Loading...

quantusRT-OCT

Automatic assessment of the presence of microcysts and hyper-reflective spots from quantitative texture analysis of an OCT image set.

Non-invasive: quantusRT-OCT is based on optical coherence tomography (OCT) analysis in diabetic retinopathy, thus avoiding the need to use an invasive technique.

Fast: quantusRT-OCT generates accurate results in just a few minutes.

Classification system applied in quantusRT-OCT

  Sensitivity Specificity
Clinical Observation 80.0% 92.0%
Microcysts 87.3%% 94.4%
Hyper-reflective Dots 82.8% 85.6%
* Specificity: probability that the test identifies as not sick those who in fact are not sick.
* Sensitivity: probability that the test identifies as sick those who are indeed sick.

WHY DOES QUANTUSRT-OCT WORK?

An automated support tool is defined as one that requires minimal or no physician intervention to obtain a result. Over the last few years, research has focused on automated algorithms to improve current clinical diagnosis from images. The rise of Artificial Intelligence techniques, and especially Deep Learning techniques, has increased the number of studies using these types of algorithms in diagnostic ophthalmology.

Several recently published studies provide evidence that diabetic retinopathy detection using trained Deep Learning models can achieve high accuracy in diverse populations and provide quantitative comparisons of how model performance can vary across datasets consisting of retinographs of different severity and ethnicity.

quantusRT-OCT is presented as a novel Artificial Intelligence method based on state-of-the-art Deep Learning. It allows to identify patterns associated with specific pathologies and to determine the risk of presence of microcysts and hyperreflective spots in the eye.

The technology is based on performing a quantitative analysis of the texture of several retinal slices obtained by means of an ocular tomograph. This analysis makes it possible to identify patterns associated with specific pathologies and to determine the number of slices with microcysts or hyperreflective spots out of the 15-30 images that make up an OCT study.

WHEN TO USE QUANTUSRT-OCT?

quantusRT-OCT has been designed with a clear focus on the diabetic population, and is intended to be a tool for the detection of diabetic retinopathy, being of great help in the screening of patients with risk factors, patient follow-up and prioritization of waiting lists.

quantusRT-OCT:



Non Invasive


Reliable


Fast