1
|
Musall BC, Gabr RE, Yang Y, Kamali A, Lincoln JA, Jacobs MA, Ly V, Luo X, Wolinsky JS, Narayana PA, Hasan KM. Detection of diffusely abnormal white matter in multiple sclerosis on multiparametric brain MRI using semi-supervised deep learning. Sci Rep 2024; 14:17157. [PMID: 39060426 PMCID: PMC11282266 DOI: 10.1038/s41598-024-67722-2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/22/2024] [Accepted: 07/15/2024] [Indexed: 07/28/2024] Open
Abstract
In addition to focal lesions, diffusely abnormal white matter (DAWM) is seen on brain MRI of multiple sclerosis (MS) patients and may represent early or distinct disease processes. The role of MRI-observed DAWM is understudied due to a lack of automated assessment methods. Supervised deep learning (DL) methods are highly capable in this domain, but require large sets of labeled data. To overcome this challenge, a DL-based network (DAWM-Net) was trained using semi-supervised learning on a limited set of labeled data for segmentation of DAWM, focal lesions, and normal-appearing brain tissues on multiparametric MRI. DAWM-Net segmentation performance was compared to a previous intensity thresholding-based method on an independent test set from expert consensus (N = 25). Segmentation overlap by Dice Similarity Coefficient (DSC) and Spearman correlation of DAWM volumes were assessed. DAWM-Net showed DSC > 0.93 for normal-appearing brain tissues and DSC > 0.81 for focal lesions. For DAWM-Net, the DAWM DSC was 0.49 ± 0.12 with a moderate volume correlation (ρ = 0.52, p < 0.01). The previous method showed lower DAWM DSC of 0.26 ± 0.08 and lacked a significant volume correlation (ρ = 0.23, p = 0.27). These results demonstrate the feasibility of DL-based DAWM auto-segmentation with semi-supervised learning. This tool may facilitate future investigation of the role of DAWM in MS.
Collapse
Affiliation(s)
- Benjamin C Musall
- Department of Diagnostic and Interventional Imaging, University of Texas McGovern Medical School, 6431 Fannin St., MSE 168, Houston, TX, 77030, USA
| | - Refaat E Gabr
- Department of Diagnostic and Interventional Imaging, University of Texas McGovern Medical School, 6431 Fannin St., MSE 168, Houston, TX, 77030, USA
| | - Yanyu Yang
- Department of Biostatistics and Data Science, University of Texas School of Public Health, Houston, TX, USA
| | - Arash Kamali
- Department of Diagnostic and Interventional Imaging, University of Texas McGovern Medical School, 6431 Fannin St., MSE 168, Houston, TX, 77030, USA
| | - John A Lincoln
- Department of Neurology, University of Texas McGovern Medical School, Houston, TX, USA
| | - Michael A Jacobs
- Department of Diagnostic and Interventional Imaging, University of Texas McGovern Medical School, 6431 Fannin St., MSE 168, Houston, TX, 77030, USA
- The Russell H. Morgan Department of Radiology and Radiological Science and Sidney Kimmel Comprehensive Cancer Center, The Johns Hopkins School of Medicine, Baltimore, MD, USA
- Department of Computer Science, Rice University, Houston, TX, USA
| | - Vi Ly
- Department of Biostatistics and Data Science, University of Texas School of Public Health, Houston, TX, USA
| | - Xi Luo
- Department of Biostatistics and Data Science, University of Texas School of Public Health, Houston, TX, USA
| | - Jerry S Wolinsky
- Department of Neurology, University of Texas McGovern Medical School, Houston, TX, USA
| | - Ponnada A Narayana
- Department of Diagnostic and Interventional Imaging, University of Texas McGovern Medical School, 6431 Fannin St., MSE 168, Houston, TX, 77030, USA
| | - Khader M Hasan
- Department of Diagnostic and Interventional Imaging, University of Texas McGovern Medical School, 6431 Fannin St., MSE 168, Houston, TX, 77030, USA.
| |
Collapse
|
2
|
Ghezzi A, Neuteboom RF. Neurofilament Light Chain in Adult and Pediatric Multiple Sclerosis: A Promising Biomarker to Better Characterize Disease Activity and Personalize MS Treatment. Neurol Ther 2023; 12:1867-1881. [PMID: 37682513 PMCID: PMC10630260 DOI: 10.1007/s40120-023-00535-z] [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: 07/05/2023] [Accepted: 08/15/2023] [Indexed: 09/09/2023] Open
Abstract
Many biological markers have been explored in multiple sclerosis (MS) to better quantify disease burden and better evaluate response to treatments, beyond clinical and MRI data. Among these, neurofilament light chain (Nf-L), although non-specific for this disease and found to be increased in other neurological conditions, has been shown to be the most promising biomarker for assessing axonal damage in MS, with a definite role in predicting the development of MS in patients at the first neurological episode suggestive of MS, and also in a preclinical phase. There is strong evidence that Nf-L levels are increased more in relapsing versus stable MS patients, and that they predict future disease evolution (relapses, progression, MRI measures of activity/progression) in MS patients, providing information on response to therapy, helping to anticipate clinical decisions in patients with an apparently stable evolution, and identifying patient non-responders to disease-modifying treatments. Moreover, Nf-L can contribute to the better understanding of the mechanisms of demyelination and axonal damage in adult and pediatric MS. A fundamental requirement for its clinical use is the accurate standardization of normal values, corrected for confounding factors, in particular age, sex, body mass index, and presence of comorbidities. In this review, a guide is provided to update clinicians on the use of Nf-L in clinical activity.
Collapse
Affiliation(s)
- Angelo Ghezzi
- Dipartimento di Scienze della Salute, Università Piemonte Orientale A. Avogadro, Via Solaroli 17, 28100, Novara, Italy.
| | - R F Neuteboom
- Department of Neurology, ErasMS Center, Erasmus MC, PO Box 2040, 3000, Rotterdam, The Netherlands
| |
Collapse
|
3
|
Mak G, Menon S, Lu JQ. Neurofilaments in neurologic disorders and beyond. J Neurol Sci 2022; 441:120380. [PMID: 36027641 DOI: 10.1016/j.jns.2022.120380] [Citation(s) in RCA: 5] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/20/2022] [Revised: 08/07/2022] [Accepted: 08/10/2022] [Indexed: 11/17/2022]
Abstract
Many neurologic diseases can initially present as a diagnostic challenge and even when a diagnosis is made, monitoring of disease activity, progression and response to therapy may be limited with existing clinical and paraclinical assessments. As such, the identification of disease specific biomarkers provides a promising avenue by which diseases can be effectively diagnosed, monitored and used as a prognostic indicator for long-term outcomes. Neurofilaments are an integral component of the neuronal cytoskeleton, where assessment of neurofilaments in the blood, cerebrospinal fluid (CSF) and diseased tissue has been shown to have value in providing diagnostic clarity, monitoring disease activity, tracking progression and treatment efficacy, as well as lending prognostic insight into long-term outcomes. As such, this review attempts to provide a glimpse into the structure and function of neurofilaments, their role in various neurologic and non-neurologic disorders, including uncommon conditions with recent knowledge of neurofilament-related pathology, as well as their applicability in future clinical practice.
Collapse
Affiliation(s)
- Gloria Mak
- McMaster University, Department of Medicine, Hamilton, Ontario, Canada
| | - Suresh Menon
- McMaster University, Department of Medicine, Hamilton, Ontario, Canada
| | - Jian-Qiang Lu
- McMaster University, Department of Pathology and Molecular Medicine, Hamilton, Ontario, Canada.
| |
Collapse
|
4
|
Update on myelin imaging in neurological syndromes. Curr Opin Neurol 2022; 35:467-474. [PMID: 35788545 DOI: 10.1097/wco.0000000000001078] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/26/2022]
Abstract
PURPOSE OF REVIEW Myelin water imaging (MWI) is generally regarded as the most rigorous approach for noninvasive, in-vivo measurement of myelin content, which has been histopathologically validated. As such, it has been increasingly applied to neurological diseases with white matter involvement, especially those affecting myelin. This review provides an overview of the most recent research applying MWI in neurological syndromes. RECENT FINDINGS Myelin water imaging has been applied in neurological syndromes including multiple sclerosis, Alzheimer's disease, Huntington's disease, traumatic brain injury, Parkinson's disease, cerebral small vessel disease, leukodystrophies and HIV. These syndromes generally showed alterations observable with MWI, with decreased myelin content tending to correlate with lower cognitive scores and worse clinical presentation. MWI has also been correlated with genetic variation in the APOE and PLP1 genes, demonstrating genetic factors related to myelin health. SUMMARY MWI can detect and quantify changes not observable with conventional imaging, thereby providing insight into the pathophysiology and disease mechanisms of a diverse range of neurological syndromes.
Collapse
|
5
|
LoPresti P. Serum-Based Biomarkers in Neurodegeneration and Multiple Sclerosis. Biomedicines 2022; 10:biomedicines10051077. [PMID: 35625814 PMCID: PMC9138270 DOI: 10.3390/biomedicines10051077] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/09/2022] [Revised: 04/27/2022] [Accepted: 04/29/2022] [Indexed: 02/04/2023] Open
Abstract
Multiple Sclerosis (MS) is a debilitating disease with typical onset between 20 and 40 years of age, so the disability associated with this disease, unfortunately, occurs in the prime of life. At a very early stage of MS, the relapsing-remitting mobility impairment occurs in parallel with a progressive decline in cognition, which is subclinical. This stage of the disease is considered the beginning of progressive MS. Understanding where a patient is along such a subclinical phase could be critical for therapeutic efficacy and enrollment in clinical trials to test drugs targeted at neurodegeneration. Since the disease course is uneven among patients, biomarkers are needed to provide insights into pathogenesis, diagnosis, and prognosis of events that affect neurons during this subclinical phase that shapes neurodegeneration and disability. Thus, subclinical cognitive decline must be better understood. One approach to this problem is to follow known biomarkers of neurodegeneration over time. These biomarkers include Neurofilament, Tau and phosphotau protein, amyloid-peptide-β, Brl2 and Brl2-23, N-Acetylaspartate, and 14-3-3 family proteins. A composite set of these serum-based biomarkers of neurodegeneration might provide a distinct signature in early vs. late subclinical cognitive decline, thus offering additional diagnostic criteria for progressive neurodegeneration and response to treatment. Studies on serum-based biomarkers are described together with selective studies on CSF-based biomarkers and MRI-based biomarkers.
Collapse
Affiliation(s)
- Patrizia LoPresti
- Department of Psychology, The University of Illinois at Chicago, 1007 West Harrison Street, Chicago, IL 60607, USA
| |
Collapse
|