Retinal imaging in infants

Oral Fluorescein Angiography for the Diagnosis of Papilledema Versus Pseudopapilledema in Children

PURPOSE

To evaluate the accuracy and safety of oral fluorescein angiography (OFA) in differentiating papilledema from pseudopapilledema in pediatric patients.

DESIGN

Retrospective evaluation of a diagnostic test.

METHODS

We retrospectively reviewed medical records of all children ≤18 years of age who presented to the Arkansas Children's Hospital between May 2018 and August 2021 with suspected optic disc (OD) swelling that had OFA and images >30 minutes after oral ingestion. Two masked specialists interpreted the images as either OD leakage, no leakage, or borderline leakage. Optic disc swelling was graded clinically according to the Frisen grading scale (0-5). We compared OFA images to the final clinical diagnosis and calculated the accuracy of the test as follows: (number of eyes correctly identified as papilledema [true positive] + number of eyes correctly identified as pseudopapilledema [true negative]) / (total number of eyes) × 100%.

RESULTS

Forty-five patients (90 eyes) were included, 11 patients with papilledema and 34 with pseudopapilledema. The mean age was 14.1 ± 3.5 years; 66.7% were female. The accuracy of OFA was 62% for reviewer 1 and 69% for reviewer 2. No ocular or systemic side effects after OFA were observed. There was substantial agreement (k = 0.779) between both reviewers in grading the OFA images.

CONCLUSION

OFA cannot definitively distinguish papilledema from pseudopapilledema in children and should be interpreted in conjunction with other clinical findings.

DIAROP: Automated Deep Learning-Based Diagnostic Tool for Retinopathy of Prematurity

Retinopathy of Prematurity (ROP) affects preterm neonates and could cause blindness. Deep Learning (DL) can assist ophthalmologists in the diagnosis of ROP. This paper proposes an automated and reliable diagnostic tool based on DL techniques called DIAROP to support the ophthalmologic diagnosis of ROP. It extracts significant features by first obtaining spatial features from the four Convolution Neural Networks (CNNs) DL techniques using transfer learning and then applying Fast Walsh Hadamard Transform (FWHT) to integrate these features. Moreover, DIAROP explores the best-integrated features extracted from the CNNs that influence its diagnostic capability. The results of DIAROP indicate that DIAROP achieved an accuracy of 93.2% and an area under receiving operating characteristic curve (AUC) of 0.98. Furthermore, DIAROP performance is compared with recent ROP diagnostic tools. Its promising performance shows that DIAROP may assist the ophthalmologic diagnosis of ROP.