No abstract

and for the BONSAI (Brain and Optic Nerve Study with Artificial Intelligence) Study Group Objective: To compare the diagnostic performance of an artificial intelligence deep learning system with that of expert neuro-ophthalmologists in classifying optic disc appearance. Methods: The deep learning system was previously trained and validated on 14,341 ocular fundus photographs from 19 international centers. The performance of the system was evaluated on 800 new fundus photographs (400 normal optic discs, 201 papilledema [disc edema from elevated intracranial pressure], 199 other optic disc abnormalities) and compared with that of 2 expert neuro-ophthalmologists who independently reviewed the same randomly presented images without clinical information. Area under the receiver operating characteristic curve, accuracy, sensitivity, and specificity were calculated. Results: The system correctly classified 678 of 800 (84.7%) photographs, compared with 675 of 800 (84.4%) for Expert 1 and 641 of 800 (80.1%) for Expert 2. The system yielded areas under the receiver operating characteristic curve of 0.97 (95% confidence interval [CI] = 0.96-0.98), 0.96 (95% CI = 0.94-0.97), and 0.89 (95% CI = 0.87-0.92) for the detection of normal discs, papilledema, and other disc abnormalities, respectively. The accuracy, sensitivity, and specificity of the system's classification of optic discs were similar to or better than the 2 experts. Intergrader agreement at the eye level was 0.71 (95% CI = 0.67-0.76) between Expert 1 and Expert 2, 0.72 (95% CI = 0.68-0.76) between the system and Expert 1, and 0.65 (95% CI = 0.61-0.70) between the system and Expert 2. Interpretation: The performance of this deep learning system at classifying optic disc abnormalities was at least as good as 2 expert neuro-ophthalmologists. Future prospective studies are needed to validate this system as a diagnostic aid in relevant clinical settings.

To investigate the effect of pituitary adenoma compressing the optic chiasm on multifocal visual evoked potential (mfVEP) responses and to compare these responses with visual field defects seen on static automated perimetry (SAP). Eight eyes of four subjects (median age, 41.50 years; interquartile range, 33-51 years) who were diagnosed with pituitary adenoma on magnetic resonance imaging (MRI) and seen to have a bitemporal visual field defect on standard automated perimetry (SAP), and twelve age-matched normal subjects (median age, 47.00 years; interquartile range, 34.75-51.75 years) were subjected to multifocal visual evoked potential (mfVEP) testing. The monocular latencies and monocular amplitudes of each sector of cases were compared with the responses of normative database. The topography of the mfVEP response was compared with corresponding field defect as seen in total deviation threshold on SAP to allow a comparison with conventional subjective perimetry. The mfVEP amplitudes were reduced in the areas with visual field defect on SAP. In 6 out of 8 eyes, locations with preserved amplitudes and no visual defects showed prolonged latency. A prolonged median latency of 9.17 ms (interquartile range, 3.44-17.69 ms) in cases was seen when compared to the median latency of 1.67 ms (interquartile range, 0.94-4.17 ms) in age-matched controls with P value of 0.054. Chiasmal compression due to pituitary adenoma causes the reduction of amplitudes and prolongation of latencies of the mfVEP response. The mfVEP can be used to assess objectively the topography of the visual field in compressive optic neuropathy secondary to pituitary adenomas. It can be used in assessing the subjects whose visual field report is unreliable and prolonged median latency can be an early sign of the disease.

Aim:To discuss the clinical features and management of patients who presented with optic disc edema and had features of presumed idiopathic intracranial hypertension (IIH).Materials and Methods:Case series of all patients diagnosed to have IIH from January 2000 to December 2003 in the neuro-ophthalmology clinic of a tertiary referral ophthalmic institution, were retrospectively analyzed. Analysis was done for 50/106 patients who fulfilled modified Dandy's criteria and had optic disc edema and a minimal follow-up period of two years.Results: Most (40/50, 80%) of the patients were females and the mean age of presentation for all the 50 patients was 32.89 years. Chief complaints were headache in 38 (76%) patients, 24(48%) patients had transient visual obscuration, 24 (48%) patients had reduced vision, 15 (30%) patients had nausea, vomiting, 4(8%) patients had diplopia. Bilateral disc edema was seen in 46 (92%) patients and unilateral disc edema in 4 (8%) patients. 60 eyes had enlarged blind spot as the common visual field defect. Neuroimaging revealed prominent perioptic CSF spaces in 14 patients and empty sella in three patients. CSF opening pressure was 250–350 mm H2O (water) in 39 patients and was >350 mm H2O in 11 patients. Medical treatment was started for all patients; whereas 35 [70%] patients responded, 15 [30%] patients had to undergo LP shunt.