RESUMEN
BACKGROUND: Neuro-ophthalmology frequently requires a complex and multi-faceted clinical assessment supported by sophisticated imaging techniques in order to assess disease status. The current approach to diagnosis requires substantial expertise and time. The emergence of AI has brought forth innovative solutions to streamline and enhance this diagnostic process, which is especially valuable given the shortage of neuro-ophthalmologists. Machine learning algorithms, in particular, have demonstrated significant potential in interpreting imaging data, identifying subtle patterns, and aiding clinicians in making more accurate and timely diagnosis while also supplementing nonspecialist evaluations of neuro-ophthalmic disease. EVIDENCE ACQUISITION: Electronic searches of published literature were conducted using PubMed and Google Scholar. A comprehensive search of the following terms was conducted within the Journal of Neuro-Ophthalmology: AI, artificial intelligence, machine learning, deep learning, natural language processing, computer vision, large language models, and generative AI. RESULTS: This review aims to provide a comprehensive overview of the evolving landscape of AI applications in neuro-ophthalmology. It will delve into the diverse applications of AI, optical coherence tomography (OCT), and fundus photography to the development of predictive models for disease progression. Additionally, the review will explore the integration of generative AI into neuro-ophthalmic education and clinical practice. CONCLUSIONS: We review the current state of AI in neuro-ophthalmology and its potentially transformative impact. The inclusion of AI in neuro-ophthalmic practice and research not only holds promise for improving diagnostic accuracy but also opens avenues for novel therapeutic interventions. We emphasize its potential to improve access to scarce subspecialty resources while examining the current challenges associated with the integration of AI into clinical practice and research.
RESUMEN
INTRODUCTION: Optical coherence tomography (OCT)-derived peripapillary retinal nerve fiber layer (pRNFL) and ganglion cell+inner plexiform layer (GCIPL) thickness inter-eye differences (IEDs) are robust measurements for identifying clinical history acute ON in people with MS (PwMS). This study investigated the utility and durability of these measures as longitudinal markers to identify optic nerve lesions. METHODS: Prospective, multi-center international study of PwMS (with/without clinical history of ON) and healthy controls. Data from two sites in the International MS Visual System Consortium (IMSVISUAL) were analyzed. Mixed-effects models were used to compare inter-eye differences based on MS and acute ON history. RESULTS: Average age of those with MS (n = 210) was 39.1 ± 10.8 and 190 (91%) were relapsing-remitting. Fifty-nine (28.1%) had a history of acute unilateral ON, while 9/210 (4.3%) had >1 IB episode. Median follow-up between OCT scans was 9 months. By mixed-effects modeling, IEDs were stable between first and last visits within groups for GCIPL for controls (p = 0.18), all PwMS (p = 0.74), PwMs without ON (p = 0.22), and PwMS with ON (p = 0.48). For pRNFL, IEDs were within controls (p = 0.10), all PwMS (p = 0.53), PwMS without ON history (p = 0.98), and PwMS with history of ON (p = 0.81). CONCLUSION: We demonstrated longitudinal stability of pRNFL and GCIPL IEDs as markers for optic nerve lesions in PwMS, thus reinforcing the role for OCT in demonstrating optic nerve lesions.
Asunto(s)
Esclerosis Múltiple , Enfermedades del Nervio Óptico , Tomografía de Coherencia Óptica , Enfermedades del Nervio Óptico/diagnóstico por imagen , Enfermedades del Nervio Óptico/etnología , Esclerosis Múltiple/complicaciones , Esclerosis Múltiple/diagnóstico por imagen , Humanos , Masculino , Femenino , Adulto Joven , Adulto , Persona de Mediana EdadRESUMEN
BACKGROUND: The diagnosis of multiple sclerosis (MS) requires demyelinating events that are disseminated in time and space. Peripapillary retinal nerve fiber layer (pRNFL) thickness as measured by optical coherence tomography (OCT) distinguishes eyes with a prior history of acute optic neuritis (ON) and may provide evidence to support a demyelinating attack. OBJECTIVE: To investigate whether a deep learning (DL)-based network can distinguish between eyes with prior ON and healthy control (HC) eyes using peripapillary ring scans. METHODS: We included 1033 OCT scans from 415 healthy eyes (213 HC subjects) and 510 peripapillary ring scans from 164 eyes with prior acute ON (140 patients with MS). Data were split into 70% training, 15% validation, and 15% test data. We included 102 OCT scans from 80 healthy eyes (40 HC) and 61 scans from 40 ON eyes (31 MS patients) from an independent second center. Receiver operating characteristic curve analyses with area under the curve (AUC) were used to investigate performance. RESULTS: We used a dilated residual convolutional neural network for the classification. The final network had an accuracy of 0.85 and an AUC of 0.86, whereas pRNFL only had an AUC of 0.77 in recognizing ON eyes. Using data from a second center, the network achieved an accuracy of 0.77 and an AUC of 0.90 compared to pRNFL, which had an AUC of 0.84. INTERPRETATION: DL-based disease classification of prior ON is feasible and has the potential to outperform thickness-based classification of eyes with and without history of prior ON.
Asunto(s)
Aprendizaje Profundo , Esclerosis Múltiple , Neuritis Óptica , Humanos , Neuritis Óptica/diagnóstico por imagen , Tomografía de Coherencia Óptica/métodos , Retina , Esclerosis Múltiple/diagnóstico por imagenRESUMEN
BACKGROUND AND OBJECTIVES: Recent studies have suggested that intereye differences (IEDs) in peripapillary retinal nerve fiber layer (pRNFL) or ganglion cell + inner plexiform (GCIPL) thickness by spectral domain optical coherence tomography (SD-OCT) may identify people with a history of unilateral optic neuritis (ON). However, this requires further validation. Machine learning classification may be useful for validating thresholds for OCT IEDs and for examining added utility for visual function tests, such as low-contrast letter acuity (LCLA), in the diagnosis of people with multiple sclerosis (PwMS) and for unilateral ON history. METHODS: Participants were from 11 sites within the International Multiple Sclerosis Visual System consortium. pRNFL and GCIPL thicknesses were measured using SD-OCT. A composite score combining OCT and visual measures was compared individual measurements to determine the best model to distinguish PwMS from controls. These methods were also used to distinguish those with a history of ON among PwMS. Receiver operating characteristic (ROC) curve analysis was performed on a training data set (2/3 of cohort) and then applied to a testing data set (1/3 of cohort). Support vector machine (SVM) analysis was used to assess whether machine learning models improved diagnostic capability of OCT. RESULTS: Among 1,568 PwMS and 552 controls, variable selection models identified GCIPL IED, average GCIPL thickness (both eyes), and binocular 2.5% LCLA as most important for classifying PwMS vs controls. This composite score performed best, with area under the curve (AUC) = 0.89 (95% CI 0.85-0.93), sensitivity = 81%, and specificity = 80%. The composite score ROC curve performed better than any of the individual measures from the model (p < 0.0001). GCIPL IED remained the best single discriminator of unilateral ON history among PwMS (AUC = 0.77, 95% CI 0.71-0.83, sensitivity = 68%, specificity = 77%). SVM analysis performed comparably with standard logistic regression models. DISCUSSION: A composite score combining visual structure and function improved the capacity of SD-OCT to distinguish PwMS from controls. GCIPL IED best distinguished those with a history of unilateral ON. SVM performed as well as standard statistical models for these classifications. CLASSIFICATION OF EVIDENCE: This study provides Class III evidence that SD-OCT accurately distinguishes multiple sclerosis from normal controls as compared with clinical criteria.
Asunto(s)
Esclerosis Múltiple , Neuritis Óptica , Humanos , Aprendizaje Automático , Esclerosis Múltiple/diagnóstico , Fibras Nerviosas , Neuritis Óptica/diagnóstico , Células Ganglionares de la Retina , Tomografía de Coherencia Óptica/métodosRESUMEN
OBJECTIVE: To determine the optimal thresholds for intereye differences in retinal nerve fiber and ganglion cell + inner plexiform layer thicknesses for identifying unilateral optic nerve lesions in multiple sclerosis. Current international diagnostic criteria for multiple sclerosis do not include the optic nerve as a lesion site despite frequent involvement. Optical coherence tomography detects retinal thinning associated with optic nerve lesions. METHODS: In this multicenter international study at 11 sites, optical coherence tomography was measured for patients and healthy controls as part of the International Multiple Sclerosis Visual System Consortium. High- and low-contrast acuity were also collected in a subset of participants. Presence of an optic nerve lesion for this study was defined as history of acute unilateral optic neuritis. RESULTS: Among patients (n = 1,530), receiver operating characteristic curve analysis demonstrated an optimal peripapillary retinal nerve fiber layer intereye difference threshold of 5µm and ganglion cell + inner plexiform layer threshold of 4µm for identifying unilateral optic neuritis (n = 477). Greater intereye differences in acuities were associated with greater intereye retinal layer thickness differences (p ≤ 0.001). INTERPRETATION: Intereye differences of 5µm for retinal nerve fiber layer and 4µm for macular ganglion cell + inner plexiform layer are robust thresholds for identifying unilateral optic nerve lesions. These thresholds may be useful in establishing the presence of asymptomatic and symptomatic optic nerve lesions in multiple sclerosis and could be useful in a new version of the diagnostic criteria. Our findings lend further validation for utilizing the visual system in a multiple sclerosis clinical trial setting. Ann Neurol 2019;85:618-629.