scholarly journals Computer-Aided Diagnosis of Multiple Sclerosis Using a Support Vector Machine and Optical Coherence Tomography Features

Sensors ◽  
2019 ◽  
Vol 19 (23) ◽  
pp. 5323 ◽  
Author(s):  
Carlo Cavaliere ◽  
Elisa Vilades ◽  
Mª Alonso-Rodríguez ◽  
María Rodrigo ◽  
Luis Pablo ◽  
...  
Keyword(s):  
Multiple Sclerosis ◽  
Support Vector Machine ◽  
Optical Coherence Tomography ◽  
Optic Neuritis ◽  
Confusion Matrix ◽  
Support Vector ◽  
Svm Classifier ◽  
Optical Coherence ◽  
Control Subjects ◽  
Peripapillary Area

The purpose of this paper is to evaluate the feasibility of diagnosing multiple sclerosis (MS) using optical coherence tomography (OCT) data and a support vector machine (SVM) as an automatic classifier. Forty-eight MS patients without symptoms of optic neuritis and forty-eight healthy control subjects were selected. Swept-source optical coherence tomography (SS-OCT) was performed using a DRI (deep-range imaging) Triton OCT device (Topcon Corp., Tokyo, Japan). Mean values (right and left eye) for macular thickness (retinal and choroidal layers) and peripapillary area (retinal nerve fibre layer, retinal, ganglion cell layer—GCL, and choroidal layers) were compared between both groups. Based on the analysis of the area under the receiver operator characteristic curve (AUC), the 3 variables with the greatest discriminant capacity were selected to form the feature vector. A SVM was used as an automatic classifier, obtaining the confusion matrix using leave-one-out cross-validation. Classification performance was assessed with Matthew’s correlation coefficient (MCC) and the AUCCLASSIFIER. The most discriminant variables were found to be the total GCL++ thickness (between inner limiting membrane to inner nuclear layer boundaries), evaluated in the peripapillary area and macular retina thickness in the nasal quadrant of the outer and inner rings. Using the SVM classifier, we obtained the following values: MCC = 0.81, sensitivity = 0.89, specificity = 0.92, accuracy = 0.91, and AUCCLASSIFIER = 0.97. Our findings suggest that it is possible to classify control subjects and MS patients without previous optic neuritis by applying machine-learning techniques to study the structural neurodegeneration in the retina.

Smart Affect Recognition System for Real-Time Biometric Surveillance Using Hybrid Features and Multilayered Binary Structured Support Vector Machine

2020 ◽  
Author(s):  
Thamba Meshach W ◽  
Hemajothi S ◽  
Mary Anita E A
Keyword(s):  
Support Vector Machine ◽  
Confusion Matrix ◽  
Recognition System ◽  
Learning Technologies ◽  
Support Vector ◽  
Affect Recognition ◽  
Svm Classifier ◽  
Ecg Signal ◽  
Hybrid Features ◽  
Structured Support Vector Machine

Abstract Human affect recognition (HAR) using images of facial expression and electrocardiogram (ECG) signal plays an important role in predicting human intention. This system improves the performance of the system in applications like the security system, learning technologies and health care systems. The primary goal of our work is to recognize individual affect states automatically using the multilayered binary structured support vector machine (MBSVM), which efficiently classify the input into one of the four affect classes, relax, happy, sad and angry. The classification is performed efficiently by designing an efficient support vector machine (SVM) classifier in multilayer mode operation. The classifier is trained using the 8-fold cross-validation method, which improves the learning of the classifier, thus increasing its efficiency. The classification and recognition accuracy is enhanced and also overcomes the drawback of ‘facial mimicry’ by using hybrid features that are extracted from both facial images (visual elements) and physiological signal ECG (signal features). The reliability of the input database is improved by acquiring the face images and ECG signals experimentally and by inducing emotions through image stimuli. The performance of the affect recognition system is evaluated using the confusion matrix, obtaining the classification accuracy of 96.88%.

scholarly journals Optical coherence tomography angiography indicates subclinical retinal disease in neuromyelitis optica spectrum disorders

2021 ◽  
pp. 135245852110288
Author(s):  
Lilian Aly ◽  
Eva-Maria Strauß ◽  
Nikolaus Feucht ◽  
Isabella Weiß ◽  
Achim Berthele ◽  
...  
Keyword(s):  
Multiple Sclerosis ◽  
Optical Coherence Tomography ◽  
Optic Neuritis ◽  
Disease Activity ◽  
Optical Coherence Tomography Angiography ◽  
Visual Performance ◽  
Healthy Controls ◽  
Optical Coherence ◽  
Neuromyelitis Optica Spectrum Disorders ◽  
Spectrum Disorders

Background: Neuromyelitis optica spectrum disorders (NMOSD) are neuroinflammatory diseases of the central nervous system. Patients suffer from recurring relapses and it is unclear whether relapse-independent disease activity occurs and whether this is of clinical relevance. Objective: To detect disease-specific alterations of the retinal vasculature that reflect disease activity during NMOSD. Methods: Cross-sectional analysis of 16 patients with NMOSD, 21 patients with relapsing-remitting multiple sclerosis, and 21 healthy controls using retinal optical coherence tomography (OCT), optical coherence tomography angiography (OCT-A), measurement of glial fibrillary acidic protein (GFAP) serum levels, and assessment of visual acuity. Results: Patients with NMOSD but not multiple sclerosis revealed lower foveal thickness (FT) ( p = 0.02) measures and an increase of the foveal avascular zone (FAZ) ( p = 0.02) compared to healthy controls independent to optic neuritis. Reduced FT ( p = 0.01), enlarged FAZ areas ( p = 0.0001), and vessel loss of the superficial vascular complex ( p = 0.01) were linked to higher serum GFAP levels and superficial vessel loss was associated with worse visual performance in patients with NMOSD irrespective of optic neuritis. Conclusion: Subclinical parafoveal retinal vessel loss might occur during NMOSD and might be linked to astrocyte damage and poor visual performance. OCT-A may be a tool to study subclinical disease activity during NMOSD.

scholarly journals Retinal Oxygen Metabolism and Haemodynamics in Patients With Multiple Sclerosis and History of Optic Neuritis

2021 ◽  
Vol 15 ◽  
Author(s):  
Martin Kallab ◽  
Nikolaus Hommer ◽  
Andreas Schlatter ◽  
Gabriel Bsteh ◽  
Patrick Altmann ◽  
...  
Keyword(s):  
Multiple Sclerosis ◽  
Optical Coherence Tomography ◽  
Optic Neuritis ◽  
Layer Thickness ◽  
Oxygen Metabolism ◽  
Retinal Blood Flow ◽  
Oxygen Extraction ◽  
Inner Plexiform Layer ◽  
Optical Coherence ◽  
History Of

Vascular changes and alterations of oxygen metabolism are suggested to be implicated in multiple sclerosis (MS) pathogenesis and progression. Recently developed in vivo retinal fundus imaging technologies provide now an opportunity to non-invasively assess metabolic changes in the neural retina. This study was performed to assess retinal oxygen metabolism, peripapillary capillary density (CD), large vessel density (LVD), retinal nerve fiber layer thickness (RNFLT) and ganglion cell inner plexiform layer thickness (GCIPLT) in patients with diagnosed relapsing multiple sclerosis (RMS) and history of unilateral optic neuritis (ON). 16 RMS patients and 18 healthy controls (HC) were included in this study. Retinal oxygen extraction was modeled using O2 saturations and Doppler optical coherence tomography (DOCT) derived retinal blood flow (RBF) data. CD and LVD were assessed using optical coherence tomography (OCT) angiography. RNFLT and GCIPLT were measured using structural OCT. Measurements were performed in eyes with (MS+ON) and without (MS-ON) history for ON in RMS patients and in one eye in HC. Total oxygen extraction was lowest in MS+ON (1.8 ± 0.2 μl O2/min), higher in MS-ON (2.1 ± 0.5 μl O2/min, p = 0.019 vs. MS+ON) and highest in HC eyes (2.3 ± 0.6 μl O2/min, p = 0.002 vs. MS, ANOVA p = 0.031). RBF was lower in MS+ON (33.2 ± 6.0 μl/min) compared to MS-ON (38.3 ± 4.6 μl/min, p = 0.005 vs. MS+ON) and HC eyes (37.2 ± 4.7 μl/min, p = 0.014 vs. MS+ON, ANOVA p = 0.010). CD, LVD, RNFLT and GCIPL were significantly lower in MS+ON eyes. The present data suggest that structural alterations in the retina of RMS patients are accompanied by changes in oxygen metabolism, which are more pronounced in MS+ON than in MS-ON eyes. Whether these alterations promote MS onset and progression or occur as consequence of disease warrants further investigation.Clinical Trial Registration:ClinicalTrials.gov registry, NCT03401879.

scholarly journals Optical Coherence Tomography and Optical Coherence Tomography Angiography Findings After Optic Neuritis in Multiple Sclerosis

2020 ◽  
Vol 11 ◽  
Author(s):  
Olwen C. Murphy ◽  
Grigorios Kalaitzidis ◽  
Eleni Vasileiou ◽  
Angeliki G. Filippatou ◽  
Jeffrey Lambe ◽  
...  
Keyword(s):  
Multiple Sclerosis ◽  
Optical Coherence Tomography ◽  
Optic Neuritis ◽  
Visual Function ◽  
Inner Plexiform Layer ◽  
Optical Coherence ◽  
Cross Sectional ◽  
Mixed Effect ◽  
Retinal Microvasculature ◽  
History Of

Background: In people with multiple sclerosis (MS), optic neuritis (ON) results in inner retinal layer thinning, and reduced density of the retinal microvasculature.Objective: To compare inter-eye differences (IEDs) in macular optical coherence tomography (OCT) and OCT angiography (OCTA) measures in MS patients with a history of unilateral ON (MS ON) vs. MS patients with no history of ON (MS non-ON), and to assess how these measures correlate with visual function outcomes after ON.Methods: In this cross-sectional study, people with MS underwent OCT and OCTA. Superficial vascular plexus (SVP) density of each eye was quantified using a deep neural network. IEDs were calculated with respect to the ON eye in MS ON patients, and with respect to the right eye in MS non-ON patients. Statistical analyses used mixed-effect regression models accounting for intra-subject correlations.Results: We included 43 MS ON patients (with 92 discrete OCT/OCTA visits) and 14 MS non-ON patients (with 24 OCT/OCTA visits). Across the cohorts, mean IED in SVP density was −2.69% (SD 3.23) in MS ON patients, as compared to 0.17% (SD 2.39) in MS non-ON patients (p = 0.002). When the MS ON patients were further stratified according to time from ON and compared to MS non-ON patients with multiple cross-sectional analyses, we identified that IED in SVP density was significantly increased in MS ON patients at 1–3 years (p = < 0.001) and >3 years post-ON (p < 0.001), but not at <3 months (p = 0.21) or 3–12 months post-ON (p = 0.07), while IED in ganglion cell + inner plexiform layer (GCIPL) thickness was significantly increased in MS ON patients at all time points post-ON (p ≦ 0.01 for all). IED in SVP density and IED in GCIPL thickness demonstrated significant relationships with IEDs in 100% contrast, 2.5% contrast, and 1.25% contrast letter acuity in MS ON patients (p < 0.001 for all).Conclusions: Our findings suggest that increased IED in SVP density can be detected after ON in MS using OCTA, and detectable changes in SVP density after ON may occur after changes in GCIPL thickness. IED in SVP density and IED in GCIPL thickness correlate well with visual function outcomes in MS ON patients.

Sign in / Sign up

Export Citation Format

Share Document