Imaging in Myopia

Hoang, Quan V.; Chua, Jacqueline; Ang, Marcus

doi:10.1007/978-981-13-8491-2_10

Cited by 8 publications

(6 citation statements)

References 128 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Since the number of fundus-FFA images is limited, we compromise to develop a multi-modal self-supervised model by synthesizing the FFA images. In reality, FFA images would provide more information about microaneurysms and hemorrhage, which would be beneficial for the disease diagnosis, such as AMD and PM [15,14,16]. One solution is to collect the datasets with color fundus and corresponding FFA images.…”

Section: Discussionmentioning

confidence: 99%

“…Fundus fluorescein angiography (FFA) is an imaging modality that can provide useful information regarding the retinal vasculature in the retina [14]. This information can help ophthalmologists better understand the structures of fundus le-sions, microangioma, and capillary non-perfusion area, which are crucial for the diagnosis and treatment of some vitreoretinal diseases like AMD and PM [15,14,16]. The retinal vasculature information presented in FFA is complementary to color fundus images since FFA could identify fundus lesions that were not discovered by color fundus images [15].…”

mentioning

confidence: 99%

See 1 more Smart Citation

Self-Supervised Feature Learning via Exploiting Multi-Modal Data for Retinal Disease Diagnosis

Jia

Islam

et al. 2020

IEEE Trans. Med. Imaging

View full text Add to dashboard Cite

The automatic diagnosis of various retinal diseases from fundus images is important to support clinical decisionmaking. However, developing such automatic solutions is challenging due to the requirement of a large amount of humanannotated data. Recently, unsupervised/self-supervised feature learning techniques receive a lot of attention, as they do not need massive annotations. Most of the current self-supervised methods are analyzed with single imaging modality and there is no method currently utilize multi-modal images for better results. Considering that the diagnostics of various vitreoretinal diseases can greatly benefit from another imaging modality, e.g., FFA, this paper presents a novel self-supervised feature learning method by effectively exploiting multi-modal data for retinal disease diagnosis. To achieve this, we first synthesize the corresponding FFA modality and then formulate a patient feature-based softmax embedding objective. Our objective learns both modality-invariant features and patient-similarity features. Through this mechanism, the neural network captures the semantically shared information across different modalities and the apparent visual similarity between patients. We evaluate our method on two public benchmark datasets for retinal disease diagnosis. The experimental results demonstrate that our method clearly outperforms other self-supervised feature learning methods and is comparable to the supervised baseline. Our code is available at GitHub 1. Index Terms-Retinal disease diagnosis, self-supervised learning, multi-modal data I. INTRODUCTION C OLOR fundus photography has been widely used in clinical practice to evaluate various conventional ophthalmic diseases, e.g., age-related macular degeneration (AMD) [1], pathologic myopia (PM) [2], and diabetic retinopathy [3, 4]. Recently, deep learning has shown very good performance on a variety of automatic ophthalmic disease detection problems from fundus images [5-7], and these techniques can help ophthalmologists in decision making. The success is attributed to the learned representative features from fundus images, which requires a large amount of training data with massive human annotations. However, it is tedious and expensive to annotate the fundus images, since experts are needed to provide reliable labels. Hence, in this paper, our goal is to learn the representative features from data itself, without any human

show abstract

Section: Discussionmentioning

confidence: 99%

mentioning

confidence: 99%

Self-Supervised Feature Learning via Exploiting Multi-Modal Data for Retinal Disease Diagnosis

Jia

Islam

et al. 2020

IEEE Trans. Med. Imaging

View full text Add to dashboard Cite

show abstract

“…Current surgical methods to prevent pterygium recurrence include conjunctival autograft, limbal and limbal-conjunctival transplant, conjunctival flap and conjunctival rotational autograft surgery, amniotic membrane transplant cultivated conjunctival transplant, lamellar keratoplasty, fibrin glue, and suture-less and glue-free conjunctival autograft" [13].…”

Section: Discussionmentioning

confidence: 99%

Doubt flap technique in pterygium surgery

Abdulgani¹

2023

djm

View full text Add to dashboard Cite

Background: A pterygium is a triangular fibrovascular sub-epithelial ingrowth of degenerative bulbar conjunctival tissue over the limbus onto the cornea. The mainstay of treatment is surgery with more measures to decrease the recurrence rate. Pterygium doesn’t need intervention unless there is an extension of the lesion towards the center of the cornea and it encroaches on the visual axis, or is symptomatic in terms of redness and discomfort. Objective: To present a new surgical technique for managing primary pterygium. We aim to find a more effective method than the one previously used. We wanted to demonstrate and prove that this technique has low recurrence rates. Patients and Methods: A Hospital-based interventional case series study, sampling done by simple random sampling from the outpatient departments. The study was conducted in the ophthalmology department of Erbil teaching hospital in Erbil city for eight months from August 2021-April 2022. In the current study 40 patients with pterygium were operated that they were attending the ophthalmology department in this hospital. Results: The result revealed 3 cases of recurrence of 7.5% out of 40 cases using a dual flap technique as a new approach for treating pterygium in the follow-up of 3 months, in which the mean ± SD of age was 46.3 ± 10.537 years. Twenty four cases were female, and 16 were male; all of the lesions were nasally located pterygium. In the sample we used in the study 5 patients had had pterygium excision using other techniques in the past at least once, and neither of them recurred utilizing this approach. Conclusion: The double flap is a proper alternative technique in pterygium surgery; this new procedure, dual conjunctival flap with 7.5% recurrence rates and provides safe and comparable results to current methods.

show abstract

“…More recently, due to the Covid-19 lockdowns, the incidence of myopia has increased approximately 4% in Chinese children aged 3 to 6 years [10]. The prevalence of myopia is lower in middle and lowincome countries are described as ranging from 1.4 to 14.4% in Latin America and 3.4 to 11.4% in Africa, based on ancient statistics [11,12].…”

Section: (Which Was Not Certified By Peer Review)mentioning

confidence: 99%

Prevalence of Myopia Among Public School Children in Southern Brazil

Gus

Maman

Lengler

et al. 2023

Preprint

View full text Add to dashboard Cite

Purpose: Myopia has been considered a public health issue by the World Health Organization since 2015.The growing incidence of myopia worldwide, called the myopia epidemic, and its potential blinding complications in adulthood like cataract, glaucoma, retinal detachment and maculopathy, have been extensively published and discussed in peer review papers. Nonetheless, little information about Latin America is available. This study aims to detect the prevalence of myopia in southern Brazil, the biggest country of South America. Methods: A prospective cross sectional study recruited 330 public school children between 2019 and 2021, aged 5 to 20 years old. All children underwent a comprehensive eye examination and detailed lifestyle questionnaire. The Pearson correlation coefficient, Kruskal Wallys and the Chi-Square Test were used to assess simple correlations and associations between myopia and medical conditions, use of medications, ophthalmic history and family history of ocular conditions, besides demographics and lifestyle focused on screen time/day. Associations between the results of the ophthalmologic evaluation and all factors included in the questionnaire were analyzed using the Generalized Estimating Equation model (GEE). The prevalence of hyperopia and astigmatism were also assessed. Results: Total prevalence of myopia was 17.4% (CI 13.8 – 21.7%). Low myopia (-0.50D to -5.75D) comprised 15.2% (CI 11.9 – 19.3%) and high myopia (-6,00D or worse) was 2.1% (CI 1.1 – 4.1%). Relative risk of myopia for females was 1.6 (CI 1.00 – 2.57%) and each additional hour of screen time increased a child’s chance of having myopia by 6.5%. The prevalence of hyperopia was 7,7% (CI 5.4 -10.9%) and of astigmatism, either myopic or hyperopic, was 25.6% (CI 21.4 – 30.2%). Conclusions: Brazil has always been considered a hyperopic country. These are the highest reported prevalences of myopia under cycloplegia and the first paper to present myopia as a more prevalent refractive error than hyperopia among Brazilian school children to date.

show abstract

Imaging in Myopia

Cited by 8 publications

References 128 publications

Self-Supervised Feature Learning via Exploiting Multi-Modal Data for Retinal Disease Diagnosis

Self-Supervised Feature Learning via Exploiting Multi-Modal Data for Retinal Disease Diagnosis

Doubt flap technique in pterygium surgery

Prevalence of Myopia Among Public School Children in Southern Brazil

Contact Info

Product

Resources

About