The barriers to global eye care equity and the role of digital innovations

Zheng, Shaokai; Choo, Justin; Chen, Jessica; Joshi, Sarala; Sun, Zhaohui

doi:10.1016/j.aopr.2021.100021

Cited by 5 publications

(2 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This study adds to the prior literature describing the 3D areal and volumetric measurements and sets the foundation for the application of 3D imaging in the periocular region. This might prompt the development of novel techniques for diagnosing and treating upper eyelid-related diseases and digital innovations for global eye care equity (27,28). The standardized measurement of area and volume has not been extensively evaluated in the periocular region.…”

Section: Discussionmentioning

confidence: 99%

A novel standardized approach for the 3D evaluation of upper eyelid area and volume

Guo¹,

Rokohl²,

Fan³

et al. 2023

Quant Imaging Med Surg

View full text Add to dashboard Cite

Background: Three-dimensional (3D) surface imaging and morphometrics are becoming the preferred craniofacial surface imaging modality. However, as a unique advantage of 3D imaging, areal and volumetric measurements have been rarely conducted and validated for evaluating soft tissue change in the periocular region, especially the upper eyelids. Therefore, based on an existing periocular landmark identification strategy, we proposed a novel modified method to define a standardized upper eyelid region for areal and volumetric measurements and validate its reliability for future clinical application.Methods: Forty-four healthy adult volunteers were enrolled in this cross-sectional study. Threedimensional facial images were taken with a 3D imaging system. Subsequently, the upper eyelid region selection and areal and volumetric measurements were conducted using a modified landmarks localization strategy to evaluate their intrarater, interrater, and intramethod reliability.Results: Areal measurement of the upper eyelid revealed highly reliable outcomes for intraclass correlation coefficient (ICC), mean absolute difference (MAD), relative error measurement (REM), technical error of measurement (TEM), and relative technical error of measurement (%TEM) of 0.982, 0.1620 cm 2 , 2.9%, 0.1510 cm 2 , and 2.7% for intrarater reliability, respectively; 0.969, 0.2076 cm 2 , 3.7%, 0.1930 cm 2 , and 3.5% for interrater reliability, respectively; and 0.917, 0.3636 cm 2 , 6.5%, 0.3354 cm 2 , and 6.0% for intramethod reliability, respectively. Unsatisfactory results were found for the volumetric measurement of the upper eyelid: the ICC, MAD, REM, TEM, and %TEM estimates for intrarater reliability were 0.992, 0.2299 mL, 10.3%, 0.2414 mL, and 10.8%, respectively; for interrater reliability, these values were 0.985, 0.2749 mL, 12.3%, 0.3253 mL, and 14.6%, respectively; and for intramethod reliability, these values were 0.433, 1.6716 mL, ^ ORCID: Yongwei Guo,

show abstract

Section: Discussionmentioning

confidence: 99%

A novel standardized approach for the 3D evaluation of upper eyelid area and volume

Guo¹,

Rokohl²,

Fan³

et al. 2023

Quant Imaging Med Surg

View full text Add to dashboard Cite

show abstract

“…OCT can reveal not only the presence of ERM but also the specific severity stage that can assist in guiding disease management [ 6 , 9 , 10 ]. However, the accurate fine-grading assessment of ERM based on OCT images requires reliable and interpretable analysis methods [ 11 ]. The large-scale interpretation of OCT images is deemed to be labor-intensive and time-consuming.…”

Section: Introductionmentioning

confidence: 99%

iERM: An Interpretable Deep Learning System to Classify Epiretinal Membrane for Different Optical Coherence Tomography Devices: A Multi-Center Analysis

Jin

Yan

Wang

et al. 2023

JCM

View full text Add to dashboard Cite

Background: Epiretinal membranes (ERM) have been found to be common among individuals >50 years old. However, the severity grading assessment for ERM based on optical coherence tomography (OCT) images has remained a challenge due to lacking reliable and interpretable analysis methods. Thus, this study aimed to develop a two-stage deep learning (DL) system named iERM to provide accurate automatic grading of ERM for clinical practice. Methods: The iERM was trained based on human segmentation of key features to improve classification performance and simultaneously provide interpretability to the classification results. We developed and tested iERM using a total of 4547 OCT B-Scans of four different commercial OCT devices that were collected from nine international medical centers. Results: As per the results, the integrated network effectively improved the grading performance by 1–5.9% compared with the traditional classification DL model and achieved high accuracy scores of 82.9%, 87.0%, and 79.4% in the internal test dataset and two external test datasets, respectively. This is comparable to retinal specialists whose average accuracy scores are 87.8% and 79.4% in two external test datasets. Conclusion: This study proved to be a benchmark method to improve the performance and enhance the interpretability of the traditional DL model with the implementation of segmentation based on prior human knowledge. It may have the potential to provide precise guidance for ERM diagnosis and treatment.

show abstract

Automatic interpretation and clinical evaluation for fundus fluorescein angiography images of diabetic retinopathy patients by deep learning

et al. 2022

View full text Add to dashboard Cite

Background/aimsFundus fluorescein angiography (FFA) is an important technique to evaluate diabetic retinopathy (DR) and other retinal diseases. The interpretation of FFA images is complex and time-consuming, and the ability of diagnosis is uneven among different ophthalmologists. The aim of the study is to develop a clinically usable multilevel classification deep learning model for FFA images, including prediagnosis assessment and lesion classification.MethodsA total of 15 599 FFA images of 1558 eyes from 845 patients diagnosed with DR were collected and annotated. Three convolutional neural network (CNN) models were trained to generate the label of image quality, location, laterality of eye, phase and five lesions. Performance of the models was evaluated by accuracy, F-1 score, the area under the curve and human-machine comparison. The images with false positive and false negative results were analysed in detail.ResultsCompared with LeNet-5 and VGG16, ResNet18 got the best result, achieving an accuracy of 80.79%–93.34% for prediagnosis assessment and an accuracy of 63.67%–88.88% for lesion detection. The human-machine comparison showed that the CNN had similar accuracy with junior ophthalmologists. The false positive and false negative analysis indicated a direction of improvement.ConclusionThis is the first study to do automated standardised labelling on FFA images. Our model is able to be applied in clinical practice, and will make great contributions to the development of intelligent diagnosis of FFA images.

show abstract

The barriers to global eye care equity and the role of digital innovations

Cited by 5 publications

References 14 publications

A novel standardized approach for the 3D evaluation of upper eyelid area and volume

A novel standardized approach for the 3D evaluation of upper eyelid area and volume

iERM: An Interpretable Deep Learning System to Classify Epiretinal Membrane for Different Optical Coherence Tomography Devices: A Multi-Center Analysis

Automatic interpretation and clinical evaluation for fundus fluorescein angiography images of diabetic retinopathy patients by deep learning

Contact Info

Product

Resources

About