1
|
Ng DP, Simonson PD, Tarnok A, Lucas F, Kern W, Rolf N, Bogdanoski G, Green C, Brinkman RR, Czechowska K. Recommendations for using artificial intelligence in clinical flow cytometry. CYTOMETRY. PART B, CLINICAL CYTOMETRY 2024; 106:228-238. [PMID: 38407537 DOI: 10.1002/cyto.b.22166] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 08/13/2023] [Revised: 01/16/2024] [Accepted: 02/06/2024] [Indexed: 02/27/2024]
Abstract
Flow cytometry is a key clinical tool in the diagnosis of many hematologic malignancies and traditionally requires close inspection of digital data by hematopathologists with expert domain knowledge. Advances in artificial intelligence (AI) are transferable to flow cytometry and have the potential to improve efficiency and prioritization of cases, reduce errors, and highlight fundamental, previously unrecognized associations with underlying biological processes. As a multidisciplinary group of stakeholders, we review a range of critical considerations for appropriately applying AI to clinical flow cytometry, including use case identification, low and high risk use cases, validation, revalidation, computational considerations, and the present regulatory frameworks surrounding AI in clinical medicine. In particular, we provide practical guidance for the development, implementation, and suggestions for potential regulation of AI-based methods in the clinical flow cytometry laboratory. We expect these recommendations to be a helpful initial framework of reference, which will also require additional updates as the field matures.
Collapse
Affiliation(s)
- David P Ng
- Department of Pathology, University of Utah, Salt Lake City, Utah, USA
| | - Paul D Simonson
- Department of Pathology and Laboratory Medicine, Weill Cornell Medicine, New York, New York, USA
| | - Attila Tarnok
- Department of Preclinical Development and Validation, Fraunhofer Institute for Cell Therapy and Immunology, IZI, Leipzig, Germany
| | - Fabienne Lucas
- Department of Laboratory Medicine and Pathology, University of Washington, Seattle, Washington, USA
| | - Wolfgang Kern
- MLL Munich Leukemia Laboratory GmbH, Munich, Germany
| | - Nina Rolf
- BC Children's Hospital Research Institute, University of British Columbia, Vancouver, British Columbia, Canada
| | - Goce Bogdanoski
- Clinical Development & Operations Quality, R&D Quality, Bristol Myers Squibb, Princeton, New Jersey, USA
| | - Cherie Green
- Translational Science, Ozette Technologies, Seattle, Washington, USA
| | | | | |
Collapse
|
2
|
Dinalankara W, Ng DP, Marchionni L, Simonson PD. Comparison of three machine learning algorithms for classification of B-cell neoplasms using clinical flow cytometry data. CYTOMETRY. PART B, CLINICAL CYTOMETRY 2024; 106:282-293. [PMID: 38721890 DOI: 10.1002/cyto.b.22177] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 11/29/2023] [Revised: 03/22/2024] [Accepted: 04/12/2024] [Indexed: 05/18/2024]
Abstract
Multiparameter flow cytometry data is visually inspected by expert personnel as part of standard clinical disease diagnosis practice. This is a demanding and costly process, and recent research has demonstrated that it is possible to utilize artificial intelligence (AI) algorithms to assist in the interpretive process. Here we report our examination of three previously published machine learning methods for classification of flow cytometry data and apply these to a B-cell neoplasm dataset to obtain predicted disease subtypes. Each of the examined methods classifies samples according to specific disease categories using ungated flow cytometry data. We compare and contrast the three algorithms with respect to their architectures, and we report the multiclass classification accuracies and relative required computation times. Despite different architectures, two of the methods, flowCat and EnsembleCNN, had similarly good accuracies with relatively fast computational times. We note a speed advantage for EnsembleCNN, particularly in the case of addition of training data and retraining of the classifier.
Collapse
Affiliation(s)
- Wikum Dinalankara
- Department of Pathology and Laboratory Medicine, Weill Cornell Medicine, New York, New York, USA
| | - David P Ng
- Department of Pathology, University of Utah, Salt Lake City, Utah, USA
| | - Luigi Marchionni
- Department of Pathology and Laboratory Medicine, Weill Cornell Medicine, New York, New York, USA
| | - Paul D Simonson
- Department of Pathology and Laboratory Medicine, Weill Cornell Medicine, New York, New York, USA
| |
Collapse
|
3
|
Ehinger M, Béné MC. Morphology and multiparameter flow cytometry combined for integrated lymphoma diagnosis on small volume samples: possibilities and limitations. Virchows Arch 2024:10.1007/s00428-024-03819-3. [PMID: 38805049 DOI: 10.1007/s00428-024-03819-3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/10/2024] [Revised: 04/18/2024] [Accepted: 05/02/2024] [Indexed: 05/29/2024]
Abstract
The diagnosis of lymphoma relies mainly on clinical examination and laboratory explorations. Among the latter, morphological and immunohistochemical analysis of a tissue biopsy are the cornerstones for proper identification and classification of the disease. In lymphoma with blood and/or bone marrow involvement, multiparameter flow cytometry is useful. This technique can also be applied to fresh cells released from a biopsy sample. For full comprehension of lymphomas, surgical biopsies are best and indeed recommended by the hematopathological community. Currently, however, there is a global trend towards less invasive procedures, resulting in smaller samples such as core needle biopsies or fine needle aspirations which can make the diagnosis quite challenging. In this review, the possibilities and limitations to make an accurate lymphoma diagnosis on such small volume material are presented. After recalling the major steps of lymphoma diagnosis, the respective value of histology, cytology, and flow cytometry is discussed, including handling of small specimens. The benefits of an integrated approach are then evoked, followed by discussion about which attitude to adopt in different contexts. Perhaps contrary to the prevailing view among many pathologists, a full diagnosis on small volume material, combined with relevant ancillary techniques, is often possible and indeed supported by recent literature. A glimpse at future evolutions, notably the merit of artificial intelligence tools, is finally provided. All in all, this document aims at providing pathologists with an overview of diagnostic possibilities in lymphoma patients when confronted with small volume material such as core needle biopsies or fine needle aspirations.
Collapse
Affiliation(s)
- Mats Ehinger
- Division of Pathology, Department of Clinical Sciences Lund, Lund University, Lund, Sweden.
- Department of Clinical Genetics, Pathology and Molecular Diagnostics, Office for Medical Services, Region Skåne, Lund, Sweden.
| | - Marie C Béné
- Faculty of Medicine, Nantes University, Nantes, France
| |
Collapse
|
4
|
Çubukçu HC, Topcu Dİ, Yenice S. Machine learning-based clinical decision support using laboratory data. Clin Chem Lab Med 2024; 62:793-823. [PMID: 38015744 DOI: 10.1515/cclm-2023-1037] [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: 09/15/2023] [Accepted: 11/17/2023] [Indexed: 11/30/2023]
Abstract
Artificial intelligence (AI) and machine learning (ML) are becoming vital in laboratory medicine and the broader context of healthcare. In this review article, we summarized the development of ML models and how they contribute to clinical laboratory workflow and improve patient outcomes. The process of ML model development involves data collection, data cleansing, feature engineering, model development, and optimization. These models, once finalized, are subjected to thorough performance assessments and validations. Recently, due to the complexity inherent in model development, automated ML tools were also introduced to streamline the process, enabling non-experts to create models. Clinical Decision Support Systems (CDSS) use ML techniques on large datasets to aid healthcare professionals in test result interpretation. They are revolutionizing laboratory medicine, enabling labs to work more efficiently with less human supervision across pre-analytical, analytical, and post-analytical phases. Despite contributions of the ML tools at all analytical phases, their integration presents challenges like potential model uncertainties, black-box algorithms, and deskilling of professionals. Additionally, acquiring diverse datasets is hard, and models' complexity can limit clinical use. In conclusion, ML-based CDSS in healthcare can greatly enhance clinical decision-making. However, successful adoption demands collaboration among professionals and stakeholders, utilizing hybrid intelligence, external validation, and performance assessments.
Collapse
Affiliation(s)
- Hikmet Can Çubukçu
- General Directorate of Health Services, Rare Diseases Department, Turkish Ministry of Health, Ankara, Türkiye
- Hacettepe University Institute of Informatics, Ankara, Türkiye
| | - Deniz İlhan Topcu
- Health Sciences University İzmir Tepecik Education and Research Hospital, Medical Biochemistry, İzmir, Türkiye
| | - Sedef Yenice
- Florence Nightingale Hospital, Istanbul, Türkiye
| |
Collapse
|
5
|
Lu Z, Morita M, Yeager TS, Lyu Y, Wang SY, Wang Z, Fan G. Validation of Artificial Intelligence (AI)-Assisted Flow Cytometry Analysis for Immunological Disorders. Diagnostics (Basel) 2024; 14:420. [PMID: 38396459 PMCID: PMC10888253 DOI: 10.3390/diagnostics14040420] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/22/2024] [Revised: 02/07/2024] [Accepted: 02/13/2024] [Indexed: 02/25/2024] Open
Abstract
Flow cytometry is a vital diagnostic tool for hematologic and immunologic disorders, but manual analysis is prone to variation and time-consuming. Over the last decade, artificial intelligence (AI) has advanced significantly. In this study, we developed and validated an AI-assisted flow cytometry workflow using 379 clinical cases from 2021, employing a 3-tube, 10-color flow panel with 21 antibodies for primary immunodeficiency diseases and related immunological disorders. The AI software (DeepFlow™, version 2.1.1) is fully automated, reducing analysis time to under 5 min per case. It interacts with hematopatholoists for manual gating adjustments when necessary. Using proprietary multidimensional density-phenotype coupling algorithm, the AI model accurately classifies and enumerates T, B, and NK cells, along with important immune cell subsets, including CD4+ helper T cells, CD8+ cytotoxic T cells, CD3+/CD4-/CD8- double-negative T cells, and class-switched or non-switched B cells. Compared to manual analysis with hematopathologist-determined lymphocyte subset percentages as the gold standard, the AI model exhibited a strong correlation (r > 0.9) across lymphocyte subsets. This study highlights the accuracy and efficiency of AI-assisted flow cytometry in diagnosing immunological disorders in a clinical setting, providing a transformative approach within a concise timeframe.
Collapse
Affiliation(s)
- Zhengchun Lu
- Department of Pathology and Laboratory Medicine, Oregon Health & Science University, 3181 SW Sam Jackson Park Road, Portland, OR 97239, USA; (Z.L.); (M.M.); (T.S.Y.); (Y.L.); (S.Y.W.)
| | - Mayu Morita
- Department of Pathology and Laboratory Medicine, Oregon Health & Science University, 3181 SW Sam Jackson Park Road, Portland, OR 97239, USA; (Z.L.); (M.M.); (T.S.Y.); (Y.L.); (S.Y.W.)
| | - Tyler S. Yeager
- Department of Pathology and Laboratory Medicine, Oregon Health & Science University, 3181 SW Sam Jackson Park Road, Portland, OR 97239, USA; (Z.L.); (M.M.); (T.S.Y.); (Y.L.); (S.Y.W.)
| | - Yunpeng Lyu
- Department of Pathology and Laboratory Medicine, Oregon Health & Science University, 3181 SW Sam Jackson Park Road, Portland, OR 97239, USA; (Z.L.); (M.M.); (T.S.Y.); (Y.L.); (S.Y.W.)
| | - Sophia Y. Wang
- Department of Pathology and Laboratory Medicine, Oregon Health & Science University, 3181 SW Sam Jackson Park Road, Portland, OR 97239, USA; (Z.L.); (M.M.); (T.S.Y.); (Y.L.); (S.Y.W.)
| | | | - Guang Fan
- Department of Pathology and Laboratory Medicine, Oregon Health & Science University, 3181 SW Sam Jackson Park Road, Portland, OR 97239, USA; (Z.L.); (M.M.); (T.S.Y.); (Y.L.); (S.Y.W.)
| |
Collapse
|
6
|
Lewis JE, Cooper LAD, Jaye DL, Pozdnyakova O. Automated Deep Learning-Based Diagnosis and Molecular Characterization of Acute Myeloid Leukemia Using Flow Cytometry. Mod Pathol 2024; 37:100373. [PMID: 37925056 DOI: 10.1016/j.modpat.2023.100373] [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: 09/18/2023] [Revised: 10/23/2023] [Accepted: 10/28/2023] [Indexed: 11/06/2023]
Abstract
The current flow cytometric analysis of blood and bone marrow samples for diagnosis of acute myeloid leukemia (AML) relies heavily on manual intervention in the processing and analysis steps, introducing significant subjectivity into resulting diagnoses and necessitating highly trained personnel. Furthermore, concurrent molecular characterization via cytogenetics and targeted sequencing can take multiple days, delaying patient diagnosis and treatment. Attention-based multi-instance learning models (ABMILMs) are deep learning models that make accurate predictions and generate interpretable insights regarding the classification of a sample from individual events/cells; nonetheless, these models have yet to be applied to flow cytometry data. In this study, we developed a computational pipeline using ABMILMs for the automated diagnosis of AML cases based exclusively on flow cytometric data. Analysis of 1820 flow cytometry samples shows that this pipeline provides accurate diagnoses of acute leukemia (area under the receiver operating characteristic curve [AUROC] 0.961) and accurately differentiates AML vs B- and T-lymphoblastic leukemia (AUROC 0.965). Models for prediction of 9 cytogenetic aberrancies and 32 pathogenic variants in AML provide accurate predictions, particularly for t(15;17)(PML::RARA) [AUROC 0.929], t(8;21)(RUNX1::RUNX1T1) (AUROC 0.814), and NPM1 variants (AUROC 0.807). Finally, we demonstrate how these models generate interpretable insights into which individual flow cytometric events and markers deliver optimal diagnostic utility, providing hematopathologists with a data visualization tool for improved data interpretation, as well as novel biological associations between flow cytometric marker expression and cytogenetic/molecular variants in AML. Our study is the first to illustrate the feasibility of using deep learning-based analysis of flow cytometric data for automated AML diagnosis and molecular characterization.
Collapse
Affiliation(s)
- Joshua E Lewis
- Department of Pathology, Brigham and Women's Hospital, Boston, Massachusetts
| | - Lee A D Cooper
- Department of Pathology, Northwestern University, Chicago, Illinois
| | - David L Jaye
- Department of Pathology and Laboratory Medicine, Emory University, Atlanta, Georgia
| | - Olga Pozdnyakova
- Department of Pathology, Brigham and Women's Hospital, Boston, Massachusetts.
| |
Collapse
|
7
|
Lewis JE, Cooper LA, Jaye DL, Pozdnyakova O. Automated Deep Learning-Based Diagnosis and Molecular Characterization of Acute Myeloid Leukemia using Flow Cytometry. BIORXIV : THE PREPRINT SERVER FOR BIOLOGY 2023:2023.09.18.558289. [PMID: 37808719 PMCID: PMC10557578 DOI: 10.1101/2023.09.18.558289] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 10/10/2023]
Abstract
Current flow cytometric analysis of blood and bone marrow samples for diagnosis of acute myeloid leukemia (AML) relies heavily on manual intervention in both the processing and analysis steps, introducing significant subjectivity into resulting diagnoses and necessitating highly trained personnel. Furthermore, concurrent molecular characterization via cytogenetics and targeted sequencing can take multiple days, delaying patient diagnosis and treatment. Attention-based multi-instance learning models (ABMILMs) are deep learning models which make accurate predictions and generate interpretable insights regarding the classification of a sample from individual events/cells; nonetheless, these models have yet to be applied to flow cytometry data. In this study, we developed a computational pipeline using ABMILMs for the automated diagnosis of AML cases based exclusively on flow cytometric data. Analysis of 1,820 flow cytometry samples shows that this pipeline provides accurate diagnoses of acute leukemia [AUROC 0.961] and accurately differentiates AML versus B- and T-lymphoblastic leukemia [AUROC 0.965]. Models for prediction of 9 cytogenetic aberrancies and 32 pathogenic variants in AML provide accurate predictions, particularly for t(15;17)(PML::RARA) [AUROC 0.929], t(8;21)(RUNX1::RUNX1T1) [AUROC 0.814], and NPM1 variants [AUROC 0.807]. Finally, we demonstrate how these models generate interpretable insights into which individual flow cytometric events and markers deliver optimal diagnostic utility, providing hematopathologists with a data visualization tool for improved data interpretation, as well as novel biological associations between flow cytometric marker expression and cytogenetic/molecular variants in AML. Our study is the first to illustrate the feasibility of using deep learning-based analysis of flow cytometric data for automated AML diagnosis and molecular characterization.
Collapse
Affiliation(s)
- Joshua E. Lewis
- Department of Pathology, Brigham and Women’s Hospital, Boston, MA, USA
| | - Lee A.D. Cooper
- Department of Pathology, Northwestern University, Chicago, IL, USA
| | - David L. Jaye
- Department of Pathology and Laboratory Medicine, Emory University, Atlanta, GA, USA
| | - Olga Pozdnyakova
- Department of Pathology, Brigham and Women’s Hospital, Boston, MA, USA
| |
Collapse
|
8
|
Seifert RP, Gorlin DA, Borkowski AA. Artificial Intelligence for Clinical Flow Cytometry. Clin Lab Med 2023; 43:485-505. [PMID: 37481325 DOI: 10.1016/j.cll.2023.04.009] [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] [Indexed: 07/24/2023]
Abstract
In this review, the authors discuss the fundamental principles of machine learning. They explore recent studies and approaches in implementing machine learning into flow cytometry workflows. These applications are promising but not without their shortcomings. Explainability may be the biggest barrier to adoption, as they contain "black boxes" in which a complex network of mathematical processes learns features of data that are not translatable into real language. The authors discuss the current limitations of machine learning models and the possibility that, without a multiinstitutional development process, these applications could have poor generalizability. They also discuss widespread deployment of augmented decision-making.
Collapse
Affiliation(s)
- Robert P Seifert
- Department of Pathology, Immunology and Laboratory Medicine, University of Florida, College of Medicine, 4800 Southwest 35th Drive, Gainesville, FL 32608, USA.
| | - David A Gorlin
- University of Florida, College of Medicine, 1600 Southwest Archer Road, Gainesville, FL 32610, USA
| | - Andrew A Borkowski
- National Artificial Intelligence Institute, Washington, DC, USA; Artificial Intelligence Service, James A. Haley Veterans' Hospital, 13000 Bruce B Downs Boulevard, Tampa, FL 33647, USA; University of South Florida Morsani School of Medicine, Tampa, FL, USA
| |
Collapse
|
9
|
Fuda F, Chen M, Chen W, Cox A. Artificial intelligence in clinical multiparameter flow cytometry and mass cytometry-key tools and progress. Semin Diagn Pathol 2023; 40:120-128. [PMID: 36894355 DOI: 10.1053/j.semdp.2023.02.004] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 11/01/2022] [Revised: 02/22/2023] [Accepted: 02/23/2023] [Indexed: 03/07/2023]
Abstract
There are many research studies and emerging tools using artificial intelligence (AI) and machine learning to augment flow and mass cytometry workflows. Emerging AI tools can quickly identify common cell populations with continuous improvement of accuracy, uncover patterns in high-dimensional cytometric data that are undetectable by human analysis, facilitate the discovery of cell subpopulations, perform semi-automated immune cell profiling, and demonstrate potential to automate aspects of clinical multiparameter flow cytometric (MFC) diagnostic workflow. Utilizing AI in the analysis of cytometry samples can reduce subjective variability and assist in breakthroughs in understanding diseases. Here we review the diverse types of AI that are being applied to clinical cytometry data and how AI is driving advances in data analysis to improve diagnostic sensitivity and accuracy. We review supervised and unsupervised clustering algorithms for cell population identification, various dimensionality reduction techniques, and their utilities in visualization and machine learning pipelines, and supervised learning approaches for classifying entire cytometry samples.Understanding the AI landscape will enable pathologists to better utilize open source and commercially available tools, plan exploratory research projects to characterize diseases, and work with machine learning and data scientists to implement clinical data analysis pipelines.
Collapse
Affiliation(s)
- Franklin Fuda
- Department of Pathology and Laboratory Medicine, University of Texas, Southwestern Medical Center, Dallas, Texas, USA
| | - Mingyi Chen
- Department of Pathology and Laboratory Medicine, University of Texas, Southwestern Medical Center, Dallas, Texas, USA
| | - Weina Chen
- Department of Pathology and Laboratory Medicine, University of Texas, Southwestern Medical Center, Dallas, Texas, USA
| | - Andrew Cox
- Lyda Hill Department of Bioinformatics, University of Texas, Southwestern Medical Center, Dallas, Texas, USA; Department of Cell and Molecular Biology, University of Texas, Southwestern Medical Center, Dallas, Texas, USA.
| |
Collapse
|
10
|
Fang K, Chen X, Dong Z, Xu P. Developing and validating a highly sensitive platelet clump detection model for the Sysmex haematology analyser. Ann Clin Biochem 2023; 60:126-135. [PMID: 36653307 DOI: 10.1177/00045632231154782] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/20/2023]
Abstract
BACKGROUND Mainstream haematology analysers (HAs) are reported to have low detection sensitivity for platelet clumps. In this study, a deep learning (DL) algorithm, convolutional neural network (CNN), was implemented to detect platelet clumps. METHODS Adenosine diphosphate (ADP) was used to induce platelet aggregation to mimic platelet clumps detected (PCD) samples. Six types of leukocyte scattergrams were collected from the Sysmex XN-10. Then, multiple CNNs were trained and validated by scattergrams in a fivefold cross-validation (CV) method. Finally, the CNN model with the best CV accuracy was tested with practical routine work samples. RESULTS A total of 386 samples (190 PCD and 196 negative samples) and 4253 samples (150 PCD and 4103 negative samples) were eligible for CNN training and practical test, respectively. The CNN with the highest CV accuracy was trained by using scattergrams of side scatter (SSC) vs. forward scatter (FSC) from the white count and nucleated red blood cells (WNR) channel, whose mean area under the curve (AUC), accuracy, specificity and sensitivity were 0.968, 0.940, 0.937 and 0.942, respectively, in the CV. In the practical test, the AUC, accuracy, specificity and sensitivity of the CNN were 0.916, 0.961, 0.860 and 0.965, respectively. The dispersed spots presenting around the leucocytes in the WNR channel may be a sign of platelet clumping. CONCLUSIONS This study demonstrates that the CNN algorithms can identify platelet clumps based on optical information from dedicated leukocyte channels and has a higher ability to detect platelet clumps than the XN-10 device's internal algorithm under practical circumstances.
Collapse
Affiliation(s)
- Kui Fang
- 232834The Third Affiliated Hospital of Zhejiang Chinese Medical University, Hangzhou, China
| | - Xiling Chen
- 232834The Third Affiliated Hospital of Zhejiang Chinese Medical University, Hangzhou, China
| | - Zheqing Dong
- 232834The Third Affiliated Hospital of Zhejiang Chinese Medical University, Hangzhou, China
| | - Peng Xu
- 232834The Third Affiliated Hospital of Zhejiang Chinese Medical University, Hangzhou, China
| |
Collapse
|