Diagnosing Optic Disc Drusen in the Modern Imaging Era: A Practical Approach

A Deep Learning Approach for Accurate Discrimination Between Optic Disc Drusen and Papilledema on Fundus Photographs

BACKGROUND

Optic disc drusen (ODD) represent an important differential diagnosis of papilledema caused by intracranial hypertension, but their distinction may be difficult in clinical practice. The aim of this study was to train, validate, and test a dedicated deep learning system (DLS) for binary classification of ODD vs papilledema (including various subgroups within each category), on conventional mydriatic digital ocular fundus photographs collected in a large international multiethnic population.

METHODS

This retrospective study included 4,508 color fundus images in 2,180 patients from 30 neuro-ophthalmology centers (19 countries) participating in the Brain and Optic Nerve Study with Artificial Intelligence (BONSAI) Group. For training and internal validation, we used 857 ODD images and 3,230 papilledema images, in 1,959 patients. External testing was performed on an independent data set (221 patients), including 207 images with ODD (96 visible and 111 buried), provided by 3 centers of the Optic Disc Drusen Studies Consortium, and 214 images of papilledema (92 mild-to-moderate and 122 severe) from a previously validated study.

RESULTS

The DLS could accurately distinguish between all ODD and papilledema (all severities included): area under the receiver operating characteristic curve (AUC) 0.97 (95% confidence interval [CI], 0.96-0.98), accuracy 90.5% (95% CI, 88.0%-92.9%), sensitivity 86.0% (95% CI, 82.1%-90.1%), and specificity 94.9% (95% CI, 92.3%-97.6%). The performance of the DLS remained high for discrimination of buried ODD from mild-to-moderate papilledema: AUC 0.93 (95% CI, 0.90-0.96), accuracy 84.2% (95% CI, 80.2%-88.6%), sensitivity 78.4% (95% CI, 72.2%-84.7%), and specificity 91.3% (95% CI, 87.0%-96.4%).

CONCLUSIONS

A dedicated DLS can accurately distinguish between ODD and papilledema caused by intracranial hypertension, even when considering buried ODD vs mild-to-moderate papilledema.

Imaging the optic nerve with optical coherence tomography

Optical coherence tomography (OCT) is a non-invasive imaging technology, which may be used to generate in vivo quantitative and qualitative measures of retinal structure. In terms of quantitative metrics, peripapillary retinal nerve fiber layer (pRNFL) thickness provides an indirect evaluation of axonal integrity within the optic nerve. Ganglion layer measures derived from macular scans indirectly reflect retinal ganglion cell status. Notably, ganglion layer indices are platform dependent and may include macular ganglion cell inner plexiform layer (mGCIPL), ganglion cell layer (GCL), and ganglion cell complex (GCC) analyses of thickness or volume. Interpreted together, pRNFL thickness and ganglion layer values can be used to diagnose optic neuropathies, monitor disease progression, and gauge response to therapeutic interventions for neuro-ophthalmic conditions. Qualitative assessments of the optic nerve head, using cross-sectional transverse axial, en face, and circular OCT imaging, may help distinguish papilledema from pseudopapilloedema, and identify outer retinal pathology. Innovations in OCT protocols and approaches including enhanced depth imaging (EDI), swept source (SS) techniques, and angiography (OCTA) may offer future insights regarding the potential pathogenesis of different optic neuropathies. Finally, recent developments in artificial intelligence (AI) utilizing OCT images may overcome longstanding challenges, which have plagued non-vision specialists who often struggle to perform reliable ophthalmoscopy. In this review, we aim to discuss the benefits and pitfalls of OCT, consider the practical applications of this technology in the assessment of optic neuropathies, and highlight scientific discoveries in the realm of optic nerve imaging that will ultimately change how neuro-ophthalmologists care for patients.

Advantages and Pitfalls of the Use of Optical Coherence Tomography for Papilledema

PURPOSE OF REVIEW

Papilledema refers to optic disc swelling caused by raised intracranial pressure. This syndrome arises from numerous potential causes, which may pose varying degrees of threat to patients. Manifestations of papilledema range from mild to severe, and early diagnosis is important to prevent vision loss and other deleterious outcomes. The purpose of this review is to highlight the role of optical coherence tomography (OCT) in the diagnosis and management of syndromes of raised intracranial pressure associated with papilledema.

RECENT FINDINGS

Ophthalmoscopy is an unreliable skill for many clinicians. Optical coherence tomography is a non-invasive ocular imaging technique which may fill a current care gap, by facilitating detection of papilledema for those who cannot perform a detailed fundus examination. Optical coherence tomography may help confirm the presence of papilledema, by detecting subclinical peripapillary retinal nerve fiber layer (pRNFL) thickening that might otherwise be missed with ophthalmoscopy. Enhanced depth imaging (EDI) and swept source OCT techniques may identify optic disc drusen as cause of pseudo-papilledema. Macular ganglion cell inner plexiform layer (mGCIPL) values may provide early signs of neuroaxonal injury in patients with papilledema and inform management for patients with syndromes of raised intracranial pressure. There are well-established advantages and disadvantages of OCT that need to be fully understood to best utilize this method for the detection of papilledema. Overall, OCT may complement other existing tools by facilitating detection of papilledema and tracking response to therapies.  Moving forward, OCT findings may be included in deep learning models to diagnose papilledema.

Understanding pseudopapilledema on spectral domain optical coherence tomography

Purpose

Optic nerve head drusen (ONHD), peripapillary hyperreflective ovoid mass-like structures (PHOMS), and horizontal hyperreflective lines (HHL) are commonly seen in eyes with pseudopapilledema on enhanced depth imaging (EDI) spectral domain optical coherence tomography (SDOCT). The objective of this study is to assess the frequency of ONHD, PHOMS, and HHL on spectral domain OCT in the eyes diagnosed to have pseudopapilledema.

Methods

A retrospective case-control study included patients diagnosed as pseudopapilledema and had EDI SD OCT imaging of the optic nerve head (n = 48 eyes) and controls (n = 20 eyes). OCT scans through the optic nerve head were studied to diagnose ONHD, HHL, and PHOMS. One proportion z test was used to find the difference in proportions.

Results

Forty eight eyes of 27 subjects were studied. ONHD as described by the optic disc drusen Studies consortium was noted in 19 eyes (39.48%), P value-0.032, PHOMS in 31 eyes (64.6%), P value 0.043, HL in 19 eyes (39.48%), P value 0.032, and none of the normals had ONHD, PHOMS, and HHL.

Conclusions

PHOMS are more frequently seen than ONHD and HHL in eyes with pseudopapilledema.

Influence of Patient Age and Presence of Optic Disc Drusen on Fluctuations in Retinal Nerve Fiber Layer Thickness

BACKGROUND

It is generally believed that optic disc drusen (ODD) change only over long periods of time. Because, in our experience, this does not apply to younger patients, we investigated the natural course of changes of the peripapillary retinal nerve fiber layer (RNFL) in patients with ODD.

METHODS

In this retrospective study, 40 eyes with and 40 eyes without ODD were examined, both cohorts were equally subdivided into younger subjects (20 years or younger) and older subjects (21 years or older). Three optical coherence tomography (OCT) scans of the peripapillary RNFL that had an interval of at least 1 month were required for each patient to be included in this study. The largest difference in total RNFL thickness (delta RNFL-t) and in RNFL thickness of the most differing sector (delta RNFL max) measured by OCT was compared.

RESULTS

The differences in total RNFL thickness and in the most differing RNFL sector in the group of patients with ODD younger than 21 years were significantly larger than in each of the other 3 groups ( P = 0.0001). The other 3 groups did not differ significantly.

CONCLUSIONS

Patients with ODD younger than 21 years have distinct variations in peripapillary RNFL thickness without evidence of increased intracranial pressure. In the absence of further pathological findings or neurological symptoms, an observational approach seems adequate in these patients.

Peripapillary hyper-reflective ovoid mass-like structures (PHOMS): clinical significance, associations, and prognostic implications in ophthalmic conditions

Pioneering advancements in optical coherence tomography (OCT) have facilitated the discernment of peripapillary hyper-reflective ovoid mass-like structures (PHOMS), prevalent neuro-ophthalmological findings associated with an array of ophthalmic conditions, such as optic disc drusen (ODD), papilledema, myopic/tilted optic discs, non-arteritic anterior ischemic optic neuropathy (NA-AION), and optic neuritis. Despite an expanding corpus of research, numerous inquiries persist concerning their clinical significance, correlations with ocular afflictions, and prognostic implications. This comprehensive review endeavors to impart an in-depth comprehension of PHOMS, encompassing facets like conceptualization, detection, pathogenesis, and associations with diverse ophthalmic conditions. Furthermore, we underscore several unresolved quandaries and suggest prospective avenues for future exploration.

A Comparison of Diagnostic Accuracy of Imaging Modalities to Detect Optic Disc Drusen: The Age of Enhanced Depth Imaging Optical Coherence Tomography

PURPOSE

To identify the most accurate diagnostic imaging modality to detect optic disc drusen (ODD) between B-scan ultrasonography (US), fundus photography, fundus autofluorescence (FAF), and enhanced depth imaging optical coherence tomography (EDI-OCT).

DESIGN

Comparative diagnostic analysis.

METHODS

Two hundred five eyes of 105 patients referred to 2 tertiary care neuro-ophthalmology clinics for suspected ODD were recruited: 108 eyes had ODD and 97 did not have ODD. All eyes received a full in-person ophthalmic exam with 3D view of the optic nerve and all 4 imaging modalities. Images were independently reviewed by 3 masked neuro-ophthalmologists to determine the presence or absence of ODD. Final interpretation was made through consensus. The reference standard was defined as the attending ophthalmologist's clinical judgement based on open chart review, with access to all image modalities and clinical information, including disease course. Main outcome measures were sensitivity, specificity, accuracy, and precision for each imaging modality. Examiner confidence was quantified as the proportion of eyes in which the reviewers were certain of their decision.

RESULTS

The EDI-OCT had the highest sensitivity and accuracy (95%, 97%) to detect ODD, compared with FAF (84%, 92%), US (74%, 86%), and fundus photography (38%, 66%), respectively. All image modalities had high specificity (> 97%) and precision (> 93%). The EDI-OCT also had highest examiner confidence (96%) compared with all others (88%).

CONCLUSIONS

Among all modalities, EDI-OCT was the imaging modality with the highest diagnostic utility for the detection of ODD and should be considered as the preferred initial diagnostic modality.

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.

Discriminating Between Papilledema and Optic Disc Drusen Using 3D Structural Analysis of the Optic Nerve Head

BACKGROUND AND OBJECTIVES

The distinction of papilledema from other optic nerve head (ONH) lesions mimicking papilledema, such as optic disc drusen (ODD), can be difficult in clinical practice. We aimed the following: (1) to develop a deep learning algorithm to automatically identify major structures of the ONH in 3-dimensional (3D) optical coherence tomography (OCT) scans and (2) to exploit such information to robustly differentiate among ODD, papilledema, and healthy ONHs.

METHODS

This was a cross-sectional comparative study of patients from 3 sites (Singapore, Denmark, and Australia) with confirmed ODD, those with papilledema due to raised intracranial pressure, and healthy controls. Raster scans of the ONH were acquired using OCT imaging and then processed to improve deep-tissue visibility. First, a deep learning algorithm was developed to identify major ONH tissues and ODD regions. The performance of our algorithm was assessed using the Dice coefficient. Second, a classification algorithm (random forest) was designed to perform 3-class classifications (1: ODD, 2: papilledema, and 3: healthy ONHs) strictly from their drusen and prelamina swelling scores (calculated from the segmentations). To assess performance, we reported the area under the receiver operating characteristic curve for each class.

RESULTS

A total of 241 patients (256 imaged ONHs, including 105 ODD, 51 papilledema, and 100 healthy ONHs) were retrospectively included in this study. Using OCT images of the ONH, our segmentation algorithm was able to isolate neural and connective tissues and ODD regions/conglomerates whenever present. This was confirmed by an averaged Dice coefficient of 0.93 ± 0.03 on the test set, corresponding to good segmentation performance. Classification was achieved with high AUCs, that is, 0.99 ± 0.001 for the detection of ODD, 0.99 ± 0.005 for the detection of papilledema, and 0.98 ± 0.01 for the detection of healthy ONHs.

DISCUSSION

Our artificial intelligence approach can discriminate ODD from papilledema, strictly using a single OCT scan of the ONH. Our classification performance was very good in the studied population, with the caveat that validation in a much larger population is warranted. Our approach may have the potential to establish OCT imaging as one of the mainstays of diagnostic imaging for ONH disorders in neuro-ophthalmology, in addition to fundus photography.

An overview of peripapillary hyperreflective ovoid mass-like structures

PURPOSE OF REVIEW

The purpose of this review is to provide an overview of the ophthalmic findings associated with peripapillary hyperreflective ovoid mass-like structures (PHOMS) in both adult and pediatric patients.

RECENT FINDINGS

PHOMS have recently been identified in a number of different ophthalmic disease entities ranging from nonpathologic to pathologic, including but not limited to anatomic abnormalities (tilting in myopia), optic nerve head drusen, optic disc edema from inflammation (optic neuritis, white dot syndromes), vascular insults (ischemic optic neuropathy, retinal vascular occlusion), and papilledema. The mechanism underlying the formation of PHOMS has not been fully elucidated although it has been hypothesized that PHOMS occur secondary to axoplasmic stasis from crowding at the optic nerve head.

SUMMARY

Although the clinical significance of the presence of PHOMS remains unclear, PHOMS are associated with several disease processes. Understanding the mechanism behind their formation and their impact on optic nerve head structure and visual function may be relevant in patients with optic nerve head pathology. The presence of PHOMS may also correlate with disease severity and duration. Future studies to evaluate whether the formation of PHOMS may be useful as an early indicator of disease or a prognostic tool are warranted.

Comparison of Spectral-Domain OCT versus Swept-Source OCT for the Detection of Deep Optic Disc Drusen

Deep optic disc drusen (ODD) are located below Bruch’s membrane opening (BMO) and may go undetected due to the challenges in imaging them. The purpose of this study is a head-to-head comparison of currently widely used imaging technologies: swept-source optical coherence tomography (SS-OCT; DRI OCT-1 Triton, Topcon) and enhanced depth imaging spectral-domain optical coherence tomography (EDI SD-OCT; Spectralis OCT, Heidelberg Engineering) for the detection of deep ODD and associated imaging features. The eyes included in this study had undergone high-resolution imaging via both EDI SD-OCT and SS-OCT volume scans, which showed at least one deep ODD or a hyperreflective line (HL). Grading was performed by three graders in a masked fashion. The study findings are based on 46 B-scan stacks of 23 eyes including a total of 7981 scans. For scan images with ODD located above or below the level of BMO, no significant difference was found between the two modalities compared in this study. However, for HLs and other features, EDI SD-OCT scan images had better visualization and less artifacts. Although SS-OCT offers deep tissue visualization, it did not appear to offer any advantage in ODD detection over a dense volume scan via EDI SD-OCT with B-scan averaging.

[Optical coherence tomography in the differential diagnostics of important neuro-ophthalmological disease patterns]

There are many disease patterns that are treated jointly by neurologists and ophthalmologists, for which optical coherence tomography (OCT) is of important differential diagnostic significance. In this context neurologists are mainly confronted by two patient collectives: patients with an acute ischemic event, who present with an acute but painless monocular visual deterioration (for central retinal artery occlusion) or with a monocular visual field defect (for arterial branch occlusion or anterior ischemic optic neuropathy). The second collective is patients without ophthalmological symptoms but with conspicuous optic nerve findings (papilledema or optic disc drusen). In this overview article both patient collectives are considered separately. In addition, the most important OCT findings for optic neuritis are presented. Before the disease patterns are described in detail, the normal OCT findings and the diagnostic possibilities of OCT are explained.

[Optical coherence tomography in the differential diagnostics of important neuro-ophthalmological disease patterns]

There are many disease patterns that are treated jointly by neurologists and ophthalmologists, for which optical coherence tomography (OCT) is of important differential diagnostic significance. In this context neurologists are mainly confronted by two patient collectives: patients with an acute ischemic event, who present with an acute but painless monocular visual deterioration (for central retinal artery occlusion) or with a monocular visual field defect (for arterial branch occlusion or anterior ischemic optic neuropathy). The second collective is patients without ophthalmological symptoms but with conspicuous optic nerve findings (papilledema or optic disc drusen). In this overview article both patient collectives are considered separately. In addition, the most important OCT findings for optic neuritis are presented. Before the disease patterns are described in detail, the normal OCT findings and the diagnostic possibilities of OCT are explained.

The Effects of Visual Field Loss from Optic Disc Drusen on Performance in a Driving Simulator

The purpose of this study was to compare the driving simulator performance of participants with visual field loss (VFL) from optic disc drusen (ODD) with a normally sighted control group and a group of individuals with glaucoma. Data on performance and safety from a traffic simulator test for five participants with VFL from ODD were retrospectively compared with data from 49 male individuals without visual deficits in a cross-sectional study. VFL of the ODD group was also compared with a group of 20 male glaucoma participants who had failed the same simulator test. Four individuals with ODD regained their driving licences after a successful simulator test and were then followed in a national accident database. All participants with ODD passed the test. No significant differences in safety or performance measures were detected between the normally sighted participants and the ODD group despite severe concentric visual field constrictions. Compared with failed glaucoma male participants, the ODD group had even lower mean sensitivity in the peripheral and peripheral inferior field of vision. None of the four participants with a regained licence were involved in a motor vehicle accident during a 3-year follow-up period after the simulator test. Despite having severe VFL, participants with ODD had no worse performance or safety than controls. As even individuals with severe VFL might drive safely, there is a need for individual practical assessments on licencing issues.