Exciting potential of artificial intelligence applications

Dermot McGrath

Posted: Thursday, September 20, 2018

Deep learning and advanced artificial intelligence (AI) applications hold exciting potential in diagnosing and treating a wide range of eye diseases and are already making an impact on current clinical practice, delegates attending yesterday’s EURETINA symposium on AI were told.
Chaired by Tariq M Aslam FRCS, PhD, the symposium “Innovations in Ophthalmology: Spotlight on Artificial Intelligence Applications” provided a broad overview of recent innovations in the field of AI and highlighted the vast potential of machine technology to provide more efficient and objective analysis of images and prediction of disease progression.
“There is little doubt that AI is probably at the peak of the famous hype curve at the moment and everybody from big pharma to the retinal physician wants to be a part of the revolution,” said Adnan Tufail, MBBS, MD, FRCOphth in his discussion on the future of AI applications in ophthalmology.
“We should be aware that a trough of disappointment inevitably follows the peak of interest, but AI is definitely here to stay. We will see some sustained genuine benefits that are going to impact our clinical practice,” he said.
While there was understandable anxiety about the role of technology in day-to-day practice, Dr Tufail said that the benefits will ultimately far outweigh the risks.
“The bottom line is that AI is not going to put us out of a job, but we need to embrace this technology to make us the best retinal specialists that we can possibly be,” he said.
The possibility of detecting and quantifying macular fluid in conventional optical coherence tomography (OCT) images using deep learning was discussed by Ursula Schmidt-Erfurth MD, PhD.
“AI enables the recognition of patterns based on decision trees. It allows for automated segmentation, quantification of lesions, pattern recognition, prediction of recurrence and progression, and structural and functional correlation at a much faster rate than humans can achieve,” she said.
She told the audience that her research group in Vienna has made enormous progress in the development and validation of a fully automated method to detect and quantify macular fluid in OCT.
“Deep learning in retinal image analysis achieves excellent accuracy for the differential detection of retinal fluid types across the most prevalent exudative macular diseases and OCT devices. Furthermore, quantification of fluid achieves a high level of concordance with manual expert assessment,” she said.