Perfusion MRI in automatic classification of multiple sclerosis lesion subtypes
Abstract This retrospective and exploratory study investigated the efficiency of the 3T perfusion magnetic resonance imaging (MRI) at the classification of MS lesion subtypes. For the MS lesion subtype classification, firstly, it was necessary to segment all MS lesions. Therefore, a Bayesian classif...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2022-06-01
|
| Series: | IET Signal Processing |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/sil2.12101 |
| _version_ | 1826830954183786496 |
|---|---|
| author | Ehsan Homayouny Rasoul Mahdavifar Khayati Seyed Massood Nabavi Vania Karami |
| author_facet | Ehsan Homayouny Rasoul Mahdavifar Khayati Seyed Massood Nabavi Vania Karami |
| author_sort | Ehsan Homayouny |
| collection | DOAJ |
| description | Abstract This retrospective and exploratory study investigated the efficiency of the 3T perfusion magnetic resonance imaging (MRI) at the classification of MS lesion subtypes. For the MS lesion subtype classification, firstly, it was necessary to segment all MS lesions. Therefore, a Bayesian classifier based on the adaptive mixture method was used to segment all lesions, and an artificial neural network (ANN) employed a multi‐layer Perceptron as a subtype classifier. The Bayesian classifier accomplished the segmentation of lesions using Fluid Attenuated Inversion Recovery automatically, and the ANN part was used as a subtype classifier that worked based on extracted information from perfusion MRI (i.e. Mean Transit Time and Cerebral Blood Volume maps) along with the intensity information of the conventional multi‐channel MRI in segmented lesions. Adding 3‐Tesla perfusion MRI to the proposed model for the subtype classification led to an increment of about 7% and 13% in the sensitivity of acute and chronic lesion classifications, respectively. The sensitivity of T2 lesions did not meaningfully change. The overall accuracy of the classification for acute, chronic, and T2 lesion classifications was 96.1%, 90.5%, and 92.9%, respectively. The proposed architectures reached high sensitivity in discrimination between MS lesion subtypes when 3T perfusion MRIs were used. |
| first_indexed | 2024-03-09T09:24:43Z |
| format | Article |
| id | doaj.art-1923152ee5164eeda583c1e640419857 |
| institution | Directory Open Access Journal |
| issn | 1751-9675 1751-9683 |
| language | English |
| last_indexed | 2025-02-16T09:50:01Z |
| publishDate | 2022-06-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Signal Processing |
| spelling | doaj.art-1923152ee5164eeda583c1e6404198572025-02-03T01:31:54ZengWileyIET Signal Processing1751-96751751-96832022-06-0116437739010.1049/sil2.12101Perfusion MRI in automatic classification of multiple sclerosis lesion subtypesEhsan Homayouny0Rasoul Mahdavifar Khayati1Seyed Massood Nabavi2Vania Karami3Biomedical Engineering Department Shahed University Tehran IranBiomedical Engineering Department Shahed University Tehran IranNeurology and Neurodegenerative Department Center for Neuroscience and Cognition Royan Institute Tehran IranNeurology and Neurosurgery Department Montreal Neurological Institute‐ Hospital (MNI) McGill University Montreal Québec CanadaAbstract This retrospective and exploratory study investigated the efficiency of the 3T perfusion magnetic resonance imaging (MRI) at the classification of MS lesion subtypes. For the MS lesion subtype classification, firstly, it was necessary to segment all MS lesions. Therefore, a Bayesian classifier based on the adaptive mixture method was used to segment all lesions, and an artificial neural network (ANN) employed a multi‐layer Perceptron as a subtype classifier. The Bayesian classifier accomplished the segmentation of lesions using Fluid Attenuated Inversion Recovery automatically, and the ANN part was used as a subtype classifier that worked based on extracted information from perfusion MRI (i.e. Mean Transit Time and Cerebral Blood Volume maps) along with the intensity information of the conventional multi‐channel MRI in segmented lesions. Adding 3‐Tesla perfusion MRI to the proposed model for the subtype classification led to an increment of about 7% and 13% in the sensitivity of acute and chronic lesion classifications, respectively. The sensitivity of T2 lesions did not meaningfully change. The overall accuracy of the classification for acute, chronic, and T2 lesion classifications was 96.1%, 90.5%, and 92.9%, respectively. The proposed architectures reached high sensitivity in discrimination between MS lesion subtypes when 3T perfusion MRIs were used.https://doi.org/10.1049/sil2.12101classificationlesion subtypesmultiple sclerosisperfusion MRI |
| spellingShingle | Ehsan Homayouny Rasoul Mahdavifar Khayati Seyed Massood Nabavi Vania Karami Perfusion MRI in automatic classification of multiple sclerosis lesion subtypes IET Signal Processing classification lesion subtypes multiple sclerosis perfusion MRI |
| title | Perfusion MRI in automatic classification of multiple sclerosis lesion subtypes |
| title_full | Perfusion MRI in automatic classification of multiple sclerosis lesion subtypes |
| title_fullStr | Perfusion MRI in automatic classification of multiple sclerosis lesion subtypes |
| title_full_unstemmed | Perfusion MRI in automatic classification of multiple sclerosis lesion subtypes |
| title_short | Perfusion MRI in automatic classification of multiple sclerosis lesion subtypes |
| title_sort | perfusion mri in automatic classification of multiple sclerosis lesion subtypes |
| topic | classification lesion subtypes multiple sclerosis perfusion MRI |
| url | https://doi.org/10.1049/sil2.12101 |
| work_keys_str_mv | AT ehsanhomayouny perfusionmriinautomaticclassificationofmultiplesclerosislesionsubtypes AT rasoulmahdavifarkhayati perfusionmriinautomaticclassificationofmultiplesclerosislesionsubtypes AT seyedmassoodnabavi perfusionmriinautomaticclassificationofmultiplesclerosislesionsubtypes AT vaniakarami perfusionmriinautomaticclassificationofmultiplesclerosislesionsubtypes |