1
|
Lewis JE, Pozdnyakova O. Advances in Bone Marrow Evaluation. Clin Lab Med 2024; 44:431-440. [PMID: 39089749 DOI: 10.1016/j.cll.2024.04.005] [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: 08/04/2024]
Abstract
Evaluation of bone marrow aspirate smear and trephine biopsy specimens is critical to the diagnosis of benign and malignant hematologic conditions. Digital pathology has the potential to revolutionize bone marrow assessment through implementation of artificial intelligence for assisted and automated evaluation, but there remain many barriers toward this implementation. This article reviews the current state of digital evaluation of bone marrow aspirate smears and trephine biopsies, recent research using machine learning models for automated specimen analysis, an outline of the advantages and barriers facing clinical implementation of artificial intelligence, and a potential vision of artificial intelligence-associated bone marrow evaluation.
Collapse
Affiliation(s)
- Joshua E Lewis
- Department of Pathology, Brigham and Women's Hospital, 75 Francis Street, Boston, MA 02215, USA
| | - Olga Pozdnyakova
- The Hospital of the University of Pennsylvania, 3400 Spruce Street, Philadelphia, PA 19104, USA.
| |
Collapse
|
2
|
Moraitis A, Küper A, Tran-Gia J, Eberlein U, Chen Y, Seifert R, Shi K, Kim M, Herrmann K, Fragoso Costa P, Kersting D. Future Perspectives of Artificial Intelligence in Bone Marrow Dosimetry and Individualized Radioligand Therapy. Semin Nucl Med 2024; 54:460-469. [PMID: 39013673 DOI: 10.1053/j.semnuclmed.2024.06.003] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/15/2024] [Accepted: 06/20/2024] [Indexed: 07/18/2024]
Abstract
Radioligand therapy is an emerging and effective treatment option for various types of malignancies, but may be intricately linked to hematological side effects such as anemia, lymphopenia or thrombocytopenia. The safety and efficacy of novel theranostic agents, targeting increasingly complex targets, can be well served by comprehensive dosimetry. However, optimization in patient management and patient selection based on risk-factors predicting adverse events and built upon reliable dose-response relations is still an open demand. In this context, artificial intelligence methods, especially machine learning and deep learning algorithms, may play a crucial role. This review provides an overview of upcoming opportunities for integrating artificial intelligence methods into the field of dosimetry in nuclear medicine by improving bone marrow and blood dosimetry accuracy, enabling early identification of potential hematological risk-factors, and allowing for adaptive treatment planning. It will further exemplify inspirational success stories from neighboring disciplines that may be translated to nuclear medicine practices, and will provide conceptual suggestions for future directions. In the future, we expect artificial intelligence-assisted (predictive) dosimetry combined with clinical parameters to pave the way towards truly personalized theranostics in radioligand therapy.
Collapse
Affiliation(s)
- Alexandros Moraitis
- Department of Nuclear Medicine, West German Cancer Center (WTZ), University Hospital Essen, University of Duisburg-Essen, Essen, Germany.
| | - Alina Küper
- Department of Nuclear Medicine, West German Cancer Center (WTZ), University Hospital Essen, University of Duisburg-Essen, Essen, Germany
| | - Johannes Tran-Gia
- Department of Nuclear Medicine, University Hospital Würzburg, Würzburg, Germany
| | - Uta Eberlein
- Department of Nuclear Medicine, University Hospital Würzburg, Würzburg, Germany
| | - Yizhou Chen
- Department of Nuclear Medicine, Inselspital, Bern University Hospital, University of Bern, Switzerland
| | - Robert Seifert
- Department of Nuclear Medicine, Inselspital, Bern University Hospital, University of Bern, Switzerland
| | - Kuangyu Shi
- Department of Nuclear Medicine, Inselspital, Bern University Hospital, University of Bern, Switzerland
| | - Moon Kim
- Institute for Artificial Intelligence in Medicine, University Hospital Essen, Essen, Germany
| | - Ken Herrmann
- Department of Nuclear Medicine, West German Cancer Center (WTZ), University Hospital Essen, University of Duisburg-Essen, Essen, Germany
| | - Pedro Fragoso Costa
- Department of Nuclear Medicine, West German Cancer Center (WTZ), University Hospital Essen, University of Duisburg-Essen, Essen, Germany
| | - David Kersting
- Department of Nuclear Medicine, West German Cancer Center (WTZ), University Hospital Essen, University of Duisburg-Essen, Essen, Germany
| |
Collapse
|
3
|
Wells C, Robertson T, Sheth P, Abraham S. How aging influences the gut-bone marrow axis and alters hematopoietic stem cell regulation. Heliyon 2024; 10:e32831. [PMID: 38984298 PMCID: PMC11231543 DOI: 10.1016/j.heliyon.2024.e32831] [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: 03/11/2024] [Revised: 06/03/2024] [Accepted: 06/10/2024] [Indexed: 07/11/2024] Open
Abstract
The gut microbiome has come to prominence across research disciplines, due to its influence on major biological systems within humans. Recently, a relationship between the gut microbiome and hematopoietic system has been identified and coined the gut-bone marrow axis. It is well established that the hematopoietic system and gut microbiome separately alter with age; however, the relationship between these changes and how these systems influence each other demands investigation. Since the hematopoietic system produces immune cells that help govern commensal bacteria, it is important to identify how the microbiome interacts with hematopoietic stem cells (HSCs). The gut microbiota has been shown to influence the development and outcomes of hematologic disorders, suggesting dysbiosis may influence the maintenance of HSCs with age. Short chain fatty acids (SCFAs), lactate, iron availability, tryptophan metabolites, bacterial extracellular vesicles, microbe associated molecular patterns (MAMPs), and toll-like receptor (TLR) signalling have been proposed as key mediators of communication across the gut-bone marrow axis and will be reviewed in this article within the context of aging.
Collapse
Affiliation(s)
- Christopher Wells
- Department of Biomedical and Molecular Sciences, Queen's University, Kingston, Ontario, Canada
| | - Tristan Robertson
- Department of Biomedical and Molecular Sciences, Queen's University, Kingston, Ontario, Canada
| | - Prameet Sheth
- Department of Biomedical and Molecular Sciences, Queen's University, Kingston, Ontario, Canada
- Division of Microbiology, Queen's University, Kingston, Ontario, Canada
- Department of Pathology and Molecular Medicine, Kingston, Ontario, Canada
| | - Sheela Abraham
- Department of Biomedical and Molecular Sciences, Queen's University, Kingston, Ontario, Canada
| |
Collapse
|
4
|
Lin Y, Chen Q, Chen T. Recent advancements in machine learning for bone marrow cell morphology analysis. Front Med (Lausanne) 2024; 11:1402768. [PMID: 38947236 PMCID: PMC11211563 DOI: 10.3389/fmed.2024.1402768] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/18/2024] [Accepted: 05/31/2024] [Indexed: 07/02/2024] Open
Abstract
As machine learning progresses, techniques such as neural networks, decision trees, and support vector machines are being increasingly applied in the medical domain, especially for tasks involving large datasets, such as cell detection, recognition, classification, and visualization. Within the domain of bone marrow cell morphology analysis, deep learning offers substantial benefits due to its robustness, ability for automatic feature learning, and strong image characterization capabilities. Deep neural networks are a machine learning paradigm specifically tailored for image processing applications. Artificial intelligence serves as a potent tool in supporting the diagnostic process of clinical bone marrow cell morphology. Despite the potential of artificial intelligence to augment clinical diagnostics in this domain, manual analysis of bone marrow cell morphology remains the gold standard and an indispensable tool for identifying, diagnosing, and assessing the efficacy of hematologic disorders. However, the traditional manual approach is not without limitations and shortcomings, necessitating, the exploration of automated solutions for examining and analyzing bone marrow cytomorphology. This review provides a multidimensional account of six bone marrow cell morphology processes: automated bone marrow cell morphology detection, automated bone marrow cell morphology segmentation, automated bone marrow cell morphology identification, automated bone marrow cell morphology classification, automated bone marrow cell morphology enumeration, and automated bone marrow cell morphology diagnosis. Highlighting the attractiveness and potential of machine learning systems based on bone marrow cell morphology, the review synthesizes current research and recent advances in the application of machine learning in this field. The objective of this review is to offer recommendations to hematologists for selecting the most suitable machine learning algorithms to automate bone marrow cell morphology examinations, enabling swift and precise analysis of bone marrow cytopathic trends for early disease identification and diagnosis. Furthermore, the review endeavors to delineate potential future research avenues for machine learning-based applications in bone marrow cell morphology analysis.
Collapse
Affiliation(s)
- Yifei Lin
- The Second Affiliated Hospital of Fujian Medical University, Quanzhou, Fujian, China
- The School of Basic Medical Sciences, Fujian Medical University, Fuzhou, Fujian, China
| | - Qingquan Chen
- The Second Affiliated Hospital of Fujian Medical University, Quanzhou, Fujian, China
- The School of Public Health, Fujian Medical University, Fuzhou, Fujian, China
| | - Tebin Chen
- The Second Affiliated Hospital of Fujian Medical University, Quanzhou, Fujian, China
| |
Collapse
|
5
|
Mohammed RN, Khoshnaw NS, Mohammed VF, Hassan DO, Abdullah CN, Mahmood TI, Abbass HA, Ahmed D, Noori KD, Saeed LI, Salih SM, Sidiq HS, Ali DO, Shwan A, Majolino I, Ipsevich F. Establishment of reference values based on influential characteristics of hematopoietic stem cells and immune cell subsets in the bone marrow. Heliyon 2024; 10:e30888. [PMID: 38774070 PMCID: PMC11107188 DOI: 10.1016/j.heliyon.2024.e30888] [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: 03/08/2024] [Revised: 04/18/2024] [Accepted: 05/07/2024] [Indexed: 05/24/2024] Open
Abstract
Hematopoietic stem cell transplantation is still a curative treatment for many haematological cancers. Many factors, such as age, sex, ethnic background, smoking status, and body mass index, affect average reference values in different populations. This study aimed to establish a reference range for the absolute numbers and percentages of healthy individuals' hematopoietic stem cells and immune cells in the bone marrow. Seventy-one healthy donors (32 males and 39 females) were enrolled in the study. Following bone marrow harvesting, using flow cytometry, immunophenotyping was performed to determine the absolute number and percentage of CD34+ stem cells and various immune subsets. We found no statistically significant difference in the absolute count of HSCs or immune cell subsets in the bone marrow between males and females. Regarding age, the younger group had more significant CD34+ and immune cell subsets. Donors with healthier body weights tend to have richer bone marrow cellularity. Establishing a reference value for hematopoietic stem cells and immune cells in the bone marrow based on various influential factors is pivotal for defining bone marrow status and donor selection.
Collapse
Affiliation(s)
- Rebar N. Mohammed
- Department of Medical Laboratory Technology, Faculty of Health Science, Qaiwan International University, Sulaimani, Kurdistan Region, Iraq
- College of Veterinary Medicine, University of Sulaimani, Sulaymaniyah, Iraq
- Bone Marrow Transplant Center, Hiwa Hospital, Sulaymaniyah, KRG, Iraq
| | - Najmaddin S.H. Khoshnaw
- Department of Medical Laboratory Science, College of Science, Komar University of Science and Technology, KRG, Iraq
- Department of Clinical Science, College of Medicine, University of Sulaimani, Sulaymaniyah, Iraq
| | | | - Dastan O. Hassan
- Bone Marrow Transplant Center, Hiwa Hospital, Sulaymaniyah, KRG, Iraq
| | | | | | - Huda A. Abbass
- Bone Marrow Transplant Center, Hiwa Hospital, Sulaymaniyah, KRG, Iraq
| | - Dereen Ahmed
- Bone Marrow Transplant Center, Hiwa Hospital, Sulaymaniyah, KRG, Iraq
| | - Kani D. Noori
- Bone Marrow Transplant Center, Hiwa Hospital, Sulaymaniyah, KRG, Iraq
| | - Lanja I. Saeed
- Bone Marrow Transplant Center, Hiwa Hospital, Sulaymaniyah, KRG, Iraq
| | | | - Hiwa S. Sidiq
- Bone Marrow Transplant Center, Hiwa Hospital, Sulaymaniyah, KRG, Iraq
| | - Dlnya Omer Ali
- Bone Marrow Transplant Center, Hiwa Hospital, Sulaymaniyah, KRG, Iraq
| | - Alan Shwan
- Bone Marrow Transplant Center, Hiwa Hospital, Sulaymaniyah, KRG, Iraq
| | - Ignazio Majolino
- Ospedale San Camillo and Salvator Mundi International Hospital, Rome, Italy
| | - Francesco Ipsevich
- Ospedale San Camillo and Salvator Mundi International Hospital, Rome, Italy
| |
Collapse
|
6
|
Hagos YB, Lecat CS, Patel D, Mikolajczak A, Castillo SP, Lyon EJ, Foster K, Tran TA, Lee LS, Rodriguez-Justo M, Yong KL, Yuan Y. Deep Learning Enables Spatial Mapping of the Mosaic Microenvironment of Myeloma Bone Marrow Trephine Biopsies. Cancer Res 2024; 84:493-508. [PMID: 37963212 PMCID: PMC10831337 DOI: 10.1158/0008-5472.can-22-2654] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/02/2022] [Revised: 12/18/2022] [Accepted: 11/07/2023] [Indexed: 11/16/2023]
Abstract
Bone marrow trephine biopsy is crucial for the diagnosis of multiple myeloma. However, the complexity of bone marrow cellular, morphologic, and spatial architecture preserved in trephine samples hinders comprehensive evaluation. To dissect the diverse cellular communities and mosaic tissue habitats, we developed a superpixel-inspired deep learning method (MoSaicNet) that adapts to complex tissue architectures and a cell imbalance aware deep learning pipeline (AwareNet) to enable accurate detection and classification of rare cell types in multiplex immunohistochemistry images. MoSaicNet and AwareNet achieved an AUC of >0.98 for tissue and cellular classification on separate test datasets. Application of MoSaicNet and AwareNet enabled investigation of bone heterogeneity and thickness as well as spatial histology analysis of bone marrow trephine samples from monoclonal gammopathies of undetermined significance (MGUS) and from paired newly diagnosed and posttreatment multiple myeloma. The most significant difference between MGUS and newly diagnosed multiple myeloma (NDMM) samples was not related to cell density but to spatial heterogeneity, with reduced spatial proximity of BLIMP1+ tumor cells to CD8+ cells in MGUS compared with NDMM samples. Following treatment of patients with multiple myeloma, there was a reduction in the density of BLIMP1+ tumor cells, effector CD8+ T cells, and regulatory T cells, indicative of an altered immune microenvironment. Finally, bone heterogeneity decreased following treatment of patients with multiple myeloma. In summary, deep learning-based spatial mapping of bone marrow trephine biopsies can provide insights into the cellular topography of the myeloma marrow microenvironment and complement aspirate-based techniques. SIGNIFICANCE Spatial analysis of bone marrow trephine biopsies using histology, deep learning, and tailored algorithms reveals the bone marrow architectural heterogeneity and evolution during myeloma progression and treatment.
Collapse
Affiliation(s)
- Yeman Brhane Hagos
- Centre for Evolution and Cancer and Division of Molecular Pathology, The Institute of Cancer Research, London, United Kingdom
| | - Catherine S.Y. Lecat
- Research Department of Haematology, University College London Cancer Institute, London, United Kingdom
| | - Dominic Patel
- Research Department of Pathology, University College London Cancer Institute, London, United Kingdom
| | - Anna Mikolajczak
- Research Department of Haematology, University College London Cancer Institute, London, United Kingdom
| | - Simon P. Castillo
- Centre for Evolution and Cancer and Division of Molecular Pathology, The Institute of Cancer Research, London, United Kingdom
| | - Emma J. Lyon
- Research Department of Haematology, University College London Cancer Institute, London, United Kingdom
| | - Kane Foster
- Research Department of Haematology, University College London Cancer Institute, London, United Kingdom
| | - Thien-An Tran
- Research Department of Haematology, University College London Cancer Institute, London, United Kingdom
| | - Lydia S.H. Lee
- Research Department of Haematology, University College London Cancer Institute, London, United Kingdom
| | - Manuel Rodriguez-Justo
- Research Department of Pathology, University College London Cancer Institute, London, United Kingdom
| | - Kwee L. Yong
- Research Department of Haematology, University College London Cancer Institute, London, United Kingdom
| | - Yinyin Yuan
- Centre for Evolution and Cancer and Division of Molecular Pathology, The Institute of Cancer Research, London, United Kingdom
- Centre for Molecular Pathology, Royal Marsden Hospital, London, United Kingdom
| |
Collapse
|
7
|
Ng WY, Erber WN, Grigg A, Dunne K, Perkins A, Forsyth C, Ross DM. Variability of bone marrow biopsy reporting affects accuracy of diagnosis of myeloproliferative neoplasms: data from the ALLG MPN01 registry. Pathology 2024; 56:75-80. [PMID: 38071156 DOI: 10.1016/j.pathol.2023.09.012] [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: 06/08/2023] [Revised: 09/13/2023] [Accepted: 09/27/2023] [Indexed: 01/24/2024]
Abstract
The Philadelphia-negative myeloproliferative neoplasms (MPN) are a heterogeneous group of overlapping bone marrow disorders defined by characteristic peripheral blood counts and bone marrow morphological findings in conjunction with recurrent somatic mutations. The accurate diagnosis and subclassification of MPN relies upon careful reporting of bone marrow morphology combined with ancillary information in an integrated pathology report. This co-operative trial group study ALLG MPN01 (ANZCTR:12613000138785), led by the Australasian Leukaemia & Lymphoma Group (ALLG), aimed to describe the current approach to diagnosis of MPN in routine practice. Specifically, we assessed the frequency with which bone marrow biopsies were performed, and the adherence of reporting pathologists to recommendations contained in the revised 2016 WHO classification pertaining to MPN. We reviewed the diagnosis of 152 patients from eight institutions who were enrolled in a national MPN registry of the ALLG between 2010 and 2016. The ALLG MPN01 registry is now closed to recruitment. Key features were extracted from pathology reports provided to the registry. Bone marrow biopsies were performed in 112/152 cases (74%). The pathological information entered was concordant with the stated clinical diagnosis in 75/112 cases (67%). The main reasons for discordant results were incomplete descriptions of megakaryocyte topography and morphology, inconsistent grading of reticulin fibrosis, and failure to integrate the available morphological and ancillary clinicopathological information. In this retrospective audit, 26% of MPN patients did not undergo a diagnostic bone marrow biopsy. In those who did, the specific MPN subtype may not have been reported correctly in 33% of cases, as evidenced by inconsistent features reported or insufficient information to assess. A more standardised approach to bone marrow reporting is required to ensure accuracy of MPN diagnoses and consistent reporting to cancer registries and clinical trials.
Collapse
Affiliation(s)
- Wei Yang Ng
- Haematology Directorate, SA Pathology, Adelaide, SA, Australia.
| | - Wendy N Erber
- Australasian Leukaemia and Lymphoma Group, Melbourne, Vic, Australia; School of Biomedical Sciences, The University of Western Australia, Crawley, WA, Australia; PathWest Laboratory Medicine, Nedlands, WA, Australia
| | - Andrew Grigg
- Australasian Leukaemia and Lymphoma Group, Melbourne, Vic, Australia; Department Clinical Haematology, Austin Hospital, Melbourne, Vic, Australia
| | - Karin Dunne
- Australasian Leukaemia and Lymphoma Group, Melbourne, Vic, Australia
| | - Andrew Perkins
- Australasian Leukaemia and Lymphoma Group, Melbourne, Vic, Australia; Princess Alexandra Hospital, Woolloongabba, Qld, Australia
| | - Cecily Forsyth
- Australasian Leukaemia and Lymphoma Group, Melbourne, Vic, Australia; Gosford Hospital, Gosford, NSW, Australia
| | - David M Ross
- Haematology Directorate, SA Pathology, Adelaide, SA, Australia; Australasian Leukaemia and Lymphoma Group, Melbourne, Vic, Australia; Department of Haematology, Flinders University and Medical Centre, Adelaide, SA, Australia
| |
Collapse
|
8
|
Ryou H, Lomas O, Theissen H, Thomas E, Rittscher J, Royston D. Quantitative interpretation of bone marrow biopsies in MPN-What's the point in a molecular age? Br J Haematol 2023; 203:523-535. [PMID: 37858962 PMCID: PMC10952168 DOI: 10.1111/bjh.19154] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/20/2023] [Revised: 09/20/2023] [Accepted: 09/30/2023] [Indexed: 10/21/2023]
Abstract
The diagnosis of myeloproliferative neoplasms (MPN) requires the integration of clinical, morphological, genetic and immunophenotypic findings. Recently, there has been a transformation in our understanding of the cellular and molecular mechanisms underlying disease initiation and progression in MPN. This has been accompanied by the widespread application of high-resolution quantitative molecular techniques. By contrast, microscopic interpretation of bone marrow biopsies by haematologists/haematopathologists remains subjective and qualitative. However, advances in tissue image analysis and artificial intelligence (AI) promise to transform haematopathology. Pioneering studies in bone marrow image analysis offer to refine our understanding of the boundaries between reactive samples and MPN subtypes and better capture the morphological correlates of high-risk disease. They also demonstrate potential to improve the evaluation of current and novel therapeutics for MPN and other blood cancers. With increased therapeutic targeting of diverse molecular, cellular and extra-cellular components of the marrow, these approaches can address the unmet need for improved objective and quantitative measures of disease modification in the context of clinical trials. This review focuses on the state-of-the-art in image analysis/AI of bone marrow tissue, with an emphasis on its potential to complement and inform future clinical studies and research in MPN.
Collapse
Affiliation(s)
- Hosuk Ryou
- Nuffield Division of Clinical Laboratory Sciences, Radcliffe Department of MedicineUniversity of OxfordOxfordUK
| | - Oliver Lomas
- Department of HaematologyOxford University Hospitals NHS Foundation TrustOxfordUK
| | - Helen Theissen
- Department of Engineering Science, Institute of Biomedical Engineering (IBME)University of OxfordOxfordUK
| | - Emily Thomas
- Department of Engineering Science, Institute of Biomedical Engineering (IBME)University of OxfordOxfordUK
| | - Jens Rittscher
- Department of Engineering Science, Institute of Biomedical Engineering (IBME)University of OxfordOxfordUK
- Ground Truth LabsOxfordUK
- Oxford NIHR Biomedical Research CentreOxford University Hospitals NHS Foundation TrustOxfordUK
- Ludwig Institute for Cancer ResearchUniversity of OxfordOxfordUK
| | - Daniel Royston
- Nuffield Division of Clinical Laboratory Sciences, Radcliffe Department of MedicineUniversity of OxfordOxfordUK
- Department of PathologyOxford University Hospitals NHS Foundation TrustOxfordUK
| |
Collapse
|
9
|
Dehkharghanian T, Mu Y, Tizhoosh HR, Campbell CJV. Applied machine learning in hematopathology. Int J Lab Hematol 2023. [PMID: 37257440 DOI: 10.1111/ijlh.14110] [Citation(s) in RCA: 4] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/09/2023] [Accepted: 05/12/2023] [Indexed: 06/02/2023]
Abstract
An increasing number of machine learning applications are being developed and applied to digital pathology, including hematopathology. The goal of these modern computerized tools is often to support diagnostic workflows by extracting and summarizing information from multiple data sources, including digital images of human tissue. Hematopathology is inherently multimodal and can serve as an ideal case study for machine learning applications. However, hematopathology also poses unique challenges compared to other pathology subspecialities when applying machine learning approaches. By modeling the pathologist workflow and thinking process, machine learning algorithms may be designed to address practical and tangible problems in hematopathology. In this article, we discuss the current trends in machine learning in hematopathology. We review currently available machine learning enabled medical devices supporting hematopathology workflows. We then explore current machine learning research trends of the field with a focus on bone marrow cytology and histopathology, and how adoption of new machine learning tools may be enabled through the transition to digital pathology.
Collapse
Affiliation(s)
- Taher Dehkharghanian
- Department of Nephrology, University Health Network, Toronto, Ontario, Canada
- Department of Pathology and Molecular Medicine, McMaster University, Hamilton, Ontario, Canada
| | - Youqing Mu
- Department of Pathology and Molecular Medicine, McMaster University, Hamilton, Ontario, Canada
| | - Hamid R Tizhoosh
- Rhazes Lab, Artificial Intelligence and Informatics, Mayo Clinic, Rochester, Minnesota, USA
| | - Clinton J V Campbell
- Department of Pathology and Molecular Medicine, McMaster University, Hamilton, Ontario, Canada
- William Osler Health System, Brampton, Ontario, Canada
| |
Collapse
|
10
|
Kaya Z, Kirkiz S, Özkurt ZN, Yagcı M, Kocak U. Analysis of bone marrow samples by the SYSMEX-XN20 hematology analyzer. Int J Lab Hematol 2023; 45:e47-e51. [PMID: 36437564 DOI: 10.1111/ijlh.13996] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/30/2022] [Accepted: 11/10/2022] [Indexed: 11/29/2022]
Affiliation(s)
- Zühre Kaya
- Department of Pediatric Hematology, Gazi University School of Medicine, Ankara, Turkey
| | - Serap Kirkiz
- Department of Pediatric Hematology, Gazi University School of Medicine, Ankara, Turkey
| | - Zübeyde Nur Özkurt
- Department of Adult Hematology, Gazi University School of Medicine, Ankara, Turkey
| | - Münci Yagcı
- Department of Adult Hematology, Gazi University School of Medicine, Ankara, Turkey
| | - Ulker Kocak
- Department of Pediatric Hematology, Gazi University School of Medicine, Ankara, Turkey
| |
Collapse
|
11
|
Sarkis R, Burri O, Royer-Chardon C, Schyrr F, Blum S, Costanza M, Cherix S, Piazzon N, Barcena C, Bisig B, Nardi V, Sarro R, Ambrosini G, Weigert M, Spertini O, Blum S, Deplancke B, Seitz A, de Leval L, Naveiras O. MarrowQuant 2.0: A Digital Pathology Workflow Assisting Bone Marrow Evaluation in Experimental and Clinical Hematology. Mod Pathol 2023; 36:100088. [PMID: 36788087 DOI: 10.1016/j.modpat.2022.100088] [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: 07/15/2022] [Revised: 11/22/2022] [Accepted: 12/15/2022] [Indexed: 01/11/2023]
Abstract
Bone marrow (BM) cellularity assessment is a crucial step in the evaluation of BM trephine biopsies for hematologic and nonhematologic disorders. Clinical assessment is based on a semiquantitative visual estimation of the hematopoietic and adipocytic components by hematopathologists, which does not provide quantitative information on other stromal compartments. In this study, we developed and validated MarrowQuant 2.0, an efficient, user-friendly digital hematopathology workflow integrated within QuPath software, which serves as BM quantifier for 5 mutually exclusive compartments (bone, hematopoietic, adipocytic, and interstitial/microvasculature areas and other) and derives the cellularity of human BM trephine biopsies. Instance segmentation of individual adipocytes is realized through the adaptation of the machine-learning-based algorithm StarDist. We calculated BM compartments and adipocyte size distributions of hematoxylin and eosin images obtained from 250 bone specimens, from control subjects and patients with acute myeloid leukemia or myelodysplastic syndrome, at diagnosis and follow-up, and measured the agreement of cellularity estimates by MarrowQuant 2.0 against visual scores from 4 hematopathologists. The algorithm was capable of robust BM compartment segmentation with an average mask accuracy of 86%, maximal for bone (99%), hematopoietic (92%), and adipocyte (98%) areas. MarrowQuant 2.0 cellularity score and hematopathologist estimations were highly correlated (R2 = 0.92-0.98, intraclass correlation coefficient [ICC] = 0.98; interobserver ICC = 0.96). BM compartment segmentation quantitatively confirmed the reciprocity of the hematopoietic and adipocytic compartments. MarrowQuant 2.0 performance was additionally tested for cellularity assessment of specimens prospectively collected from clinical routine diagnosis. After special consideration for the choice of the cellularity equation in specimens with expanded stroma, performance was similar in this setting (R2 = 0.86, n = 42). Thus, we conclude that these validation experiments establish MarrowQuant 2.0 as a reliable tool for BM cellularity assessment. We expect this workflow will serve as a clinical research tool to explore novel biomarkers related to BM stromal components and may contribute to further validation of future digitalized diagnostic hematopathology workstreams.
Collapse
Affiliation(s)
- Rita Sarkis
- Laboratory of Regenerative Hematopoiesis, Institute of Bioengineering & ISREC, Ecole Polytechnique Fédérale de Lausanne (EPFL), Lausanne, Switzerland; Department of Biomedical Sciences, University of Lausanne (UNIL), Lausanne, Switzerland; Laboratory of Systems Biology and Genetics, Institute of Bioengineering, School of Life Sciences, Ecole Polytechnique Fédérale de Lausanne (EPFL), Lausanne, Switzerland
| | - Olivier Burri
- BioImaging and Optics Core Facility, School of Life Sciences, Ecole Polytechnique Fédérale de Lausanne, Lausanne, Switzerland
| | - Claire Royer-Chardon
- Institute of Pathology, Department of Laboratory Medicine and Pathology, Lausanne University Hospital and Lausanne University, Lausanne, Switzerland
| | - Frédérica Schyrr
- Laboratory of Regenerative Hematopoiesis, Institute of Bioengineering & ISREC, Ecole Polytechnique Fédérale de Lausanne (EPFL), Lausanne, Switzerland
| | - Sophie Blum
- Laboratory of Regenerative Hematopoiesis, Institute of Bioengineering & ISREC, Ecole Polytechnique Fédérale de Lausanne (EPFL), Lausanne, Switzerland
| | - Mariangela Costanza
- Hematology Service, Departments of Oncology and Laboratory Medicine, Lausanne University Hospital (CHUV) and University of Lausanne (UNIL), Lausanne, Switzerland
| | - Stephane Cherix
- Department of Orthopaedics and Traumatology, Lausanne University Hospital and University of Lausanne, Lausanne, Switzerland
| | - Nathalie Piazzon
- Institute of Pathology, Department of Laboratory Medicine and Pathology, Lausanne University Hospital and Lausanne University, Lausanne, Switzerland
| | - Carmen Barcena
- Institute of Pathology, Department of Laboratory Medicine and Pathology, Lausanne University Hospital and Lausanne University, Lausanne, Switzerland; Department of Pathology, Hospital 12 de Octubre, Madrid, Spain
| | - Bettina Bisig
- Institute of Pathology, Department of Laboratory Medicine and Pathology, Lausanne University Hospital and Lausanne University, Lausanne, Switzerland
| | - Valentina Nardi
- Department of Pathology, Massachusetts General Hospital, Boston, Massachusetts
| | - Rossella Sarro
- Institute of Pathology, Department of Laboratory Medicine and Pathology, Lausanne University Hospital and Lausanne University, Lausanne, Switzerland; Institute of Pathology, Ente Ospedaliero Cantonale (EOC), Locarno, Switzerland
| | - Giovanna Ambrosini
- Bioinformatics Competence Center (BICC), UNIL/EPFL Lausanne, Switzerland
| | - Martin Weigert
- Institute of Bioengineering, School of Life Sciences, Ecole Polytechnique Fédérale de Lausanne (EPFL), Lausanne, Switzerland
| | - Olivier Spertini
- Hematology Service, Departments of Oncology and Laboratory Medicine, Lausanne University Hospital (CHUV) and University of Lausanne (UNIL), Lausanne, Switzerland
| | - Sabine Blum
- Hematology Service, Departments of Oncology and Laboratory Medicine, Lausanne University Hospital (CHUV) and University of Lausanne (UNIL), Lausanne, Switzerland
| | - Bart Deplancke
- Laboratory of Systems Biology and Genetics, Institute of Bioengineering, School of Life Sciences, Ecole Polytechnique Fédérale de Lausanne (EPFL) and Swiss Institute of Bioinformatics, Lausanne, Switzerland
| | - Arne Seitz
- BioImaging and Optics Core Facility, School of Life Sciences, Ecole Polytechnique Fédérale de Lausanne, Lausanne, Switzerland
| | - Laurence de Leval
- Institute of Pathology, Department of Laboratory Medicine and Pathology, Lausanne University Hospital and Lausanne University, Lausanne, Switzerland
| | - Olaia Naveiras
- Laboratory of Regenerative Hematopoiesis, Institute of Bioengineering & ISREC, Ecole Polytechnique Fédérale de Lausanne (EPFL), Lausanne, Switzerland; Hematology Service, Departments of Oncology and Laboratory Medicine, Lausanne University Hospital (CHUV) and University of Lausanne (UNIL), Lausanne, Switzerland.
| |
Collapse
|