1
|
Mastropietro A, Casali N, Taccogna MG, D’Angelo MG, Rizzo G, Peruzzo D. Classification of Muscular Dystrophies from MR Images Improves Using the Swin Transformer Deep Learning Model. Bioengineering (Basel) 2024; 11:580. [PMID: 38927816 PMCID: PMC11200745 DOI: 10.3390/bioengineering11060580] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/22/2024] [Revised: 05/28/2024] [Accepted: 06/05/2024] [Indexed: 06/28/2024] Open
Abstract
Muscular dystrophies present diagnostic challenges, requiring accurate classification for effective diagnosis and treatment. This study investigates the efficacy of deep learning methodologies in classifying these disorders using skeletal muscle MRI scans. Specifically, we assess the performance of the Swin Transformer (SwinT) architecture against traditional convolutional neural networks (CNNs) in distinguishing between healthy individuals, Becker muscular dystrophy (BMD), and limb-girdle muscular Dystrophy type 2 (LGMD2) patients. Moreover, 3T MRI scans from a retrospective dataset of 75 scans (from 54 subjects) were utilized, with multiparametric protocols capturing various MRI contrasts, including T1-weighted and Dixon sequences. The dataset included 17 scans from healthy volunteers, 27 from BMD patients, and 31 from LGMD2 patients. SwinT and CNNs were trained and validated using a subset of the dataset, with the performance evaluated based on accuracy and F-score. Results indicate the superior accuracy of SwinT (0.96), particularly when employing fat fraction (FF) images as input; it served as a valuable parameter for enhancing classification accuracy. Despite limitations, including a modest cohort size, this study provides valuable insights into the application of AI-driven approaches for precise neuromuscular disorder classification, with potential implications for improving patient care.
Collapse
Affiliation(s)
- Alfonso Mastropietro
- Istituto di Sistemi e Tecnologie Industriali Intelligenti per il Manifatturiero Avanzato, Consiglio Nazionale delle Ricerche, 20133 Milan, Italy; (A.M.); (N.C.)
| | - Nicola Casali
- Istituto di Sistemi e Tecnologie Industriali Intelligenti per il Manifatturiero Avanzato, Consiglio Nazionale delle Ricerche, 20133 Milan, Italy; (A.M.); (N.C.)
- Dipartimento di Elettronica, Informazione e Bioingegneria, Politecnico di Milano, 20133 Milan, Italy
| | - Maria Giovanna Taccogna
- Istituto di Tecnologie Biomediche, Consiglio Nazionale delle Ricerche, 20054 Segrate, Milan, Italy;
| | - Maria Grazia D’Angelo
- Unit of Rehabilitation of Rare Diseases of the Central and Peripheral Nervous System, Scientific Institute IRCCS Eugenio Medea, 23842 Bosisio Parini, Lecco, Italy;
| | - Giovanna Rizzo
- Istituto di Sistemi e Tecnologie Industriali Intelligenti per il Manifatturiero Avanzato, Consiglio Nazionale delle Ricerche, 20133 Milan, Italy; (A.M.); (N.C.)
| | - Denis Peruzzo
- Neuroimaging Unit, Scientific Institute IRCCS Eugenio Medea, 23842 Bosisio Parini, Lecco, Italy
| |
Collapse
|
2
|
Piñeros-Fernández MC. Artificial Intelligence Applications in the Diagnosis of Neuromuscular Diseases: A Narrative Review. Cureus 2023; 15:e48458. [PMID: 37942130 PMCID: PMC10629626 DOI: 10.7759/cureus.48458] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 11/07/2023] [Indexed: 11/10/2023] Open
Abstract
The accurate diagnosis of neuromuscular diseases (NMD) is in many cases difficult; the starting point is the clinical approach based on the course of the disease and a careful physical examination of the patient. Electrodiagnostic tests, imaging, muscle biopsy, and genetics are fundamental complementary studies for the diagnosis of NMD. The large volume of data obtained from such studies makes it necessary to look for efficient solutions, such as artificial intelligence (AI) applications, which can help classify, synthesize, and organize the information of patients with NMD to facilitate their accurate and timely diagnosis. The objective of this study was to describe the usefulness of AI applications in the diagnosis of patients with neuromuscular diseases. A narrative review was done, including publications on artificial intelligence applied to the diagnostic methods of NMD currently existing. Twelve studies were included. Two of the studies focused on muscle ultrasound, five of the studies on muscle MRI, two studies on electromyography, two studies on amyotrophic lateral sclerosis (ALS) biomarkers, and one study on genes related to myopathies. The accuracy of classification using different classification algorithms used in each of the studies included in this narrative review was already 90% in most studies. In conclusion, the future design of more accurate algorithms applied to NMD with greater precision will have an impact on the earlier diagnosis of this group of diseases.
Collapse
Affiliation(s)
- Martha C Piñeros-Fernández
- Pediatric Neurology, Fundación Cardio Infantil - La Cardio, Bogotá, COL
- Pediatric Neurology, Cobos Medical Center, Bogotá, COL
| |
Collapse
|
3
|
Milanese JS, Marcotte R, Costain WJ, Kablar B, Drouin S. Roles of Skeletal Muscle in Development: A Bioinformatics and Systems Biology Overview. ADVANCES IN ANATOMY, EMBRYOLOGY, AND CELL BIOLOGY 2023; 236:21-55. [PMID: 37955770 DOI: 10.1007/978-3-031-38215-4_2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/14/2023]
Abstract
The ability to assess various cellular events consequent to perturbations, such as genetic mutations, disease states and therapies, has been recently revolutionized by technological advances in multiple "omics" fields. The resulting deluge of information has enabled and necessitated the development of tools required to both process and interpret the data. While of tremendous value to basic researchers, the amount and complexity of the data has made it extremely difficult to manually draw inference and identify factors key to the study objectives. The challenges of data reduction and interpretation are being met by the development of increasingly complex tools that integrate disparate knowledge bases and synthesize coherent models based on current biological understanding. This chapter presents an example of how genomics data can be integrated with biological network analyses to gain further insight into the developmental consequences of genetic perturbations. State of the art methods for conducting similar studies are discussed along with modern methods used to analyze and interpret the data.
Collapse
Affiliation(s)
| | - Richard Marcotte
- Human Health Therapeutics, National Research Council of Canada , Montreal, QC, Canada
| | - Willard J Costain
- Human Health Therapeutics, National Research Council of Canada, Ottawa, ON, Canada
| | - Boris Kablar
- Department of Medical Neuroscience, Anatomy and Pathology, Faculty of Medicine, Dalhousie University, Halifax, NS, Canada
| | - Simon Drouin
- Human Health Therapeutics, National Research Council of Canada , Montreal, QC, Canada.
| |
Collapse
|
4
|
Gómez-Andrés D, Oulhissane A, Quijano-Roy S. Two decades of advances in muscle imaging in children: from pattern recognition of muscle diseases to quantification and machine learning approaches. Neuromuscul Disord 2021; 31:1038-1050. [PMID: 34736625 DOI: 10.1016/j.nmd.2021.08.006] [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: 07/27/2021] [Revised: 07/30/2021] [Accepted: 08/01/2021] [Indexed: 11/29/2022]
Abstract
Muscle imaging has progressively gained popularity in the neuromuscular field. Together with detailed clinical examination and muscle biopsy, it has become one of the main tools for deep phenotyping and orientation of etiological diagnosis. Even in the current era of powerful new generation sequencing, muscle MRI has arisen as a tool for prioritization of certain genetic entities, supporting the pathogenicity of variants of unknown significance and facilitating diagnosis in cases with an initially inconclusive genetic study. Although the utility of muscle imaging is increasingly clear, it has not reached its full potential in clinical practice. Pattern recognition is known for a number of diseases and will certainly be enhanced by the use of machine learning approaches. For instance, MRI heatmap representations might be confronted with molecular results by obtaining a probabilistic diagnosis based in each disease "MRI fingerprints". Muscle ultrasound as a screening tool and quantified techniques such as Dixon MRI seem still underdeveloped. In this paper, we aim to appraise the advances in recent years in pediatric muscle imaging and try to define areas of uncertainty and potential advances that might become standardized to be widely used in the future.
Collapse
Affiliation(s)
- David Gómez-Andrés
- Pediatric Neurology, Vall d'Hebron Institut de Recerca (VHIR), Hospital Universitari Vall d'Hebron, ERN-RND - EURO-NMD, Vall d'Hebron Barcelona Hospital Campus, Barcelona, Spain; European Network for Reference Centers on Neuromuscular Disorders (Euro-NMD ERN)
| | - Amal Oulhissane
- Université Paris-Saclay, APHP, Neuromuscular Unit, Pediatric Neurology and ICU Department, Raymond Poincaré Hospital, 92390 Garches, France
| | - Susana Quijano-Roy
- Université Paris-Saclay, APHP, Neuromuscular Unit, Pediatric Neurology and ICU Department, Raymond Poincaré Hospital, 92390 Garches, France; UMR 1179, Laboratoire handicap neuromusculaire: physiopathologie biothérapie pharmacologie appliquées (END-ICAP), UFR Simone Veil, Montigny Le Bretonneux, France; French Network of Neuromuscular Reference Centers (FILNEMUS), France.
| |
Collapse
|
5
|
Tsai JY, Hung IYJ, Guo YL, Jan YK, Lin CY, Shih TTF, Chen BB, Lung CW. Lumbar Disc Herniation Automatic Detection in Magnetic Resonance Imaging Based on Deep Learning. Front Bioeng Biotechnol 2021; 9:708137. [PMID: 34490222 PMCID: PMC8416668 DOI: 10.3389/fbioe.2021.708137] [Citation(s) in RCA: 12] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/13/2021] [Accepted: 07/19/2021] [Indexed: 12/30/2022] Open
Abstract
Background: Lumbar disc herniation (LDH) is among the most common causes of lower back pain and sciatica. The causes of LDH have not been fully elucidated but most likely involve a complex combination of mechanical and biological processes. Magnetic resonance imaging (MRI) is a tool most frequently used for LDH because it can show abnormal soft tissue areas around the spine. Deep learning models may be trained to recognize images with high speed and accuracy to diagnose LDH. Although the deep learning model requires huge numbers of image datasets to train and establish the best model, this study processed enhanced medical image features for training the small-scale deep learning dataset. Methods: We propose automatic detection to assist the initial LDH exam for lower back pain. The subjects were between 20 and 65 years old with at least 6 months of work experience. The deep learning method employed the YOLOv3 model to train and detect small object changes such as LDH on MRI. The dataset images were processed and combined with labeling and annotation from the radiologist's diagnosis record. Results: Our method proves the possibility of using deep learning with a small-scale dataset with limited medical images. The highest mean average precision (mAP) was 92.4% at 550 images with data augmentation (550-aug), and the YOLOv3 LDH training was 100% with the best average precision at 550-aug among all datasets. This study used data augmentation to prevent under- or overfitting in an object detection model that was trained with the small-scale dataset. Conclusions: The data augmentation technique plays a crucial role in YOLOv3 training and detection results. This method displays a high possibility for rapid initial tests and auto-detection for a limited clinical dataset.
Collapse
Affiliation(s)
- Jen-Yung Tsai
- Department of Digital Media Design, Asia University, Taichung, Taiwan
| | - Isabella Yu-Ju Hung
- Department of Nursing, Chung Hwa University of Medical Technology, Tainan, Taiwan
| | - Yue Leon Guo
- Environmental and Occupational Medicine, College of Medicine, National Taiwan University (NTU) and NTU Hospital, Taipei, Taiwan
- Graduate Institute of Environmental and Occupational Health Sciences, College of Public Health, National Taiwan University, Taipei, Taiwan
- National Institute of Environmental Health Sciences, National Health Research Institutes, Miaoli, Taiwan
| | - Yih-Kuen Jan
- Rehabilitation Engineering Lab, Department of Kinesiology and Community Health, University of Illinois at Urbana-Champaign, Champaign, IL, United States
| | - Chih-Yang Lin
- Department of Electrical Engineering, Yuan Ze University, Chung-Li, Taiwan
| | - Tiffany Ting-Fang Shih
- Department of Medical Imaging and Radiology, National Taiwan University (NTU) Hospital and NTU College of Medicine, Taipei, Taiwan
| | - Bang-Bin Chen
- Department of Medical Imaging and Radiology, National Taiwan University (NTU) Hospital and NTU College of Medicine, Taipei, Taiwan
| | - Chi-Wen Lung
- Rehabilitation Engineering Lab, Department of Kinesiology and Community Health, University of Illinois at Urbana-Champaign, Champaign, IL, United States
- Department of Creative Product Design, Asia University, Taichung, Taiwan
| |
Collapse
|