1
|
Raghaw CS, Sharma A, Bansal S, Rehman MZU, Kumar N. CoTCoNet: An optimized coupled transformer-convolutional network with an adaptive graph reconstruction for leukemia detection. Comput Biol Med 2024; 179:108821. [PMID: 38972153 DOI: 10.1016/j.compbiomed.2024.108821] [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: 11/21/2023] [Revised: 06/25/2024] [Accepted: 06/25/2024] [Indexed: 07/09/2024]
Abstract
BACKGROUND Swift and accurate blood smear analyses are crucial for diagnosing leukemia and other hematological malignancies. However, manual leukocyte count and morphological evaluation remain time-consuming and prone to errors. Additionally, conventional image processing methods struggle to differentiate cells due to visual similarities between malignant and benign cell morphology. METHOD In response to above challenges, we propose Coupled Transformer Convolutional Network (CoTCoNet) framework for leukemia classification. CoTCoNet integrates dual-feature extraction to capture long-range global features and fine-grained spatial patterns, facilitating the identification of complex hematological characteristics. Additionally, the framework employs a graph-based module to uncover hidden, biologically relevant features of leukocyte cells, along with a Population-based Meta-Heuristic Algorithm for feature selection and optimization. Furthermore, we introduce a novel combination of leukocyte segmentation and synthesis, which isolates relevant regions while augmenting the training dataset with realistic leukocyte samples. This strategy isolates relevant regions while augmenting the training data with realistic leukocyte samples, enhancing feature extraction, and addressing data scarcity without compromising data integrity. RESULTS We evaluated CoTCoNet on a dataset of 16,982 annotated cells, achieving an accuracy of 0.9894 and an F1-Score of 0.9893. We tested CoTCoNet on four diverse, publicly available datasets (including those above) to assess generalizability. Results demonstrate a significant performance improvement over existing state-of-the-art approaches. CONCLUSIONS CoTCoNet represents a significant advancement in leukemia classification, offering enhanced accuracy and efficiency compared to traditional methods. By incorporating explainable visualizations that closely align with cell annotations, the framework provides deeper insights into its decision-making process, further solidifying its potential in clinical settings.
Collapse
Affiliation(s)
- Chandravardhan Singh Raghaw
- Department of Computer Science and Engineering, Indian Institute of Technology Indore, Khandwa Road, Simrol, Indore, 453552, Madhya Pradesh, India.
| | - Arnav Sharma
- Department of Computer Science, The University of Texas at Dallas, 800 W Campbell Rd, Richardson, 75080, TX, USA.
| | - Shubhi Bansal
- Department of Computer Science and Engineering, Indian Institute of Technology Indore, Khandwa Road, Simrol, Indore, 453552, Madhya Pradesh, India.
| | - Mohammad Zia Ur Rehman
- Department of Computer Science and Engineering, Indian Institute of Technology Indore, Khandwa Road, Simrol, Indore, 453552, Madhya Pradesh, India.
| | - Nagendra Kumar
- Department of Computer Science and Engineering, Indian Institute of Technology Indore, Khandwa Road, Simrol, Indore, 453552, Madhya Pradesh, India.
| |
Collapse
|
2
|
Rubinos Rodriguez J, Fernandez S, Swartz N, Alonge A, Bhullar F, Betros T, Girdler M, Patel N, Adas S, Cervone A, Jacobs RJ. A Chronological Overview of Using Deep Learning for Leukemia Detection: A Scoping Review. Cureus 2024; 16:e61379. [PMID: 38947677 PMCID: PMC11214573 DOI: 10.7759/cureus.61379] [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: 05/06/2024] [Accepted: 05/30/2024] [Indexed: 07/02/2024] Open
Abstract
Leukemia is a rare but fatal cancer of the blood. This cancer arises from abnormal bone marrow cells and requires prompt diagnosis for effective treatment and positive patient prognosis. Traditional diagnostic methods (e.g., microscopy, flow cytometry, and biopsy) pose challenges in both accuracy and time, demanding an inquisition on the development and use of deep learning (DL) models, such as convolutional neural networks (CNN), which could allow for a faster and more exact diagnosis. Using specific, objective criteria, DL might hold promise as a tool for physicians to diagnose leukemia. The purpose of this review was to report the relevant available published literature on using DL to diagnose leukemia. Using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, articles published between 2010 and 2023 were searched using Embase, Ovid MEDLINE, and Web of Science, searching the terms "leukemia" AND "deep learning" or "artificial neural network" OR "neural network" AND "diagnosis" OR "detection." After screening retrieved articles using pre-determined eligibility criteria, 20 articles were included in the final review and reported chronologically due to the nascent nature of the phenomenon. The initial studies laid the groundwork for subsequent innovations, illustrating the transition from specialized methods to more generalized approaches capitalizing on DL technologies for leukemia detection. This summary of recent DL models revealed a paradigm shift toward integrated architectures, resulting in notable enhancements in accuracy and efficiency. The continuous refinement of models and techniques, coupled with an emphasis on simplicity and efficiency, positions DL as a promising tool for leukemia detection. With the help of these neural networks, leukemia detection could be hastened, allowing for an improved long-term outlook and prognosis. Further research is warranted using real-life scenarios to confirm the suggested transformative effects DL models could have on leukemia diagnosis.
Collapse
Affiliation(s)
- Jorge Rubinos Rodriguez
- Medicine, Dr. Kiran C. Patel College of Osteopathic Medicine, Nova Southeastern University, Fort Lauderdale, USA
| | - Santiago Fernandez
- Medicine, Dr. Kiran C. Patel College of Osteopathic Medicine, Nova Southeastern University, Fort Lauderdale, USA
| | - Nicholas Swartz
- Medicine, Dr. Kiran C. Patel College of Osteopathic Medicine, Nova Southeastern University, Fort Lauderdale, USA
| | - Austin Alonge
- Medicine, Dr. Kiran C. Patel College of Osteopathic Medicine, Nova Southeastern University, Fort Lauderdale, USA
| | - Fahad Bhullar
- Medicine, Dr. Kiran C. Patel College of Osteopathic Medicine, Nova Southeastern University, Fort Lauderdale, USA
| | - Trevor Betros
- Medicine, Dr. Kiran C. Patel College of Osteopathic Medicine, Nova Southeastern University, Fort Lauderdale, USA
| | - Michael Girdler
- Medicine, Dr. Kiran C. Patel College of Osteopathic Medicine, Nova Southeastern University, Fort Lauderdale, USA
| | - Neil Patel
- Medicine, Dr. Kiran C. Patel College of Osteopathic Medicine, Nova Southeastern University, Fort Lauderdale, USA
| | - Sayf Adas
- Medicine, Dr. Kiran C. Patel College of Osteopathic Medicine, Nova Southeastern University, Fort Lauderdale, USA
| | - Adam Cervone
- Medicine, Dr. Kiran C. Patel College of Osteopathic Medicine, Nova Southeastern University, Fort Lauderdale, USA
| | - Robin J Jacobs
- Medicine, Dr. Kiran C. Patel College of Osteopathic Medicine, Nova Southeastern University, Fort Lauderdale, USA
| |
Collapse
|
3
|
Bermejo-Peláez D, Rueda Charro S, García Roa M, Trelles-Martínez R, Bobes-Fernández A, Hidalgo Soto M, García-Vicente R, Morales ML, Rodríguez-García A, Ortiz-Ruiz A, Blanco Sánchez A, Mousa Urbina A, Álamo E, Lin L, Dacal E, Cuadrado D, Postigo M, Vladimirov A, Garcia-Villena J, Santos A, Ledesma-Carbayo MJ, Ayala R, Martínez-López J, Linares M, Luengo-Oroz M. Digital Microscopy Augmented by Artificial Intelligence to Interpret Bone Marrow Samples for Hematological Diseases. MICROSCOPY AND MICROANALYSIS : THE OFFICIAL JOURNAL OF MICROSCOPY SOCIETY OF AMERICA, MICROBEAM ANALYSIS SOCIETY, MICROSCOPICAL SOCIETY OF CANADA 2024; 30:151-159. [PMID: 38302194 DOI: 10.1093/micmic/ozad143] [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: 07/07/2023] [Revised: 11/15/2023] [Accepted: 12/22/2023] [Indexed: 02/03/2024]
Abstract
Analysis of bone marrow aspirates (BMAs) is an essential step in the diagnosis of hematological disorders. This analysis is usually performed based on a visual examination of samples under a conventional optical microscope, which involves a labor-intensive process, limited by clinical experience and subject to high observer variability. In this work, we present a comprehensive digital microscopy system that enables BMA analysis for cell type counting and differentiation in an efficient and objective manner. This system not only provides an accessible and simple method to digitize, store, and analyze BMA samples remotely but is also supported by an Artificial Intelligence (AI) pipeline that accelerates the differential cell counting process and reduces interobserver variability. It has been designed to integrate AI algorithms with the daily clinical routine and can be used in any regular hospital workflow.
Collapse
Affiliation(s)
| | | | - María García Roa
- Department of Hematology, Hospital Universitario Fundación Alcorcón, C. Budapest, 1, Alcorcón 28922, Madrid, Spain
| | - Roberto Trelles-Martínez
- Department of Hematology, Hospital Universitario Fundación Alcorcón, C. Budapest, 1, Alcorcón 28922, Madrid, Spain
| | - Alejandro Bobes-Fernández
- Department of Hematology, Hospital Universitario Fundación Alcorcón, C. Budapest, 1, Alcorcón 28922, Madrid, Spain
| | - Marta Hidalgo Soto
- Vall Hebron Institute of Oncology (VHIO), Carrer de Natzaret, 115-117, Horta-Guinardó, Barcelona 08035, Spain
| | - Roberto García-Vicente
- Department of Translational Hematology, Research Institute Hospital 12 de Octubre (imas12), Av. de Córdoba, s/n, Madrid 28041, Spain
- Hematological Malignancies Clinical Research Unit H120-CNIO, CIBERONC, C. de Melchor Fernández Almagro, 3, Madrid 28029, Spain
| | - María Luz Morales
- Department of Translational Hematology, Research Institute Hospital 12 de Octubre (imas12), Av. de Córdoba, s/n, Madrid 28041, Spain
- Hematological Malignancies Clinical Research Unit H120-CNIO, CIBERONC, C. de Melchor Fernández Almagro, 3, Madrid 28029, Spain
| | - Alba Rodríguez-García
- Department of Translational Hematology, Research Institute Hospital 12 de Octubre (imas12), Av. de Córdoba, s/n, Madrid 28041, Spain
- Hematological Malignancies Clinical Research Unit H120-CNIO, CIBERONC, C. de Melchor Fernández Almagro, 3, Madrid 28029, Spain
| | - Alejandra Ortiz-Ruiz
- Department of Translational Hematology, Research Institute Hospital 12 de Octubre (imas12), Av. de Córdoba, s/n, Madrid 28041, Spain
- Hematological Malignancies Clinical Research Unit H120-CNIO, CIBERONC, C. de Melchor Fernández Almagro, 3, Madrid 28029, Spain
| | - Alberto Blanco Sánchez
- Department of Hematology, Hospital Universitario 12 de Octubre, Av. de Córdoba, s/n, Madrid 28041, Spain
| | | | - Elisa Álamo
- Spotlab, P.º de Juan XXIII, 36B, Madrid 28040, Spain
| | - Lin Lin
- Spotlab, P.º de Juan XXIII, 36B, Madrid 28040, Spain
- Biomedical Image Technologies Laboratory, ETSI Telecomunicación, Universidad Politécnica de Madrid, Av. Complutense, 30, Madrid 28040, Spain
| | - Elena Dacal
- Spotlab, P.º de Juan XXIII, 36B, Madrid 28040, Spain
| | | | - María Postigo
- Spotlab, P.º de Juan XXIII, 36B, Madrid 28040, Spain
| | | | | | - Andrés Santos
- Biomedical Image Technologies Laboratory, ETSI Telecomunicación, Universidad Politécnica de Madrid, Av. Complutense, 30, Madrid 28040, Spain
- CIBER de Bioingeniería, Biomateriales y Nanomedicina, Instituto de Salud Carlos III, C. de Melchor Fernández Almagro, 3, Madrid 28029, Spain
| | - María Jesús Ledesma-Carbayo
- Biomedical Image Technologies Laboratory, ETSI Telecomunicación, Universidad Politécnica de Madrid, Av. Complutense, 30, Madrid 28040, Spain
- CIBER de Bioingeniería, Biomateriales y Nanomedicina, Instituto de Salud Carlos III, C. de Melchor Fernández Almagro, 3, Madrid 28029, Spain
| | - Rosa Ayala
- Department of Translational Hematology, Research Institute Hospital 12 de Octubre (imas12), Av. de Córdoba, s/n, Madrid 28041, Spain
- Hematological Malignancies Clinical Research Unit H120-CNIO, CIBERONC, C. de Melchor Fernández Almagro, 3, Madrid 28029, Spain
- Department of Hematology, Hospital Universitario 12 de Octubre, Av. de Córdoba, s/n, Madrid 28041, Spain
| | - Joaquín Martínez-López
- Department of Translational Hematology, Research Institute Hospital 12 de Octubre (imas12), Av. de Córdoba, s/n, Madrid 28041, Spain
- Hematological Malignancies Clinical Research Unit H120-CNIO, CIBERONC, C. de Melchor Fernández Almagro, 3, Madrid 28029, Spain
- Department of Hematology, Hospital Universitario 12 de Octubre, Av. de Córdoba, s/n, Madrid 28041, Spain
| | - María Linares
- Department of Translational Hematology, Research Institute Hospital 12 de Octubre (imas12), Av. de Córdoba, s/n, Madrid 28041, Spain
- Hematological Malignancies Clinical Research Unit H120-CNIO, CIBERONC, C. de Melchor Fernández Almagro, 3, Madrid 28029, Spain
- Department of Biochemistry and Molecular Biology, Pharmacy School, Universidad Complutense de Madrid, Pl. de Ramón y Cajal, s/n, Madrid 28040, Spain
| | | |
Collapse
|
4
|
Glüge S, Balabanov S, Koelzer VH, Ott T. Evaluation of deep learning training strategies for the classification of bone marrow cell images. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2024; 243:107924. [PMID: 37979517 DOI: 10.1016/j.cmpb.2023.107924] [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: 05/11/2023] [Revised: 09/28/2023] [Accepted: 11/06/2023] [Indexed: 11/20/2023]
Abstract
BACKGROUND AND OBJECTIVE The classification of bone marrow (BM) cells by light microscopy is an important cornerstone of hematological diagnosis, performed thousands of times a day by highly trained specialists in laboratories worldwide. As the manual evaluation of blood or BM smears is very time-consuming and prone to inter-observer variation, new reliable automated systems are needed. METHODS We aim to improve the automatic classification performance of hematological cell types. Therefore, we evaluate four state-of-the-art Convolutional Neural Network (CNN) architectures on a dataset of 171,374 microscopic cytological single-cell images obtained from BM smears from 945 patients diagnosed with a variety of hematological diseases. We further evaluate the effect of an in-domain vs. out-of-domain pre-training, and assess whether class activation maps provide human-interpretable explanations for the models' predictions. RESULTS The best performing pre-trained model (Regnet_y_32gf) yields a mean precision, recall, and F1 scores of 0.787±0.060, 0.755±0.061, and 0.762±0.050, respectively. This is a 53.5% improvement in precision and 7.3% improvement in recall over previous results with CNNs (ResNeXt-50) that were trained from scratch. The out-of-domain pre-training apparently yields general feature extractors/filters that apply very well to the BM cell classification use case. The class activation maps on cell types with characteristic morphological features were found to be consistent with the explanations of a human domain expert. For example, the Auer rods in the cytoplasm were the predictive cellular feature for correctly classified images of faggot cells. CONCLUSIONS Our study provides data that can help hematology laboratories to choose the optimal training strategy for blood cell classification deep learning models to improve computer-assisted blood and bone marrow cell identification. It also highlights the need for more specific training data, i.e. images of difficult-to-classify classes, including cells labeled with disease information.
Collapse
Affiliation(s)
- Stefan Glüge
- Institute of Computational Life Sciences, Zurich University of Applied Sciences, Schloss 1, 8820 Wädenswil, Switzerland.
| | - Stefan Balabanov
- Department of Medical Oncology and Haematology, University Hospital Zurich and University of Zurich, Rämistrasse 100, 8091 Zurich, Switzerland
| | - Viktor Hendrik Koelzer
- Department of Pathology and Molecular Pathology, University Hospital Zurich and University of Zurich, Schmelzbergstrasse 12, 8091 Zurich, Switzerland
| | - Thomas Ott
- Institute of Computational Life Sciences, Zurich University of Applied Sciences, Schloss 1, 8820 Wädenswil, Switzerland
| |
Collapse
|
5
|
Han Y, Akhtar J, Liu G, Li C, Wang G. Early warning and diagnosis of liver cancer based on dynamic network biomarker and deep learning. Comput Struct Biotechnol J 2023; 21:3478-3489. [PMID: 38213892 PMCID: PMC10782000 DOI: 10.1016/j.csbj.2023.07.002] [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: 04/12/2023] [Revised: 06/19/2023] [Accepted: 07/01/2023] [Indexed: 01/13/2024] Open
Abstract
Background Early detection of complex diseases like hepatocellular carcinoma remains challenging due to their network-driven pathology. Dynamic network biomarkers (DNB) based on monitoring changes in molecular correlations may enable earlier predictions. However, DNB analysis often overlooks disease heterogeneity. Methods We integrated DNB analysis with graph convolutional neural networks (GCN) to identify critical transitions during hepatocellular carcinoma development in a mouse model. A DNB-GCN model was constructed using transcriptomic data and gene expression levels as node features. Results DNB analysis identified a critical transition point at 7 weeks of age despite histological examinations being unable to detect cancerous changes at that time point. The DNB-GCN model achieved 100% accuracy in classifying healthy and cancerous mice, and was able to accurately predict the health status of newly introduced mice. Conclusion The integration of DNB analysis and GCN demonstrates potential for the early detection of complex diseases by capturing network structures and molecular features that conventional biomarker discovery methods overlook. The approach warrants further development and validation.
Collapse
Affiliation(s)
- Yukun Han
- Institute of Modern Biology, Nanjing University, Nanjing 210023, China
- Guangdong Provincial Key Laboratory of Computational Science and Material Design, Shenzhen 518055, China
- Department of Biology, School of Life Sciences, Southern University of Science and Technology, Shenzhen 518055, China
| | - Javed Akhtar
- Biomedical Science and Engineering, School of Medicine, The Chinese University of Hong Kong, Shenzhen 518172, China
- Center for Endocrinology and Metabolic Diseases, Second Affiliated Hospital, The Chinese University of Hong Kong, Shenzhen 518172, China
- Guangdong Provincial Key Laboratory of Computational Science and Material Design, Shenzhen 518055, China
- Department of Biology, School of Life Sciences, Southern University of Science and Technology, Shenzhen 518055, China
| | - Guozhen Liu
- Biomedical Science and Engineering, School of Medicine, The Chinese University of Hong Kong, Shenzhen 518172, China
| | - Chenzhong Li
- Biomedical Science and Engineering, School of Medicine, The Chinese University of Hong Kong, Shenzhen 518172, China
| | - Guanyu Wang
- Biomedical Science and Engineering, School of Medicine, The Chinese University of Hong Kong, Shenzhen 518172, China
- Center for Endocrinology and Metabolic Diseases, Second Affiliated Hospital, The Chinese University of Hong Kong, Shenzhen 518172, China
- Guangdong Provincial Key Laboratory of Computational Science and Material Design, Shenzhen 518055, China
- Department of Biology, School of Life Sciences, Southern University of Science and Technology, Shenzhen 518055, China
| |
Collapse
|
6
|
Gedefaw L, Liu CF, Ip RKL, Tse HF, Yeung MHY, Yip SP, Huang CL. Artificial Intelligence-Assisted Diagnostic Cytology and Genomic Testing for Hematologic Disorders. Cells 2023; 12:1755. [PMID: 37443789 PMCID: PMC10340428 DOI: 10.3390/cells12131755] [Citation(s) in RCA: 5] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/11/2023] [Revised: 06/21/2023] [Accepted: 06/28/2023] [Indexed: 07/15/2023] Open
Abstract
Artificial intelligence (AI) is a rapidly evolving field of computer science that involves the development of computational programs that can mimic human intelligence. In particular, machine learning and deep learning models have enabled the identification and grouping of patterns within data, leading to the development of AI systems that have been applied in various areas of hematology, including digital pathology, alpha thalassemia patient screening, cytogenetics, immunophenotyping, and sequencing. These AI-assisted methods have shown promise in improving diagnostic accuracy and efficiency, identifying novel biomarkers, and predicting treatment outcomes. However, limitations such as limited databases, lack of validation and standardization, systematic errors, and bias prevent AI from completely replacing manual diagnosis in hematology. In addition, the processing of large amounts of patient data and personal information by AI poses potential data privacy issues, necessitating the development of regulations to evaluate AI systems and address ethical concerns in clinical AI systems. Nonetheless, with continued research and development, AI has the potential to revolutionize the field of hematology and improve patient outcomes. To fully realize this potential, however, the challenges facing AI in hematology must be addressed and overcome.
Collapse
Affiliation(s)
- Lealem Gedefaw
- Department of Health Technology and Informatics, The Hong Kong Polytechnic University, Hong Kong, China; (L.G.); (C.-F.L.); (M.H.Y.Y.)
| | - Chia-Fei Liu
- Department of Health Technology and Informatics, The Hong Kong Polytechnic University, Hong Kong, China; (L.G.); (C.-F.L.); (M.H.Y.Y.)
| | - Rosalina Ka Ling Ip
- Department of Pathology, Pamela Youde Nethersole Eastern Hospital, Hong Kong, China; (R.K.L.I.); (H.-F.T.)
| | - Hing-Fung Tse
- Department of Pathology, Pamela Youde Nethersole Eastern Hospital, Hong Kong, China; (R.K.L.I.); (H.-F.T.)
| | - Martin Ho Yin Yeung
- Department of Health Technology and Informatics, The Hong Kong Polytechnic University, Hong Kong, China; (L.G.); (C.-F.L.); (M.H.Y.Y.)
| | - Shea Ping Yip
- Department of Health Technology and Informatics, The Hong Kong Polytechnic University, Hong Kong, China; (L.G.); (C.-F.L.); (M.H.Y.Y.)
| | - Chien-Ling Huang
- Department of Health Technology and Informatics, The Hong Kong Polytechnic University, Hong Kong, China; (L.G.); (C.-F.L.); (M.H.Y.Y.)
| |
Collapse
|