment in practice. We aim to provide readers with an overview of the latest developments, assist them with insights into identifying some specific challenges that may require resolution, and suggest recommendations and potential future research directions. © 2023 The Authors. The Journal of Pathology published by John Wiley & Sons Ltd on behalf of The Pathological Society of Great Britain and Ireland.
Collapse
Affiliation(s)
- Amina Asif
- Tissue Image Analytics Centre, Department of Computer ScienceUniversity of WarwickCoventryUK
| | - Kashif Rajpoot
- School of Computer ScienceUniversity of BirminghamBirminghamUK
| | - Simon Graham
- Histofy Ltd, Birmingham Business ParkBirminghamUK
| | - David Snead
- Histofy Ltd, Birmingham Business ParkBirminghamUK
- Department of PathologyUniversity Hospitals Coventry & Warwickshire NHS TrustCoventryUK
| | - Fayyaz Minhas
- Tissue Image Analytics Centre, Department of Computer ScienceUniversity of WarwickCoventryUK
- Cancer Research CentreUniversity of WarwickCoventryUK
| | - Nasir Rajpoot
- Tissue Image Analytics Centre, Department of Computer ScienceUniversity of WarwickCoventryUK
- Histofy Ltd, Birmingham Business ParkBirminghamUK
- Cancer Research CentreUniversity of WarwickCoventryUK
- The Alan Turing InstituteLondonUK
| |
Collapse
|
12
|
Jain Y, Godwin LL, Ju Y, Sood N, Quardokus EM, Bueckle A, Longacre T, Horning A, Lin Y, Esplin ED, Hickey JW, Snyder MP, Patterson NH, Spraggins JM, Börner K. Segmentation of human functional tissue units in support of a Human Reference Atlas. Commun Biol 2023; 6:717. [PMID: 37468557 PMCID: PMC10356924 DOI: 10.1038/s42003-023-04848-5] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/30/2021] [Accepted: 04/17/2023] [Indexed: 07/21/2023] Open
Abstract
The Human BioMolecular Atlas Program (HuBMAP) aims to compile a Human Reference Atlas (HRA) for the healthy adult body at the cellular level. Functional tissue units (FTUs), relevant for HRA construction, are of pathobiological significance. Manual segmentation of FTUs does not scale; highly accurate and performant, open-source machine-learning algorithms are needed. We designed and hosted a Kaggle competition that focused on development of such algorithms and 1200 teams from 60 countries participated. We present the competition outcomes and an expanded analysis of the winning algorithms on additional kidney and colon tissue data, and conduct a pilot study to understand spatial location and density of FTUs across the kidney. The top algorithm from the competition, Tom, outperforms other algorithms in the expanded study, while using fewer computational resources. Tom was added to the HuBMAP infrastructure to run kidney FTU segmentation at scale-showcasing the value of Kaggle competitions for advancing research.
Collapse
Affiliation(s)
- Yashvardhan Jain
- Department of Intelligent Systems Engineering, Luddy School of Informatics, Computing, and Engineering, Indiana University, Bloomington, IN, 47408, USA.
| | - Leah L Godwin
- Department of Intelligent Systems Engineering, Luddy School of Informatics, Computing, and Engineering, Indiana University, Bloomington, IN, 47408, USA
| | - Yingnan Ju
- Department of Intelligent Systems Engineering, Luddy School of Informatics, Computing, and Engineering, Indiana University, Bloomington, IN, 47408, USA
| | - Naveksha Sood
- Department of Intelligent Systems Engineering, Luddy School of Informatics, Computing, and Engineering, Indiana University, Bloomington, IN, 47408, USA
| | - Ellen M Quardokus
- Department of Intelligent Systems Engineering, Luddy School of Informatics, Computing, and Engineering, Indiana University, Bloomington, IN, 47408, USA
| | - Andreas Bueckle
- Department of Intelligent Systems Engineering, Luddy School of Informatics, Computing, and Engineering, Indiana University, Bloomington, IN, 47408, USA
| | - Teri Longacre
- Department of Pathology, Stanford University School of Medicine, Stanford, CA, 94305, USA
| | - Aaron Horning
- Thermo Fisher Scientific, South San Francisco, CA, 94080, USA
| | - Yiing Lin
- Department of Surgery, Washington University School of Medicine, St. Louis, MO, 63110, USA
| | - Edward D Esplin
- Department of Genetics, Stanford University School of Medicine, Stanford, CA, 94305, USA
| | - John W Hickey
- Department of Microbiology & Immunology, Stanford University School of Medicine, Stanford, CA, 94305, USA
| | - Michael P Snyder
- Department of Genetics, Stanford University School of Medicine, Stanford, CA, 94305, USA
| | | | - Jeffrey M Spraggins
- Mass Spectrometry Research Center, Vanderbilt University, Nashville, TN, 37232, USA
- Department of Cell and Developmental Biology, Vanderbilt University, Nashville, TN, 37232, USA
| | - Katy Börner
- Department of Intelligent Systems Engineering, Luddy School of Informatics, Computing, and Engineering, Indiana University, Bloomington, IN, 47408, USA.
| |
Collapse
|
13
|
Kung VL, Nelson JW. Machine Learning Illuminates the Extraglomerular Microvasculature. KIDNEY360 2023; 4:578-579. [PMID: 37229727 PMCID: PMC10371299 DOI: 10.34067/kid.0000000000000111] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/27/2023]
Affiliation(s)
- Vanderlene L. Kung
- Department of Pathology and Laboratory Medicine, Oregon Health and Science University, Portland, Oregon
| | - Jonathan W. Nelson
- Division of Nephrology and Hypertension, Oregon Health and Science University, Portland, Oregon
| |
Collapse
|
14
|
McElliott MC, Al-Suraimi A, Telang AC, Ference-Salo JT, Chowdhury M, Soofi A, Dressler GR, Beamish JA. High-throughput image analysis with deep learning captures heterogeneity and spatial relationships after kidney injury. Sci Rep 2023; 13:6361. [PMID: 37076596 PMCID: PMC10115810 DOI: 10.1038/s41598-023-33433-3] [Citation(s) in RCA: 3] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/20/2022] [Accepted: 04/12/2023] [Indexed: 04/21/2023] Open
Abstract
Recovery from acute kidney injury can vary widely in patients and in animal models. Immunofluorescence staining can provide spatial information about heterogeneous injury responses, but often only a fraction of stained tissue is analyzed. Deep learning can expand analysis to larger areas and sample numbers by substituting for time-intensive manual or semi-automated quantification techniques. Here we report one approach to leverage deep learning tools to quantify heterogenous responses to kidney injury that can be deployed without specialized equipment or programming expertise. We first demonstrated that deep learning models generated from small training sets accurately identified a range of stains and structures with performance similar to that of trained human observers. We then showed this approach accurately tracks the evolution of folic acid induced kidney injury in mice and highlights spatially clustered tubules that fail to repair. We then demonstrated that this approach captures the variation in recovery across a robust sample of kidneys after ischemic injury. Finally, we showed markers of failed repair after ischemic injury were correlated both spatially within and between animals and that failed repair was inversely correlated with peritubular capillary density. Combined, we demonstrate the utility and versatility of our approach to capture spatially heterogenous responses to kidney injury.
Collapse
Affiliation(s)
- Madison C McElliott
- Division of Nephrology, Department of Internal Medicine, University of Michigan, 1500 E. Medical Center Drive, SPC 5364, Ann Arbor, MI, 48109, USA
| | - Anas Al-Suraimi
- Division of Nephrology, Department of Internal Medicine, University of Michigan, 1500 E. Medical Center Drive, SPC 5364, Ann Arbor, MI, 48109, USA
| | - Asha C Telang
- Division of Nephrology, Department of Internal Medicine, University of Michigan, 1500 E. Medical Center Drive, SPC 5364, Ann Arbor, MI, 48109, USA
| | - Jenna T Ference-Salo
- Division of Nephrology, Department of Internal Medicine, University of Michigan, 1500 E. Medical Center Drive, SPC 5364, Ann Arbor, MI, 48109, USA
| | - Mahboob Chowdhury
- Division of Nephrology, Department of Internal Medicine, University of Michigan, 1500 E. Medical Center Drive, SPC 5364, Ann Arbor, MI, 48109, USA
| | - Abdul Soofi
- Department of Pathology, University of Michigan, Ann Arbor, MI, USA
| | | | - Jeffrey A Beamish
- Division of Nephrology, Department of Internal Medicine, University of Michigan, 1500 E. Medical Center Drive, SPC 5364, Ann Arbor, MI, 48109, USA.
| |
Collapse
|
15
|
Shickel B, Lucarelli N, Rao A, Yun D, Moon KC, Han SS, Sarder P. Spatially Aware Transformer Networks for Contextual Prediction of Diabetic Nephropathy Progression from Whole Slide Images. PROCEEDINGS OF SPIE--THE INTERNATIONAL SOCIETY FOR OPTICAL ENGINEERING 2023; 12471:124710K. [PMID: 37818350 PMCID: PMC10563813 DOI: 10.1117/12.2655266] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 10/12/2023]
Abstract
Diabetic nephropathy (DN) in the context of type 2 diabetes is the leading cause of end-stage renal disease (ESRD) in the United States. DN is graded based on glomerular morphology and has a spatially heterogeneous presentation in kidney biopsies that complicates pathologists' predictions of disease progression. Artificial intelligence and deep learning methods for pathology have shown promise for quantitative pathological evaluation and clinical trajectory estimation; but, they often fail to capture large-scale spatial anatomy and relationships found in whole slide images (WSIs). In this study, we present a transformer-based, multi-stage ESRD prediction framework built upon nonlinear dimensionality reduction, relative Euclidean pixel distance embeddings between every pair of observable glomeruli, and a corresponding spatial self-attention mechanism for a robust contextual representation. We developed a deep transformer network for encoding WSI and predicting future ESRD using a dataset of 56 kidney biopsy WSIs from DN patients at Seoul National University Hospital. Using a leave-one-out cross-validation scheme, our modified transformer framework outperformed RNNs, XGBoost, and logistic regression baseline models, and resulted in an area under the receiver operating characteristic curve (AUC) of 0.97 (95% CI: 0.90-1.00) for predicting two-year ESRD, compared with an AUC of 0.86 (95% CI: 0.66-0.99) without our relative distance embedding, and an AUC of 0.76 (95% CI: 0.59-0.92) without a denoising autoencoder module. While the variability and generalizability induced by smaller sample sizes are challenging, our distance-based embedding approach and overfitting mitigation techniques yielded results that suggest opportunities for future spatially aware WSI research using limited pathology datasets.
Collapse
Affiliation(s)
- Benjamin Shickel
- Dept. of Medicine, University of Florida, Gainesville, FL, USA
- Univ. of Florida Intelligent Critical Care Center, Gainesville, FL, USA
| | | | - Adish Rao
- Dept. of Computer and Information Science and Engineering, Univ. of Florida, Gainesville, FL
| | - Donghwan Yun
- Dept. of Internal Medicine, Seoul National Univ. College of Medicine, Seoul, Korea
| | - Kyung Chul Moon
- Dept. of Internal Medicine, Seoul National Univ. College of Medicine, Seoul, Korea
| | - Seung Seok Han
- Dept. of Internal Medicine, Seoul National Univ. College of Medicine, Seoul, Korea
| | - Pinaki Sarder
- Dept. of Medicine, University of Florida, Gainesville, FL, USA
- Univ. of Florida Intelligent Critical Care Center, Gainesville, FL, USA
| |
Collapse
|