Comparison of Machine Learning Methods Using Spectralis OCT for Diagnosis and Disability Progression Prognosis in Multiple Sclerosis

Montolío, Alberto; Cegoñino, José; García‐Martín, Elena; Palomar, Amaya Pérez del

doi:10.1007/s10439-022-02930-3

Cited by 31 publications

(31 citation statements)

References 67 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Likewise, Montolío et al [ 64 ] used OCT to measure patients’ RNFL thinness for MS diagnosis and prognosis using ML techniques. The study included 72 MS patients and 30 healthy controls, and the classifiers used in this study included SVM, Multiple Linear Regression (MLR), KNN, DT, NB, ensemble classifier (EC), and long short-term memory (LSTM-RNN).…”

Section: Related Studiesmentioning

confidence: 99%

Multiple Sclerosis Diagnosis Using Machine Learning and Deep Learning: Challenges and Opportunities

Aslam

Khan

Bashamakh

et al. 2022

Sensors

View full text Add to dashboard Cite

Multiple Sclerosis (MS) is a disease that impacts the central nervous system (CNS), which can lead to brain, spinal cord, and optic nerve problems. A total of 2.8 million are estimated to suffer from MS. Globally, a new case of MS is reported every five minutes. In this review, we discuss the proposed approaches to diagnosing MS using machine learning (ML) published between 2011 and 2022. Numerous models have been developed using different types of data, including magnetic resonance imaging (MRI) and clinical data. We identified the methods that achieved the best results in diagnosing MS. The most implemented approaches are SVM, RF, and CNN. Moreover, we discussed the challenges and opportunities in MS diagnosis to improve AI systems to enable researchers and practitioners to enhance their approaches and improve the automated diagnosis of MS. The challenges faced by automated MS diagnosis include difficulty distinguishing the disease from other diseases showing similar symptoms, protecting the confidentiality of the patients’ data, achieving reliable ML models that are also easily understood by non-experts, and the difficulty of collecting a large reliable dataset. Moreover, we discussed several opportunities in the field such as the implementation of secure platforms, employing better AI solutions, developing better disease prognosis systems, combining more than one data type for better MS prediction and using OCT data for diagnosis, utilizing larger, multi-center datasets to improve the reliability of the developed models, and commercialization.

show abstract

Section: Related Studiesmentioning

confidence: 99%

Multiple Sclerosis Diagnosis Using Machine Learning and Deep Learning: Challenges and Opportunities

Aslam

Khan

Bashamakh

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…Previous studies have shown that RNFL thickness decreases over time in MS patients, with a gradually increasing trend. Previous studies have demonstrated that RNFL thickness is correlated with visual impairment, axon loss, brain atrophy, cognitive and physical disorders, and MRI abnormalities (14).…”

Section: Discussionmentioning

confidence: 99%

Assessment of Retinal Nerve Fiber Layer (RNFL) and Retinal Ganglion Cell Layer (RGCL) Thickness in Radiologically Isolated Syndrome (RIS)

et al. 2023

View full text Add to dashboard Cite

Background: Three-thirds of people with radiologically isolated syndrome (RIS) develop multiple sclerosis (MS) within five years following their first brain magnetic resonance imaging (MRI). Subclinical applications of optical coherence tomography (OCT) include measuring the thickness of different retinal layers and monitoring the progression of visual pathway atrophy and neurodegeneration in relation to the progress of the entire brain. Objectives: Our OCT study was conducted in individuals with RIS to evaluate the thickness of the macular retinal nerve fiber layer (mRNFL) and the retinal ganglion cell layer (RGCL). Methods: In this study, 22 patients with RIS and 23 healthy individuals healthy control (HC) were enrolled. The control group and the RIS subjects underwent retinal imaging with OCT. Results: Total mRNFL thickness was 110.34 ± 13.71 μm in the RIS patients and 112.10 ± 11.23 μm in the HC group. Regional analysis of the mRNFL showed that the difference in thickness was more prominent in the superior quadrant. In regards to ganglion cell layer (GCL)++ thickness, the RIS and HCs population showed statistically significant differences in the nasal (P = 0.041), inferior (P = 0.040), and superior (P = 0.045) quadrants. The nasal (P = 0.041) quadrant showed the highest reduction in thickness compared to other regions of the GCL++. Meanwhile, no significant reduction was seen in GCL+ thickness (P-value > 0.05). When the thickness of the retinal layer of the right eye was compared to that of the left eye of the RIS group, no statistically significant differences were found (P-value > 0.05). Conclusions: Compared to the control group, the RIS group had a lower mean thickness of mRNFL and GCL++, indicating retinal neuroaxonal loss.

show abstract

“…In a recent study, researchers developed a system based on a convolutional neural network that can classify the disease according to the thickness of the OCT scans, thus assisting in the early diagnosis of the disorder [ 40 ]. Machine learning has also been successfully used to predict disability progression in pwMS by analysing RNFL thickness [ 41 ].…”

Section: Optical Coherence Tomography In Multiple Sclerosismentioning

confidence: 99%

Optical Coherence Tomography and Optical Coherence Tomography with Angiography in Multiple Sclerosis

et al. 2022

View full text Add to dashboard Cite

Multiple sclerosis (MS) is an inflammatory and neurodegenerative, potentially disabling disease of the central nervous system. OCT (Optical Coherence Tomography) and OCT-A (Optical Coherence Tomography with Angiography) are imaging techniques for the retina and choroid that are used in the diagnosis and monitoring of ophthalmological conditions. Their use has recently expanded the study of several autoimmune disorders, including MS. Although their application in MS remains unclear, the results seem promising. This review aimed to provide insight into the most recent OCT and OCT-A findings in MS and may function as a reference point for future research. According to the current literature, the retinal nerve fibre layer (RNFL) and ganglion cell-inner plexiform complex (GC-IPL) are significantly reduced in people with MS and are inversely correlated with disease duration. The use of OCT might help distinguish between MS and neuromyelitis optica spectrum disorders (NMOSD), as the latter presents with more pronounced thinning in both the RNFL and GC-IPL. The OCT-A findings in MS include reduced vessel density in the macula, peripapillary area, or both, and the enlargement of the foveal avascular zone (FAZ) in the setting of optic neuritis. Additionally, OCT-A might be able to detect damage in the very early stages of the disease as well as disease progression in severe cases.

show abstract

Comparison of Machine Learning Methods Using Spectralis OCT for Diagnosis and Disability Progression Prognosis in Multiple Sclerosis

Cited by 31 publications

References 67 publications

Multiple Sclerosis Diagnosis Using Machine Learning and Deep Learning: Challenges and Opportunities

Multiple Sclerosis Diagnosis Using Machine Learning and Deep Learning: Challenges and Opportunities

Assessment of Retinal Nerve Fiber Layer (RNFL) and Retinal Ganglion Cell Layer (RGCL) Thickness in Radiologically Isolated Syndrome (RIS)

Optical Coherence Tomography and Optical Coherence Tomography with Angiography in Multiple Sclerosis

Contact Info

Product

Resources

About