1
|
Shekari F, Vard A, Adibi I, Danesh-Mobarhan S. Investigating the feasibility of differentiating MS active lesions from inactive ones using texture analysis and machine learning methods in DWI images. Mult Scler Relat Disord 2024; 82:105363. [PMID: 38118289 DOI: 10.1016/j.msard.2023.105363] [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: 08/06/2023] [Revised: 12/04/2023] [Accepted: 12/05/2023] [Indexed: 12/22/2023]
Abstract
BACKGROUND Magnetic resonance imaging (MRI) is commonly used in conjunction with a gadolinium-based contrast agent (GBCA) to distinguish active multiple sclerosis (MS) lesions. However, recent studies have raised concerns regarding the long-term effects of the accumulation of GBCA in the body. Thus, the purpose of this study is to investigate the possibility of using texture analysis in diffusion-weighted imaging (DWI) and machine learning algorithms to discriminate active from inactive MS lesions without the use of GBCA. METHODS To achieve this purpose, we introduce an image processing pipeline. In the proposed pipeline, following registration and alignment of slices, MS lesions from DWI images are segmented and quantized. Next, different texture analysis methods are employed to extract texture features from the lesions. Then, a two-stage feature reduction method is applied, in which the first stage involves a statistical t-test and the second stage relies on principal component analysis (PCA), sequential forward selection (SFS), sequential backward selection (SBS), and ReliefF algorithms. Finally, we use five classifiers logistic regression (LR), support vector machine (SVM), decision tree (DT), K nearest neighbor (KNN), and linear discriminant analysis (LDA) in a 5-fold cross-validation procedure to determine active and inactive MS lesions. RESULTS In this study, we collected and prepared 255 active/inactive MS lesions from MRI scans of 34 patients diagnosed with MS, with a mean age of 35.56±10.89. Among 89 texture features extracted, 63 features showed statistically significant differences between the means of active and inactive lesions (P<0.05). The SVM classifier with the PCA feature reduction algorithm demonstrated the best performance with an average accuracy of 0.960 (±0.024), specificity and precision of 1.0, sensitivity of 0.913 (±0.053), and AUC of 0.957 (±0.027). CONCLUSION Our study indicates that DWI changes detected using texture analysis-based machine learning models can precisely differentiate active from inactive MS lesions. This finding provides valuable clinical information for the early diagnosis and effective monitoring of MS disease.
Collapse
Affiliation(s)
- Farshad Shekari
- Department of Bioelectrics and Biomedical Engineering, School of Advanced Technologies in Medicine, Isfahan University of Medical Sciences, Isfahan 81746-73461, Iran; Student Research Center, Isfahan University of Medical Sciences, Isfahan, Iran
| | - Alireza Vard
- Department of Bioelectrics and Biomedical Engineering, School of Advanced Technologies in Medicine, Isfahan University of Medical Sciences, Isfahan 81746-73461, Iran; Medical Image and Signal Processing Research Center, Isfahan University of Medical Sciences, Isfahan, Iran.
| | - Iman Adibi
- Department of Neurology, School of Medicine, Isfahan University of Medical Sciences, Isfahan, Iran,; Isfahan Neurosciences Research Center, Isfahan University of Medical Sciences, Isfahan, Iran
| | - Safieh Danesh-Mobarhan
- Department of Radiology, School of Medicine, Isfahan University of Medical Sciences, Isfahan, Iran
| |
Collapse
|
2
|
Ismail MA, Elsayed NM. Diffusion-Weighted Images and Contrast-Enhanced MRI in the Diagnosis of Different Stages of Multiple Sclerosis of the Central Nervous System. Cureus 2023; 15:e41650. [PMID: 37575819 PMCID: PMC10420334 DOI: 10.7759/cureus.41650] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 07/09/2023] [Indexed: 08/15/2023] Open
Abstract
Introduction Multiple sclerosis (MS) is one of the most prevalent disorders of the central nervous system (CNS), and it can be observed in the field of radiological cross-sectional magnetic resonance imaging (MRI). The prevalence of MS in Saudi Arabia has increased as compared to the past few years. MRI is the gold standard non-invasive modality of choice in MS diagnosis according to the National Multiple Sclerosis Society (NMSS), New York City. This study aimed to highlight the significance of using diffusion-weighted images (DWIs) and the use of contrast media in the MS protocol, as well as the importance of identifying the suitable time of imaging after contrast enhancement to detect active lesions. Methods A retrospective cross-sectional study was conducted of 100 MS patients with an age range of 17 to 56 years. The data set included 41 active cases and 59 inactive cases. All patients had an MRI standard protocol of both the brain and spine in addition to DWI sequence and contrast agent (CA) injection, with images taken in early and delayed time. Results Of the patients, 71% were female and 29% were male. Active MS disease was more significant at younger ages than at older ages. Active lesions were significantly enhanced in delayed contrast images and showed high signal intensity in both the DWI and apparent diffusion coefficient (ADC) map, while inactive lesions showed no enhancement after contrast injection and showed an iso-signal intensity in both the DWI and ADC map. Conclusion The use of CA has developed over the years in the diagnosis of MS patients. In this study, the relationship between active lesions, DWI, and delayed contrast enhancement is very strong. In future research, we recommend adding a DWI sequence for the suspected active MS spine lesions in addition to delayed enhancement time in active MS after contrast injection to increase MRI sensitivity toward active MS lesions of the brain and spinal cord as well.
Collapse
Affiliation(s)
- Mashael A Ismail
- Radiologic Sciences, Faculty of Applied Medical Sciences, King Abdullah Medical Complex, Ministry of Health, Jeddah, SAU
| | - Naglaa M Elsayed
- Radiologic Sciences, Faculty of Applied Medical Sciences, King Abdulaziz University, Jeddah, SAU
- Diagnostic Radiology, Faculty of Medicine, Cairo University, Cairo, EGY
| |
Collapse
|
3
|
Clinical applications of diffusion-weighted sequence in brain imaging: beyond stroke. Neuroradiology 2021; 64:15-30. [PMID: 34596716 PMCID: PMC8484843 DOI: 10.1007/s00234-021-02819-3] [Citation(s) in RCA: 8] [Impact Index Per Article: 2.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/07/2021] [Accepted: 09/10/2021] [Indexed: 11/20/2022]
Abstract
Diffusion-weighted imaging (DWI) is a well-established MRI sequence for diagnosing early stroke and provides therapeutic implications. However, DWI yields pertinent information in various other brain pathologies and helps establish a specific diagnosis and management of other central nervous system disorders. Some of these conditions can present with acute changes in neurological status and mimic stroke. This review will focus briefly on diffusion imaging techniques, followed by a more comprehensive description of the utility of DWI in common neurological entities beyond stroke.
Collapse
|
4
|
Correlation between contrast enhanced plaques and plaque diffusion restriction and their signal intensities in FLAIR images in patients who admitted with acute symptoms of multiple sclerosis. J Med Imaging Radiat Sci 2021; 52:121-126. [DOI: 10.1016/j.jmir.2020.12.001] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/04/2020] [Revised: 10/26/2020] [Accepted: 12/15/2020] [Indexed: 11/24/2022]
|
5
|
G H M, G PJ, A A, P G. Detection of Active Plaques in Multiple Sclerosis using 3 and 12 Directional Diffusion-weighted Imaging: Comparison with Gadolinium-enhanced MR Imaging. J Biomed Phys Eng 2020; 10:737-744. [PMID: 33364211 PMCID: PMC7753260 DOI: 10.31661/jbpe.v0i0.925] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/13/2018] [Accepted: 06/10/2018] [Indexed: 11/16/2022]
Abstract
Background Multiple Sclerosis (MS), distinguished by aggravating the function of central nervous system because of inflammatory demyelination. The most sensitive method for MS diagnosis is Magnetic resonance imaging (MRI). To distinguish inactive and active MS lesions, contrast-enhanced T1-weighted imaging (CE T1WI) is being used as a gold standard. There are some contraindications in gadolinium based contrast agents (GBCAs) usage. Moreover, diffusion-weighted imaging (DWI) can discover diffusion changes involved inflammatory lesions. Objective The current research aims at investigating if typical DWI (3 directional) and 12 directional DWI could be a substitute for CE T1WI in order to show active lesions of MS. Material and Methods In this cross-sectional study, 138 patients with CNS symptoms were examined. For all patients, along with CE T1WI, 3 & 12 directional DWI were performed. Intraclass correlation coefficient (ICC), receiver operating characteristic (ROC), the sensitivity versus specificity plot and the area under the curve (AUC) were calculated. Results There was a contrast enhancement in CE T1WI for 114 patients (82.6%); in addition, hyper-intense lesions on DWI 3 and DWI 12 were shown in 107 (77.5%) and 117 patients (84.7%) in order. Sensitivity, specificity and AUC were 94.7%, 62.5% and 84% for DWI 12. Moreover, the results were 86%, 62.5 and 79% for the sensitivity, specificity and AUC for DWI 3 respectively. Conclusion In spite of lower sensitivity of 12 directional DWI compared to CE T1WI, it could be used as a diagnostic sequence in differentiating enhanced lesions from non-enhanced ones when CE-MRI is a worry.
Collapse
Affiliation(s)
- Meftahi G H
- PhD, Neuroscience Research Centre, Baqiyatallah University of Medical Sciences, Tehran, Iran
| | - Pirzad Jahromi G
- PhD, Neuroscience Research Centre, Baqiyatallah University of Medical Sciences, Tehran, Iran
| | - Azari A
- BSc, Radiology Department, School of Paramedical Sciences, Shiraz University of Medical Sciences, Shiraz, Iran
| | - Ghaemmaghami P
- PhD, Biostatistics Department, School of Medicine, Shiraz University of Medical Sciences, Shiraz, Iran
| |
Collapse
|
6
|
Ding J, Zhu DS, Hong RH, Wu YF, Li ZZ, Zhou XJ, Cai J, Guan YT. The differential expression of natural killer cells in NMOSD and MS. J Clin Neurosci 2019; 71:9-14. [PMID: 31864829 DOI: 10.1016/j.jocn.2019.11.022] [Citation(s) in RCA: 13] [Impact Index Per Article: 2.6] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/19/2019] [Revised: 10/07/2019] [Accepted: 11/19/2019] [Indexed: 12/29/2022]
Abstract
Natural killer (NK) cells are involved in the pathogenesis of inflammatory demyelinating diseases of the central nervous system. However, the differential expressions of NK cells in the peripheral blood of patients with neuromyelitis optica spectrum disorders (NMOSD) and multiple sclerosis (MS) are unknown. This study aimed to explore the differential expressions of NK cells in NMOSD and MS and evaluate the clinical implications of this difference. We performed a cross-sectional study to investigate the expression of NK cells in the peripheral blood of patients with NMOSD (n = 78) and MS (n = 24) and of healthy controls (HC, n = 27). Furthermore, we investigated the relationship between NK cell level and disease phase in 102 patients with NMOSD and MS through Spearman correlation analysis and receiver operating characteristic (ROC) analysis. Our results showed that the median (interquartile range) NK cell levels in acute-phase NMOSD patients, remission-phase NMOSD patients, acute-phase MS patients, and HC subjects were 114.10 (64.75-153.38) cells/µL, 167.60 (116.35-266.15) cells/µL, 282.55 (140.57-368.20) cells/µL, and 221.00 (170.40-269.55) cells/µL, respectively (p < 0.001). The Spearman correlation coefficient (95%) for the relationship between NK level and disease phase in NMOSD patients was 0.366 (0.150-0.550) (p < 0.001). Furthermore, ROC analysis revealed that patients with NK cell values lower than 172.200 cells/µL were more prone to have acute-phase NMOSD than MS. In conclusion, the expression of NK cells in peripheral blood was lower in patients with NMOSD than in patients with MS in the acute phase, and a low expression of NK cells may suggest having acute-phase NMOSD rather than MS.
Collapse
Affiliation(s)
- Jie Ding
- Department of Neurology, Renji Hospital, School of Medicine, Shanghai Jiaotong University, Shanghai 200127, China
| | - De-Sheng Zhu
- Department of Neurology, Renji Hospital, School of Medicine, Shanghai Jiaotong University, Shanghai 200127, China
| | - Rong-Hua Hong
- Department of Neurology, Renji Hospital, School of Medicine, Shanghai Jiaotong University, Shanghai 200127, China
| | - Yi-Fan Wu
- Department of Neurology, Renji Hospital, School of Medicine, Shanghai Jiaotong University, Shanghai 200127, China
| | - Ze-Zhi Li
- Department of Neurology, Renji Hospital, School of Medicine, Shanghai Jiaotong University, Shanghai 200127, China
| | - Xia-Jun Zhou
- Department of Neurology, Renji Hospital, School of Medicine, Shanghai Jiaotong University, Shanghai 200127, China
| | - Jian Cai
- Department of Neurology, Renji Hospital, School of Medicine, Shanghai Jiaotong University, Shanghai 200127, China
| | - Yang-Tai Guan
- Department of Neurology, Renji Hospital, School of Medicine, Shanghai Jiaotong University, Shanghai 200127, China.
| |
Collapse
|
7
|
Abstract
MRI is a commonly used diagnostic tool in neurology, and all neurologists should possess a working knowledge of imaging fundamentals. An overview of current and impending MRI techniques is presented to help the referring clinician communicate better with the imaging department, understand the utility and limitations of current and emerging technology, improve specificity and appropriateness when ordering MRI studies, and recognize key findings.
Collapse
Affiliation(s)
- Nandor K Pinter
- Dent Neurologic Institute, 3980A Sheridan Drive, Suite 101, Amherst, NY 14226, USA; Department of Neurosurgery, State University of New York at Buffalo, Buffalo, NY, USA
| | - Joseph V Fritz
- Dent Neurologic Institute, 3980 Sheridan Drive, Suite 501, Amherst, NY 14226, USA; NeuroNetPro, Amherst, NY, USA.
| |
Collapse
|
8
|
Unal S, Peker E, Erdogan S, Erden MI. Is It Possible to Discriminate Active MS Lesions with Diffusion Weighted Imaging? Eurasian J Med 2019; 51:219-223. [PMID: 31692763 DOI: 10.5152/eurasianjmed.2019.18473] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.6] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/22/2022] Open
Abstract
Objective Patients with multiple sclerosis (MS) are at a risk of gadolinium deposition because of multiple control imaging. Therefore, it is important to determine biomarkers that can differentiate active and chronic lesions without using contrast agent. This study aimed to assess mean apparent diffusion coefficient (ADC) values and signal intensities (SI) on diffusion weighted imaging (DWI) values of active and nonactive lesions. Materials and Methods We included 25 patients in this study. We measured mean ADC values and SI on DWI of the randomly selected active and nonactive lesions and normal appearing white matter (NAWM) for all patients with MS. SI on DWI and ADC values were normalized to the SI of the CSF. We compared all of the measurements between active and nonactive lesions, active lesions and NAWM, and nonactive lesions and NAWM. SI on DWI and mean ADC values of normal healthy white matter (NHWM) of control group were measured. A comparison was made between NHWM and NAWM. Results For patients with active lesions, the mean nADC value was 0.35±0.06 for active lesions and 0.30±0.07 for nonactive lesions (p>0.050). The mean nDWI-SI value was 3.69±0.68 for active lesions was 3.39±0.68 for nonactive lesions (p<0.050). When patients with and without active lesions were compared, both nDWI values and nADC values for active and nonactive lesions were statistically insignificant (p>0.050). Discussion In MS lesions, diffusion alternations can be quantitatively evaluated with ADC mapping. Lesions seen in patients with MS have higher mean ADC values than NAWM and NHWM.
Collapse
Affiliation(s)
- Sena Unal
- Department of Radiology, Ankara University School of Medicine, Ankara, Turkey
| | - Elif Peker
- Department of Radiology, Ankara University School of Medicine, Ankara, Turkey
| | - Seyda Erdogan
- Department of Neurology, Ankara University School of Medicine, Ankara, Turkey
| | - Memet Ilhan Erden
- Department of Radiology, Ankara University School of Medicine, Ankara, Turkey
| |
Collapse
|
9
|
Holdsworth SJ, O'Halloran R, Setsompop K. The quest for high spatial resolution diffusion-weighted imaging of the human brain in vivo. NMR IN BIOMEDICINE 2019; 32:e4056. [PMID: 30730591 DOI: 10.1002/nbm.4056] [Citation(s) in RCA: 28] [Impact Index Per Article: 5.6] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 04/09/2018] [Revised: 09/11/2018] [Accepted: 11/08/2018] [Indexed: 06/09/2023]
Abstract
Diffusion-weighted imaging, a contrast unique to MRI, is used for assessment of tissue microstructure in vivo. However, this exquisite sensitivity to finer scales far above imaging resolution comes at the cost of vulnerability to errors caused by sources of motion other than diffusion motion. Addressing the issue of motion has traditionally limited diffusion-weighted imaging to a few acquisition techniques and, as a consequence, to poorer spatial resolution than other MRI applications. Advances in MRI imaging methodology have allowed diffusion-weighted MRI to push to ever higher spatial resolution. In this review we focus on the pulse sequences and associated techniques under development that have pushed the limits of image quality and spatial resolution in diffusion-weighted MRI.
Collapse
Affiliation(s)
- Samantha J Holdsworth
- Department of Anatomy Medical Imaging & Centre for Brain Research, University of Auckland, Auckland, New Zealand
| | | | - Kawin Setsompop
- Harvard Medical School, Massachusetts General Hospital, Boston, MA, USA
| |
Collapse
|
10
|
Arashloo FT, Hanzaei FF, Sedighi B, Amjad G, Younesi L. Efficacy of diffusion-weighted imaging in symptomatic and asymptomatic multiple sclerotic plaques. J Family Med Prim Care 2019; 8:2409-2413. [PMID: 31463267 PMCID: PMC6691452 DOI: 10.4103/jfmpc.jfmpc_420_19] [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] [Indexed: 11/09/2022] Open
Abstract
Introduction: Magnetic resonance imaging (MRI) currently accompanies clinical findings in disease diagnosis, patients’ follow-up, assessment of drugs complications, and evaluation of treatment response. Although contrast-enhanced MRI (CE-MRI) is considered as the imaging modality of choice for multiple sclerosis (MS), due to disease chronicity, applying multiple doses of gadolinium-based contrast agents (GBCAs) increases the risk of nephrogenic syndrome in patients with acute (ARF) and chronic renal syndromes (CRF). Moreover, the effect of gadolinium on the fetus is not well-known in pregnant patients. Therefore, this study evaluates the possibility of replacing postcontrast images with physiologically based MRI sequences such as diffusion weighted imaging (DWI) and apparent diffusion coefficient (ADC). Method: We prospectively evaluated 26 patients with known multiple sclerosis. The patients with MS attacks and the asymptomatic patients who were referred for follow-up were enrolled. Conventional MRI including postcontrast T1W, DWI, and ADC were performed for all patients. The signal intensity (SI) of all enhancing and nonenhancing plaques of more than 10 × 10 mm size were investigated in all sequences and analyzed. Results: A total of 83 plaques were detected in T2-FLAIR sequences of which 51 plaques were enhanced (68%) after gadolinium administration. While 42 MS plaques had hypersignal intensity in DWI (56%), 32 plaques had iso- or hyposignal intensities in DWI (44%). No statistically significant values were obtained. Conclusion: Although DWI could not replace CE-MRI, using these two modalities together could increase detection of active MS plaques and alter patients’ therapy and prognosis.
Collapse
Affiliation(s)
| | - Farnaz Fahimi Hanzaei
- Clinical Research Unit, Afzalipour Hospital, Kerman University of Medical Sciences, Kerman, Iran
| | - Behnaz Sedighi
- Neurology Research Center, Kerman University of Medical Sciences, Kerman, Iran
| | - Ghazaleh Amjad
- Shahid Akbar Abadi Clinical Research Development Unit, Iran University of Medical Sciences, Tehran, Iran
| | - Ladan Younesi
- Shahid Akbar Abadi Clinical Research Development Unit, Iran University of Medical Sciences, Tehran, Iran
| |
Collapse
|
11
|
Mohammed FF, Ismail MH. Validity of apparent diffusion coefficient (ADC) value in diagnosis and follow-up of multiple sclerosis patients in different clinical subtypes. THE EGYPTIAN JOURNAL OF RADIOLOGY AND NUCLEAR MEDICINE 2018. [DOI: 10.1016/j.ejrnm.2018.07.006] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.2] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/28/2022] Open
|