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.

Osmolality of Cerebrospinal Fluid from Patients with Idiopathic Intracranial Hypertension (IIH).

INTRODUCTION: Idiopathic intracranial hypertension (IIH) is a disorder of increased intracranial fluid pressure (ICP) of unknown etiology. This study aims to investigate osmolality of cerebrospinal fluid (CSF) from patients with IIH. METHODS: We prospectively collected CSF from individuals referred on suspicion of IIH from 2011-2013. Subjects included as patients fulfilled Friedman and Jacobson's diagnostic criteria for IIH. Individuals in whom intracranial hypertension was refuted were included as controls. Lumbar puncture with ICP measurement was performed at inclusion and repeated for patients after three months of treatment. Osmolality was measured with a Vapor Pressure Osmometer. RESULTS: We collected 90 CSF samples from 38 newly diagnosed patients and 28 controls. At baseline 27 IIH-samples and at 3 months follow-up 35 IIH-samples were collected from patients. We found no significant differences in osmolality between 1) patients at baseline and controls (p = 0. 86), 2) patients at baseline and after 3 months treatment (p = 0.97), and 3) patients with normalized pressure after 3 months and their baseline values (p = 0.79). Osmolality in individuals with normal ICP from 6-25 cmH2O (n = 41) did not differ significantly from patients with moderately elevated ICP from 26-45 cmH2O (n = 21) (p = 0.86) and patients with high ICP from 46-70 cmH2O (n = 4) (p = 0.32), respectively. There was no correlation between osmolality and ICP, BMI, age and body height, respectively. Mean CSF osmolality was 270 mmol/kg (± 1 SE, 95% confidence interval 267-272) for both patients and controls. CONCLUSIONS: CSF osmolality was normal in patients with IIH, and there was no relation to treatment, ICP, BMI, age and body height. Mean CSF osmolality was 270 mmol/kg and constitutes a reference for future studies. Changes in CSF osmolality are not responsible for development of IIH. Other underlying pathophysiological mechanisms must be searched.