Automated detection of glaucoma biomarkers may predict progression
Click Here to Manage Email Alerts
Algorithm-aided detection of apoptosing retinal cells could predict glaucoma progression 18 months later, showing potential to provide an automated, objective biomarker with widespread clinical application, according to a study.
Detection of apoptosing retinal cells (DARC), a noninvasive imaging technique using confocal scanning laser ophthalmoscopy to visualize apoptotic retinal cells in vivo and at the early stages, was previously tested in phase 1 and 2 studies.
The aim of this new study was to develop an automatic method of DARC spot detection using a convolutional neural network (CNN) algorithm and to evaluate the ability of this method to predict the risk for glaucoma progression.
Retinal images were acquired from 40 healthy control subjects and 20 patients with glaucoma, and the algorithm was trained using candidate DARC spots identified by at least two of five manual observers. When tested on glaucomatous eyes, defined as progressing or stable based on OCT retinal nerve fiber layer measurements at 18 months, accuracy of the algorithm was demonstrated with 85.7% sensitivity and 91.7% specificity.
The DARC count using the CNN-aided algorithm was significantly higher in glaucoma patients who were later found to be progressing at 18 months vs. those who remained stable.
“We were also able to find a threshold value. Since no stable eyes had a CNN DARC count above 30, and all patients who had DARC more than 30 went on to progress 18 months later, this threshold could be confidently used to separate those at risk of progression,” Maria Francesca Cordeiro, MD, told Healio/OSN.
This further development of the DARC technology could represent a milestone in the management of glaucoma and in the testing and validation process of neuroprotective glaucoma therapies.
“Something we have been lacking in neuroprotection is good measures of how quickly people respond to successful treatment. Now we can shorten study times and set up smaller concept trials to then go on to larger ones when we have proved the efficacy,” Cordeiro said.
Collapse
Read more about
Click Here to Manage Email Alerts