Quantifying frequency content in cross-sectional retinal scans of diabetics vs controls

 

Published on MedED:  29 August
Type of article: Clinical Article Summary
MedED Catalogue Reference: MOT001
Compiler: Linda Ravenhill

Sources: PLoS One, Medical Express
 

Approximately 28 million diabetic patients globally are thought to have vision-threatening retinopathy.  

Neural and vascular changes in the retina are a prominent feature of diabetic retinopathy and diabetic macular oedema and the main sight-threatening complications in the retina of many people with diabetes.2
 
In the early stages, these changes are detectable; however, new research has found that the changes can be determined even earlier, through the use of specialised imaging techniques and artificial intelligence in the form of computer analysis, allowing for earlier intervention and ultimately better outcomes for the patient.2
 
The clinical classification of the stages of severity of retinal disease involves various vascular changes, including changes to the blood vessels and the leakage of fluid and lipids. Most grading and classification schemes have not yet evolved to make the best use of modern imaging techniques and instead rely on colour fundus photography, with the original cameras using flood illumination and lacking scanning or confocal apertures to increase contrast.2
 
Traditionally an increase in retinal thickness was used as a marker to determine these changes. It may not be a sensitive measure of retinal pathology for several reasons, including:2
  • Damage or loss of neural elements in diabetic retinas which is a common pathological change
  • Changes such as those contributing to trans-synaptic degeneration of retinal ganglion cells resulting in retinal thinning can also be associated with other diseases, for example, stroke.
  • Additionally, some retinal changes result in one layer being thinned while another is thickened.2

Feature-based classification schedules are being developed, but these currently depend on human intervention, with human graders making the assessment – all of which is time-consuming and subjective

Furthermore, the potential optical signatures that would indicate early changes to vessels or vessel leakage are often small features, e.g. small, hyper-reflective hard exudates or hyper-reflective structures within vessels, and can be challenging to detect with clinical means or wide-field imaging.2
 
This new study suggests that an alternative is to consider a combination of methods that provide thickness and features.
 
Although not thicker than controls, the study found that diabetic retinas had subtle but quantifiable pattern changes in SD-OCT images, particularly in deeper fundus layers. The size range and distribution of this pattern in diabetic eyes were consistent with small blood vessel abnormalities and leakage of lipid and fluid.1
 
Feature-based biomarkers may augment retinal thickness criteria for the management of diabetic eye complications and may detect early changes.1 This new study is part of the current widespread emphasis on detection of diabetic retinopathy through artificial intelligence applied to retinal images.2
 
References:
1. Indiana University. (2021, July 26). New biomarkers may detect early eye changes that can lead to diabetes-related blindness. Retrieved August 29, 2021, from Medical Xpress: https://medicalxpress.com/news/2021-07-biomarkers-early-eye-diabetes-related.html
2.  Papay, J. A., & Elsner, A. E. (2021, June 21). Quantifying frequency content in cross-sectional retinal scans of diabetics vs. controls. PLos One. doi:DOI: 10.1371/journal.pone.0253091. Accessed 29 August 21. Retrieved from https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0253091

 

Contributor: Linda Ravenhill
Linda Ravenhill is a medical professional with an MA in Journalism. She has worked in the medical, technology and digital development spaces for over 25 years, & has a particular interest in the impact of technology on the delivery of healthcare in the Sub-Saharan Africa region.

Disclaimer
This article is compiled from a variety of resources researched and compiled by the contributor. It is in no way presented as an original work.  Every effort has been made to correctly attribute quotes and content. Where possible all information has been independently verified. The Medical Education Network bears no responsibility for any inaccuracies which may occur from the use of third-party sources. If you have any queries regarding this article contact us 


Fact-checking Policy
The Medical Education Network makes every effort to review and fact-check the articles used as source material in our summaries and original material. We have strict guidelines in relation to the publications we use as our source data, favouring peer-reviewed research wherever possible. Every effort is made to ensure that the information contained here is an accurate reflection of the original material. Should you find inaccuracies, out of date content or have any additional issues with our articles, please make use of the contact us form to notify us.
Rating  

Most Viewed Articles

Ethics & New Media
Aug 19, 2015
Rapid SSL

The Medical Education Network
Powered by LiveCAST, a VisualLive Solution