Applying the 2022 optic neuritis criteria to noninflammatory optic neuropathies with optic nerve T2-hyperintensity: an observational study.

INTRODUCTION: Recent diagnostic criteria for optic neuritis include T2-hyperintensity of the optic nerve (ON), even without associated contrast enhancement. However, isolated ON-T2-hyperintensity is a nonspecific finding found in any optic neuropathy or severe retinopathy. We applied the 2022 optic neuritis diagnostic criteria to a cohort of patients with noninflammatory optic neuropathy and ON-T2-hyperintensity in at least one eye, to assess the rate of optic neuritis misdiagnosis using these criteria. METHODS: Retrospective study of consecutive patients who underwent brain/orbit MRI with/without contrast between 07/01/2019 and 06/30/2022. Patients with ON-T2-hyperintensity in at least one eye were included. The 2022 optic neuritis diagnostic criteria were applied to patients with noninflammatory optic neuropathies who had an ophthalmologic examination available for review. RESULTS: Of 150 patients included, 85/150 had compressive optic neuropathy; 32/150 had glaucoma; 12/150 had papilledema; 8/150 had hereditary (3), radiation-induced (3), nutritional (1), traumatic (1) optic neuropathies (none fulfilled the criteria); 13/150 had ischemic optic neuropathy and 4 fulfilled the criteria as definite optic neuritis due to contrast enhancement of the ON head. Seven additional patients would have satisfied the diagnostic criteria if red flags for alternative diagnoses had been overlooked. DISCUSSION: The application of the 2022 optic neuritis diagnostic criteria in patients with noninflammatory optic neuropathy and ON-T2-hyperintensity in at least one ON resulted in misdiagnosis of optic neuritis in only 4 patients because of ON head enhancement, all with nonarteritic anterior ischemic optic neuropathy. Neuro-ophthalmologic evaluation and exclusion of the ON head as a location in the MRI criteria would have prevented optic neuritis misdiagnosis in our study.

The Increasing Burden of Emergency Department and Inpatient Consultations for "Papilledema".

BACKGROUND: Increasing incidence of idiopathic intracranial hypertension (IIH), overreported radiologic signs of intracranial hypertension, difficult access to outpatient neuro-ophthalmology services, poor insurance coverage, and medicolegal concerns have lowered the threshold for emergency department (ED) visits for "papilledema." Our objective was to examine referral patterns and outcomes of neuro-ophthalmology ED and inpatient consultations for concern for papilledema. METHODS: At one university-based quaternary care center, all adults referred for "papilledema" over one year underwent a standardized ED "papilledema protocol." We collected patient demographics, final diagnoses, and referral patterns. RESULTS: Over 1 year, 153 consecutive patients were referred for concern for papilledema. After papilledema protocol, 89 of 153 patients (58%) had bilateral optic disc edema, among whom 89% (79/89) had papilledema (intracranial hypertension). Of the 38 of 153 (25%) consultations for suspected disorder of intracranial pressure without previous fundus examination (Group 1), 74% (28/38) did not have optic disc edema, 21% (8/38) had papilledema, and 5% (2/38) had other causes of bilateral disc edema. Of the 89 of 153 (58%) consultations for presumed papilledema seen on fundus examination (Group 2), 58% (66/89) had confirmed papilledema, 17% (15/89) had pseudopapilledema, and 9% (8/89) had other causes of bilateral optic disc edema. Of the 26 of 153 (17%) patients with known IIH (Group 3), 5 had papilledema and 4 required urgent intervention. The most common diagnosis was IIH (58/79). Compared with IIH, patients with secondary causes of intracranial hypertension were older (P = 0.002), men (P < 0.001), not obese (P < 0.001), and more likely to have neurologic symptoms (P = 0.002). CONCLUSION: Inpatient and ED consultations for "papilledema" are increasing. Of the 153 ED and inpatient neuro-ophthalmology consultations seen for "papilledema" over 1 year, one-third of patients with optic disc edema of unknown cause before presentation to our ED had new vision- or life-threatening disease, supporting the need for prompt identification and evaluation of optic disc edema in the ED. In the face of limited access to neuro-ophthalmologists, this study supports the need for emergency department access to expert eye-care evaluation or ocular fundus camera for prompt identification of optic disc edema and standardized evaluation for neurologic emergencies.

Therapeutic benefit of idebenone in patients with Leber hereditary optic neuropathy: The LEROS nonrandomized controlled trial.

Leber hereditary optic neuropathy (LHON) is a mitochondrial disease leading to rapid and severe bilateral vision loss. Idebenone has been shown to be effective in stabilizing and restoring vision in patients treated within 1 year of onset of vision loss. The open-label, international, multicenter, natural history-controlled LEROS study (ClinicalTrials.gov NCT02774005) assesses the efficacy and safety of idebenone treatment (900 mg/day) in patients with LHON up to 5 years after symptom onset (N = 199) and over a treatment period of 24 months, compared to an external natural history control cohort (N = 372), matched by time since symptom onset. LEROS meets its primary endpoint and confirms the long-term efficacy of idebenone in the subacute/dynamic and chronic phases; the treatment effect varies depending on disease phase and the causative mtDNA mutation. The findings of the LEROS study will help guide the clinical management of patients with LHON.

Glaucoma as a cause of optic nerve abnormalities on magnetic resonance imaging.

BACKGROUND/OBJECTIVES: To report a series of patients with glaucoma and optic nerve abnormalities on magnetic resonance imaging (MRI) in at least one-eye, and to determine whether these findings correlate with the severity of glaucoma. PATIENTS AND METHODS: Retrospective study of all patients who underwent a brain/orbits MRI without and with contrast at our institution between 07/1/2019-6/30/2022. Patients with optic nerve T2-hyperintensity and/or MRI optic nerve atrophy in at least one-eye and a diagnosis of isolated glaucoma in at least one-eye were included. Demographic information, glaucoma clinical characteristics, glaucoma severity parameters, and MRI indication were collected. RESULTS: Fifty-six patients (112 eyes) (age 65 years-old [range 26-88]; 70% male) had isolated bilateral glaucoma with at least one-eye MRI optic nerve abnormality. The indication for MRI was atypical/asymmetric glaucoma in 91% of patients. Of the 112 eyes, 23 had optic nerve T2-hyperintensity alone; 33 had both optic nerve T2-hyperintensity and MRI optic nerve atrophy; 34 had MRI optic nerve atrophy alone; and 22 did not have abnormal optic nerve MRI-findings. None had optic nerve enhancement. A statistically significant association between optic nerve T2-hyperintensity or MRI optic nerve atrophy and glaucoma severity parameters was found. CONCLUSIONS: Glaucoma is a clinical diagnosis and MRI brain is usually not required, except in atypical or asymmetric cases. Optic nerve T2-hyperintensity and MRI optic nerve atrophy are nonspecific MRI-findings that can be found in severe glaucomatous optic nerves and should not systematically prompt investigations for another cause of optic neuropathy.

Optic Nerve MRI T2-Hyperintensity: A Nonspecific Marker of Optic Nerve Damage.

BACKGROUND: MRI abnormalities are common in optic neuropathies, especially on dedicated orbital imaging. In acute optic neuritis, optic nerve T2-hyperintensity associated with optic nerve contrast enhancement is the typical imaging finding. In chronic optic neuropathies, optic nerve T2-hyperintensity and atrophy are regularly seen. Isolated optic nerve T2-hyperintensity is often erroneously presumed to reflect optic neuritis, frequently prompting unnecessary investigations and neuro-ophthalmology consultations. Our goal was to determine the significance of optic nerve/chiasm T2-hyperintensity and/or atrophy on MRI. METHODS: Retrospective study of consecutive patients who underwent brain/orbital MRI with/without contrast at our institution between July 1, 2019, and June 6, 2022. Patients with optic nerve/chiasm T2-hyperintensity and/or atrophy were included. Medical records were reviewed to determine the etiology of the T2-hyperintensity and/or atrophy. RESULTS: Four hundred seventy-seven patients (698 eyes) were included [mean age 52 years (SD ±18 years); 57% women]. Of the 364 of 698 eyes with optic nerve/chiasm T2-hyperintensity without atrophy, the causes were compressive (104), inflammatory (103), multifactorial (49), glaucoma (21), normal (19), and other (68); of the 219 of 698 eyes with optic nerve/chiasm T2-hyperintensity and atrophy, the causes were compressive (57), multifactorial (40), inflammatory (38), glaucoma (33), normal (7), and other (44); of the 115 of 698 eyes with optic nerve/chiasm atrophy without T2-hyperintensity, the causes were glaucoma (34), multifactorial (21), inflammatory (13), compressive (11), normal (10), and other (26). Thirty-six eyes with optic nerve/chiasm T2-hyperintensity or atrophy did not have evidence of optic neuropathy or retinopathy on ophthalmologic examination, and 17 eyes had clinical evidence of severe retinopathy without primary optic neuropathy. CONCLUSIONS: Optic nerve T2-hyperintensity or atrophy can be found with any cause of optic neuropathy and with severe chronic retinopathy. These MRI findings should not automatically prompt optic neuritis diagnosis, workup, and treatment, and caution is advised regarding their use in the diagnostic criteria for multiple sclerosis. Cases of incidentally found MRI optic nerve T2-hyperintensity and/or atrophy without a known underlying optic neuropathy or severe retinopathy are rare. Such patients should receive an ophthalmologic examination before further investigations.

The BONSAI (Brain and Optic Nerve Study with Artificial Intelligence) deep learning system can accurately identify pediatric papilledema on standard ocular fundus photographs.

BACKGROUND: Pediatric papilledema often reflects an underlying severe neurologic disorder and may be difficult to appreciate, especially in young children. Ocular fundus photographs are easy to obtain even in young children and in nonophthalmology settings. The aim of our study was to ascertain whether an improved deep-learning system (DLS), previously validated in adults, can accurately identify papilledema and other optic disk abnormalities in children. METHODS: The DLS was tested on mydriatic fundus photographs obtained in a multiethnic pediatric population (<17 years) from three centers (Atlanta-USA; Bucharest-Romania; Singapore). The DLS's multiclass classification accuracy (ie, normal optic disk, papilledema, disks with other abnormality) was calculated, and the DLS's performance to specifically detect papilledema and normal disks was evaluated in a one-vs-rest strategy using the AUC, sensitivity and specificity, with reference to expert neuro-ophthalmologists. RESULTS: External testing was performed on 898 fundus photographs: 447 patients; mean age, 10.33 (231 patients ≤10 years of age; 216, 11-16 years); 558 normal disks, 254 papilledema, 86 other disk abnormalities. Overall multiclass accuracy of the DLS was 89.6% (range, 87.8%-91.6%). The DLS successfully distinguished "normal" from "abnormal" optic disks (AUC 0.99 [0.98-0.99]; sensitivity, 87.3% [84.9%-89.8%]; specificity, 98.5% [97.6%-99.6%]), and "papilledema" from "normal and other" (AUC 0.99 [0.98-1.0]; sensitivity, 98.0% [96.8%-99.4%]; specificity, 94.1% (92.4%-95.9%)]. CONCLUSIONS: Our DLS reliably distinguished papilledema from normal optic disks and other disk abnormalities in children, suggesting it could be utilized as a diagnostic aid for the assessment of optic nerve head appearance in the pediatric age group.

Characteristics of Vitamin A Deficiency Retinopathy at a Tertiary Referral Center in the United States.

PURPOSE: To explore the risk factors and fundus imaging features of vitamin A deficiency retinopathy (VADR) in an academic tertiary referral center in Atlanta, GA, United States, and to propose guidance regarding diagnostic workup and management of affected patients. DESIGN: Single-center retrospective case series. SUBJECTS: Nine patients seen between 2015 and 2021 at the Emory Eye Center diagnosed with VADR. METHODS: Retrospective chart review. MAIN OUTCOME MEASURES: Baseline serum retinol level, Snellen visual acuity, multimodal fundus imaging findings, and electroretinography findings. RESULTS: Nine patients, 4 (44.4%) female, with a median (range) age of 68 (50-75) years were identified. The most common underlying etiologies for vitamin A deficiency included history of gastrointestinal surgery (55.6%), liver disease (44.4%), and nutritional depletion due to low-quality diet (44.4%). Only 1 (11.1%) patient had a history of bariatric surgery. Four (44.4%) patients were on some form of vitamin A supplementation before the diagnosis of VADR. Median (range) serum retinol level was 0.06 (< 0.06-0.19) mg/L. All patients had macular subretinal hyperreflective deposits resembling subretinal drusenoid deposits, although in some cases, these were scant and sparsely distributed. Six eyes of 3 patients with longstanding deficiency had defects in the external limiting membrane (ELM). Three of these eyes additionally had macular areas of complete retinal pigment epithelium and outer retinal atrophy (cRORA). Full-field electroretinography demonstrated severe rod dysfunction and mild to moderate cone system dysfunction. Many findings of VADR were reversible with vitamin A repletion. However, all eyes with ELM defects or cRORA had persistence or continued growth of these lesions. CONCLUSION: Vitamin A deficiency retinopathy is uncommon in the developed world. However, given that early intervention can lead to dramatic visual improvement and avoid potentially permanent retinal damage, retina specialists should be familiar with its clinical presentation. The presence of nyctalopia and subretinal hyperreflective deposits in a patient with a history of gastrointestinal surgery, liver disease, and/or poor diet can be suggestive of this diagnosis, even in the presence of ongoing vitamin A supplementation. Vitamin A supplementation can vary in route and dosage and can be tailored to the individual with serial testing of serum retinol. FINANCIAL DISCLOSURE(S): The authors have no proprietary or commercial interest in any materials discussed in this article.

Application of a Deep Learning System to Detect Papilledema on Nonmydriatic Ocular Fundus Photographs in an Emergency Department.

PURPOSE: The Fundus photography vs Ophthalmoscopy Trial Outcomes in the Emergency Department (FOTO-ED) studies showed that ED providers poorly recognized funduscopic findings in patients in the ED. We tested a modified version of the Brain and Optic Nerve Study Artificial Intelligence (BONSAI) deep learning system on nonmydriatic fundus photographs from the FOTO-ED studies to determine if the deep learning system could have improved the detection of papilledema had it been available to ED providers as a real-time diagnostic aid. DESIGN: Retrospective secondary analysis of a cohort of patients included in the FOTO-ED studies. METHODS: The testing data set included 1608 photographs obtained from 828 patients in the FOTO-ED studies. Photographs were reclassified according to the optic disc classification system used by the deep learning system ("normal optic discs," "papilledema," and "other optic disc abnormalities"). The system's performance was evaluated by calculating the area under the receiver operating characteristic curve (AUC), sensitivity, and specificity using a 1-vs-rest strategy, with reference to expert neuro-ophthalmologists. RESULTS: The BONSAI deep learning system successfully distinguished normal from abnormal optic discs (AUC 0.92 [95% confidence interval {CI} 0.90-0.93]; sensitivity 75.6% [73.7%-77.5%] and specificity 89.6% [86.3%-92.8%]), and papilledema from normal and others (AUC 0.97 [0.95-0.99]; sensitivity 84.0% [75.0%-92.6%] and specificity 98.9% [98.5%-99.4%]). Six patients with missed papilledema in 1 eye were correctly identified by the deep learning system as having papilledema in the other eye. CONCLUSIONS: The BONSAI deep learning system was able to reliably identify papilledema and normal optic discs on nonmydriatic photographs obtained in the FOTO-ED studies. Our deep learning system has excellent potential as a diagnostic aid in EDs and non-ophthalmology clinics equipped with nonmydriatic fundus cameras. NOTE: Publication of this article is sponsored by the American Ophthalmological Society.

Seizures as the Initial Manifestation of Idiopathic Intracranial Hypertension Spectrum Disorder.

Idiopathic intracranial hypertension (IIH) is a syndrome of isolated elevated intracranial pressure of unknown aetiology. The IIH spectrum has evolved over the past decade making the diagnosis and management more challenging. The neurological examination in IIH is typically normal except for papilloedema and possible cranial nerve 6 palsy. Recent publications have highlighted skull base thinning and remodelling in patients with chronic IIH. Resulting skull base defects can cause meningo-encephalocoeles, which are potential epileptogenic foci. We describe the clinical and radiological characteristics of five IIH patients with seizures and meningo-encephalocoeles as the presenting manifestations of IIH spectrum disorder.

Optometric Practice Patterns for Acute Central and Branch Retinal Artery Occlusion.

BACKGROUND: Optometrists are often the first providers to evaluate patients with acute vision loss and are often the first to diagnose a central retinal artery occlusion (CRAO). How quickly these patients present to the optometrist, are diagnosed, and referred for evaluation are major factors influencing the possibility of acute therapeutic intervention. Our aim was to survey the U.S. optometric community to determine current optometric practice patterns for management of CRAO. METHODS: An anonymous seven-question survey was emailed in 2020 to the 5,101 members of the American Academy of Optometry and the 26,502 members of the American Optometric Association. RESULTS: Of 31,603 optometrists who were sent the survey, 1,926 responded (6.1%). Most respondents (1,392/1,919, 72.5%) worked in an optometry-predominant outpatient clinic and were less than 30 minutes from a certified stroke center (1,481/1,923, 77.0%). Ninety-eight percent (1,884/1,922) of respondents had diagnosed less than 5 CRAOs in the previous year, and 1,000/1,922 (52.0%) had not diagnosed a CRAO in the prior year. Of the optometrists who diagnosed at least one CRAO in the previous year, 661/922 (71.7%) evaluated these patients more than 4 hours after the onset of vision loss. Optometrists who diagnosed a CRAO or branch retinal artery occlusion referred patients to an emergency department (ED) affiliated with a certified stroke center (844/1,917, 44.0%), an outpatient ophthalmology clinic (764/1,917, 39.9%), an ED without a stroke center (250/1,917, 13.0%), an outpatient neurology clinic (20/1,917, 1.0%), or other (39/1,917, 2.0%); most (22/39, 56.4%) who responded "other" would refer to a primary care physician. CONCLUSIONS: Optometrists are likely the first providers to evaluate patients with acute vision loss, including from a retinal artery occlusion. However, only 6.1% of optometrists responded to our survey despite 2 reminder emails, likely reflecting the lack of exposure to acute retinal artery occlusions, and a potential lack of interest of optometrists in participating in research. Of the optometrists who reported evaluating a CRAO in the previous year, less than 29% saw the patient within 4 hours of vision loss. In addition, a large portion of optometrists are referring acute CRAO patients to outpatient ophthalmology clinics, delaying appropriate acute management. Therefore, it is imperative that optometrists and ophthalmologists are educated to view acute retinal arterial ischemia as an acute stroke and urgently refer these patients to an ED affiliated with a stroke center. The delay in patient presentation and these referral patterns make future clinical trials for acute CRAO challenging.

Neuro-ophthalmology Emergency Department and Inpatient Consultations at a Large Academic Referral Center.

PURPOSE: Prompt neuro-ophthalmology consultation prevents diagnostic errors and improves patient outcomes. The scarcity of neuro-ophthalmologists means that the increasing outpatient demand cannot be met, prompting many emergency department (ED) referrals by non-neuro-ophthalmologists. We describe our quaternary care institution's ED and inpatient neuro-ophthalmology consultation patterns and patient outcomes. DESIGN: Prospective observational study. PARTICIPANTS: Consecutive neuro-ophthalmology ED and inpatient consultation requests over 1 year. METHODS: We collected patient demographics, distance traveled, insurance status, referring provider details, consultation question, final diagnosis, complexity of consultation, time of consultation, and need for outpatient follow-up. MAIN OUTCOME MEASURES: Consultation patterns and diagnoses, complexity, and follow-up. RESULTS: Of 494 consecutive adult ED and inpatient neuro-ophthalmology consultations requested over 1 year, 241 of 494 consultations (49%) occurred at night or during weekends. Of ED consultations (322 of 494 [65%]), 127 of 322 consultations (39%) occurred during weekdays, 126 of 322 consultations (39%) occurred on weeknights, and 69 of 322 consultations (22%) occurred on weekends or holidays. Of 322 ED consultations, 225 of 322 consultations (70%) were patients who initially sought treatment in the ED with a neuro-ophthalmic chief symptom. Of the 196 patients sent to the ED by a health care professional, 148 patients (148/196 [76%]) were referred by eye care specialists (74 optometrists and 74 ophthalmologists). The most common ED referral questions were for papilledema (75 of 322 [23%]) and vision loss (72 of 322 [22%]). A total of 219 of 322 patients (68%) received a final active neuro-ophthalmic diagnosis, 222 of 322 patients (69%) were cases of high or very high complexity, and 143 of 322 patients (44%) required admission. Inpatient consultations (n = 172) were requested most frequently by hospitalists, including neurologists (71 of 172 [41%]) and oncologists (20 of 172 [12%]) for vision loss (43 of 172 [25%]) and eye movement disorders (36 of 172 [21%]) and by neurosurgeons (58 of 172 [33%]) for examination for mass or a preoperative evaluation (19 of 172 [11%]). An active neuro-ophthalmic diagnosis was confirmed in 67% of patients (116 of 172). Outpatient neuro-ophthalmology follow-up was required for 291 of 494 patients (59%). CONCLUSIONS: Neuro-ophthalmology consultations are critical to the diagnosis and management in the hospital setting. In the face of a critical shortage of neuro-ophthalmologists, this study highlights the need for technological and diagnostic aids for greater outpatient access. FINANCIAL DISCLOSURE(S): Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Diagnosis of Optic Disc Oedema: Fundus Features, Ocular Imaging Findings, and Artificial Intelligence.

Optic disc swelling is a manifestation of a broad range of processes affecting the optic nerve head and/or the anterior segment of the optic nerve. Accurately diagnosing optic disc oedema, grading its severity, and recognising its cause, is crucial in order to treat patients in a timely manner and limit vision loss. Some ocular fundus features, in light of a patient's history and visual symptoms, may suggest a specific mechanism or aetiology of the visible disc oedema, but current criteria can at most enable an educated guess as to the most likely cause. In many cases only the clinical evolution and ancillary testing can inform the exact diagnosis. The development of ocular fundus imaging, including colour fundus photography, fluorescein angiography, optical coherence tomography, and multimodal imaging, has provided assistance in quantifying swelling, distinguishing true optic disc oedema from pseudo-optic disc oedema, and differentiating among the numerous causes of acute optic disc oedema. However, the diagnosis of disc oedema is often delayed or not made in busy emergency departments and outpatient neurology clinics. Indeed, most non-eye care providers are not able to accurately perform ocular fundus examination, increasing the risk of diagnostic errors in acute neurological settings. The implementation of non-mydriatic fundus photography and artificial intelligence technology in the diagnostic process addresses these important gaps in clinical practice.

Carotid-Cavernous Fistula Presenting as Isolated Painful Anisocoria.

A painful isolated third nerve palsy is an uncommon presenting sign of a carotid-cavernous fistula (CCF). It mostly occurs in dural CCFs with posterior drainage into the petrosal sinuses. We present a case of a 50-year-old woman who developed acute right periorbital facial pain in the territory of the first branch of the right trigeminal nerve and was noted to have a right dilated unreactive pupil with very subtle right ptosis. She was subsequently diagnosed with a posteriorly draining dural CCF.

Race Distribution in Nonarteritic Anterior Ischemic Optic Neuropathy.

PURPOSE: To describe the racial distribution of patients diagnosed with nonarteritic anterior ischemic optic neuropathy (NAION) in 2 large urban academic centers in the United States. DESIGN: Retrospective cross-sectional study. METHODS: All patients with NAION evaluated between 2014 and 2022 in tertiary neuro-ophthalmology services in Atlanta, GA, and New York, NY, respectively, were included. In order to assess the racial accessibility to our services, similar numbers of patients with idiopathic intracranial hypertension seen in the same services were included. Self-reported race at the time of neuro-ophthalmologic examination was collected for all patients. Results were compared with data published by the US Bureau of Census for Decennial Census in 2020 for the states of Georgia and New York, and for the total population of the United States. RESULTS: In both locations, the vast majority of patients with NAION reported being White (91.06% in Atlanta and 78.9% in New York). Only 7.27% of patients in Atlanta and 3% in New York reported being Black, and 1.24% of patients in Atlanta and 5.9% in New York reported being Asian. There were a much higher proportion of White people among NAION patients than in the group of patients with idiopathic intracranial hypertension and in each respective state and in the United States. CONCLUSIONS: Our results show that the majority of patients with NAION are White, followed by Black and Asian races, respectively, thus confirming the NAION race distribution reported by past clinical trials.

A Deep Learning System for Automated Quality Evaluation of Optic Disc Photographs in Neuro-Ophthalmic Disorders.

The quality of ocular fundus photographs can affect the accuracy of the morphologic assessment of the optic nerve head (ONH), either by humans or by deep learning systems (DLS). In order to automatically identify ONH photographs of optimal quality, we have developed, trained, and tested a DLS, using an international, multicentre, multi-ethnic dataset of 5015 ocular fundus photographs from 31 centres in 20 countries participating to the Brain and Optic Nerve Study with Artificial Intelligence (BONSAI). The reference standard in image quality was established by three experts who independently classified photographs as of "good", "borderline", or "poor" quality. The DLS was trained on 4208 fundus photographs and tested on an independent external dataset of 807 photographs, using a multi-class model, evaluated with a one-vs-rest classification strategy. In the external-testing dataset, the DLS could identify with excellent performance "good" quality photographs (AUC = 0.93 (95% CI, 0.91-0.95), accuracy = 91.4% (95% CI, 90.0-92.9%), sensitivity = 93.8% (95% CI, 92.5-95.2%), specificity = 75.9% (95% CI, 69.7-82.1%) and "poor" quality photographs (AUC = 1.00 (95% CI, 0.99-1.00), accuracy = 99.1% (95% CI, 98.6-99.6%), sensitivity = 81.5% (95% CI, 70.6-93.8%), specificity = 99.7% (95% CI, 99.6-100.0%). "Borderline" quality images were also accurately classified (AUC = 0.90 (95% CI, 0.88-0.93), accuracy = 90.6% (95% CI, 89.1-92.2%), sensitivity = 65.4% (95% CI, 56.6-72.9%), specificity = 93.4% (95% CI, 92.1-94.8%). The overall accuracy to distinguish among the three classes was 90.6% (95% CI, 89.1-92.1%), suggesting that this DLS could select optimal quality fundus photographs in patients with neuro-ophthalmic and neurological disorders affecting the ONH.