Review of Retinal Imaging Modalities for Hydroxychloroquine Retinopathy

Cheong, Kai Xiong; Ong, Charles; Chandrasekaran, Priya R; Zhao, Jinzhi; Teo, Kelvin Yi Chong; Mathur, Ranjana

doi:10.3390/diagnostics13101752

Cited by 2 publications

(1 citation statement)

References 144 publications

(207 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The feature maps demonstrate that the heatmap scores are predominantly concentrated around the foveal locations (F). This observation aligns with previous studies on HCQ retinal retinopathy, which have utilized OCT spectral-domain analysis [34][35][36][37][38][39]. These studies have indicated that the concentration and presence of HCQ active ingredients significantly impact the thickness in the corresponding area.…”

Section: A Novel Screening Technique For Hcq Retinopathysupporting

confidence: 90%

Detection of Hydroxychloroquine Retinopathy via Hyperspectral and Deep Learning through Ophthalmoscope Images

Fan¹,

Nguyêñ

Wang³

et al. 2023

Diagnostics

View full text Add to dashboard Cite

Hydroxychloroquine, also known as quinine, is primarily utilized to manage various autoimmune diseases, such as systemic lupus erythematosus, rheumatoid arthritis, and Sjogren’s syndrome. However, this drug has side effects, including diarrhea, blurred vision, headache, skin itching, poor appetite, and gastrointestinal discomfort. Blurred vision is caused by irreversible retinal damages and can only be mitigated by reducing hydroxychloroquine dosage or discontinuing the drug under a physician’s supervision. In this study, color fundus images were utilized to identify differences in lesions caused by hydroxychloroquine. A total of 176 color fundus images were captured from a cohort of 91 participants, comprising 25 patients diagnosed with hydroxychloroquine retinopathy and 66 individuals without any retinopathy. The mean age of the participants was 75.67 ± 7.76. Following the selection of a specific region of interest within each image, hyperspectral conversion technology was employed to obtain the spectrum of the sampled image. Spectral analysis was then conducted to discern differences between normal and hydroxychloroquine-induced lesions that are imperceptible to the human eye on the color fundus images. We implemented a deep learning model to detect lesions, leveraging four artificial neural networks (ResNet50, Inception_v3, GoogLeNet, and EfficientNet). The overall accuracy of ResNet50 reached 93% for the original images (ORIs) and 96% for the hyperspectral images (HSIs). The overall accuracy of Inception_v3 was 87% for ORIs and 91% for HSI, and that of GoogLeNet was 88% for ORIs and 91% for HSIs. Finally, EfficientNet achieved an overall accuracy of 94% for ORIs and 97% for HSIs.

show abstract

Section: A Novel Screening Technique For Hcq Retinopathysupporting

confidence: 90%

Detection of Hydroxychloroquine Retinopathy via Hyperspectral and Deep Learning through Ophthalmoscope Images

Fan¹,

Nguyêñ

Wang³

et al. 2023

Diagnostics

View full text Add to dashboard Cite

show abstract

Classification of Hydroxychloroquine Retinopathy: A Literature Review and Proposal for Revision

Ahn

2024

Diagnostics

View full text Add to dashboard Cite

Establishing universal standards for the nomenclature and classification of hydroxychloroquine retinopathy is essential. This review summarizes the classifications used for categorizing the patterns of hydroxychloroquine retinopathy and grading its severity in the literature, highlighting the limitations of these classifications based on recent findings. To overcome these limitations, I propose categorizing hydroxychloroquine retinopathy into four categories based on optical coherence tomography (OCT) findings: parafoveal (parafoveal damage only), pericentral (pericentral damage only), combined parafoveal and pericentral (both parafoveal and pericentral damage), and posterior polar (widespread damage over parafoveal, pericentral, and more peripheral areas), with or without foveal involvement. Alternatively, eyes can be categorized simply into parafoveal and pericentral retinopathy based on the most dominant area of damage, rather than the topographic distribution of overall retinal damage. Furthermore, I suggest a five-stage modified version of the current three-stage grading system of disease severity based on fundus autofluorescence (FAF) as follows: 0, no hyperautofluorescence (normal); 1, localized parafoveal or pericentral hyperautofluorescence on FAF; 2, hyperautofluorescence extending greater than 180° around the fovea; 3, combined retinal pigment epithelium (RPE) defects (hypoautofluorescence on FAF) without foveal involvement; and 4, fovea-involving hypoautofluorescence. These classification systems can better address the topographic characteristics of hydroxychloroquine retinopathy using disease patterns and assess the risk of vision-threatening retinopathy by stage, particularly with foveal involvement.

show abstract

Review of Retinal Imaging Modalities for Hydroxychloroquine Retinopathy

Cited by 2 publications

References 144 publications

Detection of Hydroxychloroquine Retinopathy via Hyperspectral and Deep Learning through Ophthalmoscope Images

Detection of Hydroxychloroquine Retinopathy via Hyperspectral and Deep Learning through Ophthalmoscope Images

Classification of Hydroxychloroquine Retinopathy: A Literature Review and Proposal for Revision

Contact Info

Product

Resources

About