Diagnosis of multiple sclerosis using multifocal ERG data feature fusion
Autor: | J. Pérez, L. de Santiago, C. Cavalliere, E. Mª Sánchez Morla, A. López-Dorado, M. Ortiz, Elena García-Martín, J.M. Miguel-Jiménez, Elena López-Guillén, Roman Blanco, Luciano Boquete, Maria Jesus Rodrigo |
---|---|
Jazyk: | angličtina |
Rok vydání: | 2021 |
Předmět: |
Support vector machine
genetic structures Computer science Article Correlation Multiple sclerosis Classifier (linguistics) medicine Optic neuritis Continuous wavelet transform Feature fusion business.industry Pattern recognition Filter (signal processing) medicine.disease Matthews correlation coefficient eye diseases Visual field Hardware and Architecture Signal Processing Empirical Mode Decomposition sense organs Artificial intelligence Multifocal electroretinogram business Software Information Systems |
Zdroj: | An International Journal on Information Fusion |
ISSN: | 1872-6305 1566-2535 |
Popis: | Highlights • A computer-aided system for diagnosis of multiple sclerosis is implemented. • 40 features are obtained from the multifocal electroretinogram recordings. • The four most relevant features are selected using a filter and the wrapper selection method. • The classifier produces a Matthews correlation coefficient value of 0.89. • A promising new electrophysiological-biomarker method for diagnosis of multiple sclerosis is identified. The purpose of this paper is to implement a computer-aided diagnosis (CAD) system for multiple sclerosis (MS) based on analysing the outer retina as assessed by multifocal electroretinograms (mfERGs). MfERG recordings taken with the RETI‐port/scan 21 (Roland Consult) device from 15 eyes of patients diagnosed with incipient relapsing-remitting MS and without prior optic neuritis, and from 6 eyes of control subjects, are selected. The mfERG recordings are grouped (whole macular visual field, five rings, and four quadrants). For each group, the correlation with a normative database of adaptively filtered signals, based on empirical model decomposition (EMD) and three features from the continuous wavelet transform (CWT) domain, are obtained. Of the initial 40 features, the 4 most relevant are selected in two stages: a) using a filter method and b) using a wrapper-feature selection method. The Support Vector Machine (SVM) is used as a classifier. With the optimal CAD configuration, a Matthews correlation coefficient value of 0.89 (accuracy = 0.95, specificity = 1.0 and sensitivity = 0.93) is obtained. This study identified an outer retina dysfunction in patients with recent MS by analysing the outer retina responses in the mfERG and employing an SVM as a classifier. In conclusion, a promising new electrophysiological-biomarker method based on feature fusion for MS diagnosis was identified. |
Databáze: | OpenAIRE |
Externí odkaz: |