Automatic Segmentation of Retinal Layers in Multiple Neurodegenerative Disorder Scenarios.

Retinal Optical Coherence Tomography (OCT) allows the non-invasive direct observation of the central nervous system, enabling the measurement and extraction of biomarkers from neural tissue that can be helpful in the assessment of ocular, systemic and Neurological Disorders (ND). Deep learning models can be trained to segment the retinal layers for biomarker extraction. However, the onset of ND can have an impact on the neural tissue, which can lead to the degraded performance of models not exposed to images displaying signs of disease during training. We present a fully automatic approach for the retinal layer segmentation in multiple neurodegenerative disorder scenarios, using an annotated dataset of patients of the most prevalent NDs: Alzheimer's disease, Parkinson's disease, multiple sclerosis and essential tremor, along with healthy control patients. Furthermore, we present a two-part, comprehensive study on the effects of ND on the performance of these models. The results show that images of healthy patients may not be sufficient for the robust training of automated segmentation models intended for the analysis of ND patients, and that using images representative of different NDs can increase the model performance. These results indicate that the presence or absence of patients of ND in datasets should be taken into account when training deep learning models for retinal layer segmentation, and that the proposed approach can provide a valuable tool for the robust and reliable diagnosis in multiple scenarios of ND.

Explainable artificial intelligence toward usable and trustworthy computer-aided diagnosis of multiple sclerosis from Optical Coherence Tomography.

BACKGROUND: Several studies indicate that the anterior visual pathway provides information about the dynamics of axonal degeneration in Multiple Sclerosis (MS). Current research in the field is focused on the quest for the most discriminative features among patients and controls and the development of machine learning models that yield computer-aided solutions widely usable in clinical practice. However, most studies are conducted with small samples and the models are used as black boxes. Clinicians should not trust machine learning decisions unless they come with comprehensive and easily understandable explanations. MATERIALS AND METHODS: A total of 216 eyes from 111 healthy controls and 100 eyes from 59 patients with relapsing-remitting MS were enrolled. The feature set was obtained from the thickness of the ganglion cell layer (GCL) and the retinal nerve fiber layer (RNFL). Measurements were acquired by the novel Posterior Pole protocol from Spectralis Optical Coherence Tomography (OCT) device. We compared two black-box methods (gradient boosting and random forests) with a glass-box method (explainable boosting machine). Explainability was studied using SHAP for the black-box methods and the scores of the glass-box method. RESULTS: The best-performing models were obtained for the GCL layer. Explainability pointed out to the temporal location of the GCL layer that is usually broken or thinning in MS and the relationship between low thickness values and high probability of MS, which is coherent with clinical knowledge. CONCLUSIONS: The insights on how to use explainability shown in this work represent a first important step toward a trustworthy computer-aided solution for the diagnosis of MS with OCT.

Evaluation of multiple sclerosis severity using a new OCT tool.

PURPOSE: To assess the ability of a new posterior pole protocol to detect areas with significant differences in retinal nerve fiber layer (RNFL) and ganglion cell layer (GCL) thickness in patients with multiple sclerosis versus healthy control subjects; in addition, to assess the correlation between RNFL and GCL thickness, disease duration, and the Expanded Disability Status Scale (EDSS). METHODS: We analyzed 66 eyes of healthy control subjects and 100 eyes of remitting-relapsing multiple sclerosis (RR-MS) patients. Double analysis based on first clinical symptom onset (CSO) and conversion to clinically definite MS (CDMS) was performed. The RR-MS group was divided into subgroups by CSO and CDMS year: CSO-1 (≤ 5 years) and CSO-2 (≥ 6 years), and CDMS-1 (≤ 5 years) and CDMS-2 (≥ 6 years). RESULTS: Significant differences in RNFL and GCL thickness were found between the RR-MS group and the healthy controls and between the CSO and CDMS subgroups and in both layers. Moderate to strong correlations were found between RNFL and GCL thickness and CSO and CDMS. Furthermore, we observed a strong correlation with EDSS 1 year after the OCT examination. CONCLUSIONS: The posterior pole protocol is a useful tool for assessing MS and can reveal differences even in early stages of the disease. RNFL thickness shows a strong correlation with disability status, while GCL thickness correlates better with disease duration.

Diagnosis of multiple sclerosis using optical coherence tomography supported by artificial intelligence.

BACKGROUND: Current procedures for diagnosing multiple sclerosis (MS) present a series of limitations, making it critically important to identify new biomarkers. The aim of the study was to identify new biomarkers for the early diagnosis of MS using spectral-domain optical coherence tomography (OCT) and artificial intelligence. METHODS: Spectral domain OCT was performed on 79 patients with relapsing-remitting multiple sclerosis (RRMS) (disease duration ≤ 2 years, no history of optic neuritis) and on 69 age-matched healthy controls using the posterior pole protocol that incorporates the anatomic Positioning System. Median retinal thickness values in both eyes and inter-eye difference in healthy controls and patients were evaluated by area under the receiver operating characteristic (AUROC) curve analysis in the foveal, parafoveal and perifoveal areas and in the overall area spanned by the three rings. The structures with the greatest discriminant capacity - retinal thickness and inter-eye difference - were used as inputs to a convolutional neural network to assess the diagnostic capability. RESULTS: Analysis of retinal thickness and inter-eye difference in RRMS patients revealed that greatest alteration occurred in the ganglion cell (GCL), inner plexiform (IPL), and inner retinal (IRL) layers. By using the average thickness of the GCL (AUROC = 0.82) and the inter-eye difference in the IPL (AUROC = 0.71) as inputs to a two-layer convolutional neural network, automatic diagnosis attained accuracy = 0.87, sensitivity = 0.82, and specificity = 0.92. CONCLUSION: This study adds weight to the argument that neuroretinal structure analysis could be incorporated into the diagnostic criteria for MS.

Assessment of visual function and the neuroretina in subjects diagnosed with congenital anomaly of color vision.

This cross-sectional and observational study includes 50 eyes of subjects with color blindness and 50 eyes of control subjects. Visual function (visual acuity, contrast sensitivity, and color vision) and neuroretinal structure were assessed in all subjects using optical coherence tomography (OCT). Significant thinning of the retinal nerve fiber layer, ganglion cell layer, and retina were observed in the color blindness group. Significant thinning was also recorded in layers that involve photoreceptor nuclei (between the outer limiting layer and the Bruch membrane and between the outer plexiform layer and the outer limiting membrane). OCT evaluation based on retinal segmentation is a rapid (5-10 minutes) non-invasive technique and seems to be a good biomarker of color blindness.

Ability of Swept-source OCT and OCT-angiography to detect neuroretinal and vasculature changes in patients with Parkinson disease and essential tremor.

BACKGROUND/OBJECTIVES: To evaluate the ability of swept-source optical coherence tomography (SS-OCT) implemented with angiography analysis (SS-OCTA) to detect neuro-retinal and vasculature changes in patients with Parkinson's disease (PD) and essential tremor (ET), and to distinguish between both pathologies. SUBJECTS/METHODS: A total 42 PD and 26 ET patients and 146 controls underwent retinal evaluation using SS-OCT plus OCT-Angio™. The macular (m) and peripapillary (p) retinal nerve fiber layer (RNFL) and ganglion cell layer (GCL), and macular vasculature were assessed. A Linear discriminant function (LDF) was calculated to evaluate the diagnostic ability of SS-OCTA in both PD and ET. RESULTS: PD patients presented a reduction in mRNFL (p < 0.005), mGCL (all sectors, p < 0.05) and pRNFL (p < 0.005) vs healthy controls, and in mRNFL and pRNFL vs ET patients (p < 0.001). ET patients showed a significant reduction in mGCL vs controls (p < 0.001). No differences were observed in the macular vasculature between groups. Predictive diagnostic variables were significant only for PD and a LDF was obtained with an area under the ROC curve of 0.796. CONCLUSIONS: Neuro-retinal thinning is present in both diseases, being greater in PD. While SS-OCT could be useful in diagnosing ET and PD, the diagnostic potential for SS-OCTA based on an LDF applies only to PD, not ET.

Diagnostic Ability and Capacity of Optical Coherence Tomography-Angiography to Detect Retinal and Vascular Changes in Patients with Fibromyalgia.

Background: To evaluate the neuroretina and retinal vasculature of fibromyalgia (FM) patients and calculate a linear discriminant function (LDF) to improve retinal parameters' contribution to FM diagnosis. Methods: Fifty FM patients and 232 healthy controls underwent retinal evaluation using swept-source optical coherence tomography (SS-OCT) angiography (Triton plus; Topcon) and spectral domain OCT (SD-OCT) (Spectralis; Heidelberg). The macular (m) and peripapillary (p) retinal nerve fibre layer (RNFL) and ganglion cell layer (GCL) were assessed, as was the macular vascular density. A logistic regression analysis was performed, and an LDF was calculated to evaluate OCT's contribution to FM diagnosis. Results: With Triton OCT, the patients presented pRNFL thinning in the temporal sector (p=0.006). Spectralis OCT measurements showed decreased pRNFL in patients in the following sectors: superonasal, p=0.001; nasal, p=0.001; inferonasal, p=0.006; temporal, p=0.001; and inferotemporal, p=0.001. No significant differences were observed in the macular vascular plexus between patients and controls. However, vascular density in the superior sector showed a strong inverse correlation with disease duration (r = -0.978, p=0.022). The LDF calculated for Spectralis OCT yielded an area under the ROC curve of 0.968. Conclusions: FM patients present RNFL thinning observable using SS- and SD-OCT. However, these patients show similar vascular density in the macular area to healthy controls. The LDF that combines several RNFL parameters obtained using Spectralis OCT gives this device a powerful ability to differentiate between healthy individuals and individuals with FM.

Evaluation of Progressive Retinal Degeneration in Bipolar Disorder Patients over a Period of 5 Years.

PURPOSE: To quantify visual and retinal changes in patients with bipolar disorder (BD) over 5 years, compared with controls. METHODS: Thirty-eight patients with BD and 122 healthy subjects underwent visual acuity (VA) evaluation, contrast sensitivity vision testing (CSV) with the Pelli Robson and CSV 1000E tests, and retinal thicknesses measurement [ganglion cell layer (GCL) and retinal nerve fiber layer (RNFL)] using Spectralis Optical Coherence Tomography (OCT). All subjects were re-evaluated after 5 years. The relationship between progressive structural changes and disease duration was analyzed. RESULTS: Visual function parameters in BD patients remained unchanged during the follow-up period. A progressive decrease affecting macular and peripapillary RNFL thickness (p < 0.050) was observed in patients. Progressive changes in BD were more pronounced when compared with healthy controls (p < 0.050). A significant correlation between GCL thickness changes and disease duration was found (GCL outer temporal, r = -0.680, p = 0.016; GCL central, r = -0.540, p = 0.038). CONCLUSIONS: Progressive axonal loss was detected in BD patients. Visual function parameters were not affected after the 5-year follow-up. Despite observed changes in the neuroretina of patients with BD, axonal degeneration in these patients seemed to be mild and might be slowed down by other factors, such as BD treatments.

Ganglion Cell and Retinal Nerve Fiver Layers Correlated with Time Disease of Bipolar Disorder Using 64 Cell Grid OCT Tool.

MATERIALS AND METHODS: Twenty-five eyes of 25 patients with bipolar disorder and 74 eyes of 74 healthy controls underwent retinal measurements of retinal nerve fiber layer (RNFL) and ganglion cell layer (GCL) thickness. Measurements were obtained using the Spectralis-OCT device with the new Posterior Pole protocol which assesses the macular area by analyzing retinal thickness in a grid of 64 (8*8) cells. RESULTS: Significant differences (p < 0.05) in RNFL and GCL thickness were found between BD patients and healthy controls, in parafoveal and perifoveal cells respectively. Significant inverse correlations were found between RNFL and GCL thinning at their thickest location and the duration of bipolar disorder. Several predictive variables were observed with a binary logistic regression for the presence/absence of BD: cell 1.3 RNFL (p = 0.028) and GCL in cells 7.8 (p = 0.012), 2.7 (p = 0.043) and 1.3 (p = 0.047). CONCLUSION: Posterior Pole OCT protocol is a useful tool to assess changes in the inner retinal layers in bipolar disorder. These observed changes, especially those affecting the GCL, may be associated with disease evolution and may be predictive of the presence of the disease. OCT data could potentially be a useful tool for clinicians to diagnose and monitor BD patients.

Angiography with optical coherence tomography as a biomarker in multiple sclerosis.

PURPOSE: To investigate superficial retinal microvascular plexuses detected by optical coherence tomography angiography (OCT-A) in multiple sclerosis (MS) subjects and compare them with healthy controls. METHODS: A total of 92 eyes from 92 patients with relapsing-remitting MS and 149 control eyes were included in this prospective observational study. OCT-A imaging was performed using Triton Swept-Source OCT (Topcon Corporation, Japan). The vessel density (VD) percentage in the superficial retinal plexus and optic disc area (6 x 6 mm grid) was measured and compared between groups. RESULTS: MS patients showed a significant decrease VD in the superior (p = 0.005), nasal (p = 0.029) and inferior (p = 0.040) parafoveal retina compared with healthy subjects. Patients with disease durations of more than 5 years presented lower VD in the superior (p = 0.002), nasal (p = 0.017) and inferior (p = 0.022) parafoveal areas compared with healthy subjects. Patients with past optic neuritis episodes did not show retinal microvasculature alterations, but patients with an EDSS score of less than 3 showed a significant decrease in nasal (p = 0.024) and superior (p = 0.006) perifoveal VD when compared with healthy subjects. CONCLUSIONS: MS produces a decrease in retinal vascularization density in the superficial plexus of the parafoveal retina. Alterations in retinal vascularization observed in MS patients are independent of the presence of optic nerve inflammation. OCT-A has the ability to detect subclinical vascular changes and is a potential biomarker for diagnosing the presence and progression of MS.

Empirical Mode Decomposition-Based Filter Applied to Multifocal Electroretinograms in Multiple Sclerosis Diagnosis.

As multiple sclerosis (MS) usually affects the visual pathway, visual electrophysiological tests can be used to diagnose it. The objective of this paper is to research methods for processing multifocal electroretinogram (mfERG) recordings to improve the capacity to diagnose MS. MfERG recordings from 15 early-stage MS patients without a history of optic neuritis and from 6 control subjects were examined. A normative database was built from the control subject signals. The mfERG recordings were filtered using empirical mode decomposition (EMD). The correlation with the signals in a normative database was used as the classification feature. Using EMD-based filtering and performance correlation, the mean area under the curve (AUC) value was 0.90. The greatest discriminant capacity was obtained in ring 4 and in the inferior nasal quadrant (AUC values of 0.96 and 0.94, respectively). Our results suggest that the combination of filtering mfERG recordings using EMD and calculating the correlation with a normative database would make mfERG waveform analysis applicable to assessment of multiple sclerosis in early-stage patients.