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.

Deep Learning System Outperforms Clinicians in Identifying Optic Disc Abnormalities.

Background: The examination of the optic nerve head (optic disc) is mandatory in patients with headache, hypertension, or any neurological symptoms, yet it is rarely or poorly performed in general clinics. We recently developed a brain and optic nerve study with artificial intelligence-deep learning system (BONSAI-DLS) capable of accurately detecting optic disc abnormalities including papilledema (swelling due to elevated intracranial pressure) on digital fundus photographs with a comparable classification performance to expert neuro-ophthalmologists, but its performance compared to first-line clinicians remains unknown.

Methods: In this international, cross-sectional multicenter study, the DLS, trained on 14,341 fundus photographs, was tested on a retrospectively collected convenience sample of 800 photographs (400 normal optic discs, 201 papilledema and 199 other abnormalities) from 454 patients with a robust ground truth diagnosis provided by the referring expert neuro-ophthalmologists.

Artificial Intelligence Meets Neuro-Ophthalmology.

Recent advances in artificial intelligence have provided ophthalmologists with fast, accurate, and automated means for diagnosing and treating ocular conditions, paving the way to a modern and scalable eye care system. Compared to other ophthalmic disciplines, neuro-ophthalmology has, until recently, not benefitted from significant advances in the area of artificial intelligence. In this narrative review, we summarize and discuss recent advancements utilizing artificial intelligence for the detection of structural and functional optic nerve head abnormalities, and ocular movement disorders in neuro-ophthalmology.

Vision-related quality-of-life in pediatric primary brain tumor patients.

Purpose: Brain tumors are the leading cause of death from childhood cancer. Although overall survival has improved due to earlier detection, better therapies, and improved surveillance, visual dysfunction and impaired vision-related quality-of-life (VR-QOL) are often unrecognized in children. This project investigated VR-QOL in pediatric brain tumor patients.

Accuracy of a Deep Learning System for Classification of Papilledema Severity on Ocular Fundus Photographs.

Objective: To evaluate the performance of a deep learning system (DLS) in classifying the severity of papilledema associated with increased intracranial pressure on standard retinal fundus photographs.

Methods: A DLS was trained to automatically classify papilledema severity in 965 patients (2,103 mydriatic fundus photographs), representing a multiethnic cohort of patients with confirmed elevated intracranial pressure. Training was performed on 1,052 photographs with mild/moderate papilledema (MP) and 1,051 photographs with severe papilledema (SP) classified by a panel of experts.

Machine learning to determine relative contribution of modifiable and non-modifiable risk factors of major eye diseases.

Aims: To use machine learning (ML) to determine the relative contributions of modifiable and non-modifiable clinical, metabolic, genetic, lifestyle and socioeconomic factors on the risk of major eye diseases.

Methods: We conducted analyses in a cross-sectional multi-ethnic population-based study (n=10 033 participants) and determined a range of modifiable and non-modifiable risk factors of common eye diseases, including diabetic retinopathy (DR), non-diabetic-related retinopathy (NDR); early and late age-related macular degeneration (AMD); nuclear, cortical and posterior subcapsular (PSC) cataract; and primary open-angle (POAG) and primary angle-closure glaucoma (PACG). Risk factors included individual characteristics, metabolic profiles, genetic background, lifestyle patterns and socioeconomic status (n~100 risk factors).

Optic Disc Classification by Deep Learning versus Expert Neuro-Ophthalmologists.

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.

Prospective study of serum and aqueous humour anti-Hsp70.1 IgG antibody levels in ocular toxoplasmosis.

Aims: We evaluate whether the serum and aqueous humour (AH) level of IgG anti-Hsp70.1 antibodies improved the biological diagnosis of ocular toxoplasmosis.

Methods And Results: In this prospective cross-sectional and multicentre study, serum and AH were collected at the time of active uveitis.

Influence of Optic Nerve Appearance on Visual Outcome in Pediatric Idiopathic Intracranial Hypertension.

Objectives: To determine whether optic disc hemorrhages (ODH) and cotton wool spots (CWS) at presentation are associated with worse visual outcomes in pediatric patients with idiopathic intracranial hypertension (IIH).

Methods: Retrospective institutional review of 100 eyes of 50 consecutive pediatric IIH patients (aged 16 years or less) who had baseline optic disc photographs before or within 30 days of their diagnostic lumbar puncture and initiation of medical treatment. Optic disc photographs were independently graded by three ophthalmologists in a standardized manner.

Artificial Intelligence to Detect Papilledema from Ocular Fundus Photographs.

Background: Nonophthalmologist physicians do not confidently perform direct ophthalmoscopy. The use of artificial intelligence to detect papilledema and other optic-disk abnormalities from fundus photographs has not been well studied.

Methods: We trained, validated, and externally tested a deep-learning system to classify optic disks as being normal or having papilledema or other abnormalities from 15,846 retrospectively collected ocular fundus photographs that had been obtained with pharmacologic pupillary dilation and various digital cameras in persons from multiple ethnic populations.

Lack of Relationship between Central Corneal Thickness and Papilloedema in Idiopathic Intracranial Hypertension.

Translaminar pressure gradient abnormalities have been implicated in the pathogenesis and progression of glaucoma. A "reversed" translaminar pressure gradient may be related to papilloedema severity in idiopathic intracranial hypertension. Central corneal thickness is related to intraocular pressure measurements and, by extension, to translaminar pressure gradients.

Monitoring of visual field over 6 months after active ocular toxoplasmosis.

Purpose: To prospectively report the perimetric defects during a 6-month follow-up (FU) in patients with initially active ocular toxoplasmosis (OT).

Methods: Twenty-four patients were studied, including 11 eyes with chorioretinal toxoplasmosis proven with a positive aqueous humor sample and 13 eyes with a biologically unproven, chorioretinal lesion. Automated 24-2 SITA-Standard visual fields were performed at baseline, at the first, and sixth months of FU.

Differing presenting features of idiopathic intracranial hypertension in the UK and US.

Aim: Demographic factors potentially influencing the presentation and severity of idiopathic intracranial hypertension (IIH) in the US vs. UK populations include obesity and ethnicity. We aimed to compare the presenting features of IIH between populations in the UK and US tertiary referral centres, to assess what population differences exist and whether these cause different presentations and impact on visual function.

Nonmydriatic Fundus Photography in Patients with Acute Vision Loss.

p

Optic nerve appearance as a predictor of visual outcome in patients with idiopathic intracranial hypertension.

Background/aims: It remains unclear whether the presence of optic disc haemorrhages (ODH) or cotton wool spots (CWS) at presentation in patients with papilloedema from idiopathic intracranial hypertension (IIH) has prognostic value. The aim of this study was to determine if optic disc appearance at presentation predicts visual outcome in patients with IIH.

Methods: Retrospective study of 708 eyes of 360 consecutive patients with IIH who had baseline optic disc photographs before or within 30 days of their diagnostic lumbar puncture and initiation of medical treatment.

Optic nerve head edema among patients presenting to the emergency department.

Objective: To determine the frequency of and predictive factors for optic nerve head edema (ONHE) among patients with headache, neurologic deficit, visual loss, or elevated blood pressure in the emergency department (ED).

Methods: Cross-sectional analysis was done of patients with ONHE in the prospective Fundus Photography vs Ophthalmoscopy Trial Outcomes in the Emergency Department (FOTO-ED) study. Demographics, neuroimaging results, management, and patient disposition were collected.

Cerebrospinal fluid total protein in idiopathic intracranial hypertension.

Objective: To evaluate the relationship between CSF total protein concentration (CSF protein) and CSF opening pressure in idiopathic intracranial hypertension (IIH), and to explore the association of age, gender, race, BMI, and Humphrey visual field mean deviation (HVF MD) with CSF total protein.

Methods: The medical records of all IIH patients seen between 1989 and 2016 at one institution were systematically reviewed for demographics, CSF opening pressure, CSF contents, and HVF MD (at initial evaluation and most recent follow-up). Linear regression of CSF protein on CSF opening pressure was performed also considering BMI, age, gender, race, HVF MD, and year of lumbar puncture.

[Pseudomonas aeruginosa unilateral endogenous endophthalmitis in a preterm infant: a case report].

Endogenous endophthalmitis is a rare eye disease, affecting vulnerable subjects (such as preterm or older elderly subjects), with reserved visual and sometimes vital prognosis. We present a preterm boy, born at 35 weeks and 2 days gestation, who developed a right eye Pseudomonas aeruginosa endogenous endophthalmitis secondary to a left-foot peripherical catheter-infection-associated bacteremia. He had a first intravenous antibiotic therapy associating third-generation cephalosporin and fluoroquinolone, then Ceftazidime® by intravitreous injection and a subconjunctival injection of betamethasone.

[Endogenous Candida endophthalmitis in drug misusers injecting intravenous buprenorphine].

Purpose: To analyze patients presenting ocular candidiasis caused by intravenous drug addiction to buprenorphine.

Patients And Methods: We have listed all the cases of endogenous fungal endophthalmitis hospitalized between 1996 and 2005 in the ophthalmology department of the university-affiliated hospital of Rouen, France. Posterior vitrectomy was performed for each patient, with direct examination and bacterial and fungal cultures.

[Multifocal placoid pigment epitheliopathy as a manifestation of ophthalmological sarcoidosis].

Introduction: An ocular manifestation may be the only location of a general disease.

Observation: This is the case of a young female patient who developed placoid epitheliopathy at the age of 24. Four years later, sarcoidosis was diagnosed, with multivisceral damage and severe ophthalmological impairment, as well as skin, renal, and pulmonary involvement.

[Surgical management of nontraumatic corneal perforations: an 8-year retrospective study].

Purpose: Treatment of nontraumatic corneal perforation is a difficult task. The aim of our study was to retrospectively analyze predisposing conditions leading to perforation, surgical treatments, and visual outcomes.

Methods: Fifty-six patients were admitted in our department for a nontraumatic corneal perforation between 1997 and 2004.

[Intraocular fluids analysis for etiologic diagnosis of presumed infectious uveitis].

Purpose: To study the etiologic distribution of patients with presumed infectious uveitis who underwent ocular fluid analysis.

Patients And Methods: We retrospectively analyzed vitreous and or aqueous humor samples of patients with presumed infectious uveitis, referred to the department of Ophthalmology of the University Hospital of Rouen, France, between January 1997 and June 2004. We excluded patients with postsurgical or endogenous endophthalmitis.

A keratitis rat model for evaluation of anti-Acanthamoeba polyphaga agents.

Purpose: To develop a rat model of chronic Acanthamoeba polyphaga keratitis suitable for pharmacologic assessment of therapeutic agents.

Methods: An A. polyphaga isolate (ATCC #50495) was grown in peptone-yeast extract-glucose medium.