Teleophthalmic Approach for Detection of Corneal Diseases: Accuracy and Reliability

Woodward, Maria A.; Musch, David C.; Hood, Christopher T.; Greene, Jonathan B.; Niziol, Leslie M.; Jeganathan, V Swetha E; Lee, Paul P.

doi:10.1097/ico.0000000000001294

Cited by 33 publications

(32 citation statements)

References 54 publications

(45 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Remote assessment of ocular injury in animal models can accurately identify referable conditions, such as eyelid laceration and globe rupture [30]. Additionally, when provided with patient history, corneal photography in telemedicine has demonstrated modest diagnostic specificity compared with inperson slit-lamp examination [31,32], suggesting some diagnostic utility in virtual examination.…”

Section: Visual Functionmentioning

confidence: 99%

Ophthalmology Practice During the Coronavirus Disease 2019 Pandemic: The University of Pittsburgh Experience in Promoting Clinic Safety and Embracing Video Visits

et al. 2020

View full text Add to dashboard Cite

The coronavirus disease 2019 pandemic has led to widespread change as public health strategies for containment have emphasized social distancing and remaining at home. These policies have led to downscaled clinic volumes, cancellation of elective procedures, enhanced personal protective strategies in the clinic, and adoption of telemedicine encounters. We describe the evidence-based practical approach taken in our ophthalmology department to continue delivering eye care during the pandemic by rescheduling visits, enhancing clinic safety, and adopting virtual video encounters. Key Summary PointsThis article covers the following topics relating to ophthalmology practice during the coronavirus disease 2019 pandemic.Brief background on COVID-19 and ophthalmic manifestations.Triage and rescheduling clinic appointments and OR procedures.Telemedicine, its role and implementation in the current pandemic. Early teleophthalmology experience from UPMC.This study has two Co-Principal Investigators:

show abstract

Section: Visual Functionmentioning

confidence: 99%

Ophthalmology Practice During the Coronavirus Disease 2019 Pandemic: The University of Pittsburgh Experience in Promoting Clinic Safety and Embracing Video Visits

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Prior studies on telemedicine in the diagnosis of corneal disease have focused on validating the use of portable cameras in remote evaluation of corneal disease. 20,23,24 It will be particularly exciting to explore the utility of telemedicine consultation of eye bank medical directors in determining the transplant suitability of corneal tissue-a use of telemedicine that has the potential to universally enhance tissue transplant-suitability determination by making medical director consults more accessible and more efficient.…”

Section: Discussionmentioning

confidence: 99%

“…Some investigations have validated the use of the video slit lamp or digital slit lamp images in remote evaluation of anterior segment eye diseases, 20,21 and others have relied on images obtained from portable cameras or smartphone camera attachments for remote evaluation of corneal disease. [22][23][24] To our knowledge, no prior study has described the use of telemedicine in eye bank tissue evaluation.…”

Section: Introductionmentioning

confidence: 99%

Novel Use of Telemedicine for Corneal Tissue Evaluation in Eye Banking: Establishing a Standardized Approach for the Remote Evaluation of Donor Corneas for Transplantation

Alabi

Ansin²,

Clover³

et al. 2018

Cornea

View full text Add to dashboard Cite

To determine the feasibility of employing telemedicine consultations in the evaluation of recovered donor corneas for transplant suitability. Methods: This study aims to establish and test the minimum imaging requirements for telemedical consultations of corneal tissue by remote eye bank medical directors. Digital images from the slit lamp, optical coherence tomography, and/or specular microscope were assembled into telemedical consults and emailed to 4 eye bank medical directors (MAT, JW, CSS, NKR). Surgeon feedback on the minimum image requirements for each corneal finding was collected. After establishing a standardized imaging and presentation protocol, test cases were presented to the medical directors to examine the validity of these remote consults. To establish a benchmark for the study's parameters, one medical director (JW) examined each case in-person after his initial remote review. Examiners were masked to each other's responses. Results: Minimum image requirements for determination of corneal findings were defined and were specific to each anatomic layer of the cornea (epithelial, stromal, or endothelial). Using a defined set of digital images for a set of common corneal findings, the rate of agreement between remote evaluators, eye bank staff, and the in-person evaluator was 100% (11 out of 11 examples). For ambiguous test cases, all remote evaluators agreed on 80% of the cases (4 out of 5).

show abstract

“…This technique was successful in detecting pterygium with 93.53% accuracy and 88.18% specificity [8]. A study of pterygium detection in 2017 by [66], where the ASPI was obtained from a slit-lamp camera, achieved 90% sensitivity.…”

Section: ) Towards Automated Detectionmentioning

confidence: 98%

Automated Pterygium Detection Using Deep Neural Network

et al. 2020

View full text Add to dashboard Cite

Ocular imaging has developed rapidly and plays a critical role in clinical care and ocular disease management. Development of image processing technologies pertinent to ocular diseases has paved the way for automated diagnostic systems including detection techniques using deep learning (DL) approaches. The prevalence of an abnormal tissue layer in the conjunctiva, known as pterygium eye disease, is increasing due to lack of awareness. Despite the non-cancerous/benign nature of pterygium, a clinical diagnosis from an ophthalmologist is still required to prevent the pterygium tissues from extending into the pupil, which would result in blurred vision. However, current diagnostic methods are mostly dependent on human expertise. Automated detection can potentially serve as an assistive method to reduce diagnosis time by applying a DL approach. Considering the lack of comprehensive research work on pterygium detection using DL, we propose a new architecture consisting of an improved CNN-based trained network named VggNet16-wbn that is derived from VggNet16, a pre-trained CNN algorithm. This paper presents an overview of the DL as a core approach to the transfer learning (TL) concept, as well as current efforts towards automated ocular detection approaches. A new architecture of a CNN-based trained network was proposed based on a network assessment from six CNN pre-trained networks to detect pterygium. This work consists of two main modules, namely, data acquisition and DCNN classification. The proposed trained network, VggNet16-wbn, shows the best performance with 99.22% accuracy, 98.45% sensitivity, and a perfect score on specificity and area under the curve metrics. This work has high potential for creating a pterygium screening system that can be used as a baseline for fully automated detection using a DL approach.

show abstract

Teleophthalmic Approach for Detection of Corneal Diseases: Accuracy and Reliability

Cited by 33 publications

References 54 publications

Ophthalmology Practice During the Coronavirus Disease 2019 Pandemic: The University of Pittsburgh Experience in Promoting Clinic Safety and Embracing Video Visits

Ophthalmology Practice During the Coronavirus Disease 2019 Pandemic: The University of Pittsburgh Experience in Promoting Clinic Safety and Embracing Video Visits

Novel Use of Telemedicine for Corneal Tissue Evaluation in Eye Banking: Establishing a Standardized Approach for the Remote Evaluation of Donor Corneas for Transplantation

Automated Pterygium Detection Using Deep Neural Network

Contact Info

Product

Resources

About