Professor Kanagasingam and his team trained Dr Grader’s AI using deep learning techniques, a form of machine learning for computer programs inspired by the human brain. The program is ‘trained’ to recognise diabetic retinopathy symptoms by giving it a large image data set of affected eyes to learn from.
Australian scientists have developed an artificial intelligence-driven technology that could make it easier to prevent blindness in the 1.7 million Australians with diabetes.
Published by Gizmodo in collaboration with the International Diabetes Federation.
Since 2018, around 15,000 patients have used artificial intelligence for faster and more accurate eye screenings across six polyclinics. Lek Wan Zhen finds out more.
Published by Lek Wan Zhen for Channel News Asia.
A ground breaking CSIRO eye-screening technology trialled at Midland GP Superclinic may soon make diabetes related blindness preventable.
Published by Andrew Carter for Echo News.
CSIRO has developed an innovative eye-screening technology that could help prevent blindness in the 1.7 million Australians living with diabetes.
Published by Jasmina for Australian Manufacturing.
Artificial intelligence could help detect diabetic retinopathy earlier than through traditional methods.
Published by Engineers Australia.
The study will benefit a lot more people other than astronauts, though: the agency believes its results could help us better understand conditions such as glaucoma, hydrocephalus and idiopathic intracranial hypertension, which causes severe headaches most pain killers can't alleviate.
Published by Engadget.
The Smart-I is a revolutionary portable eye scanner designed by Perth inventors Yogesan Kanagasingam and Edward Khoury. Professor Kanagasingam, an ophthalmology expert with TeleMedC and CSIRO research director, is the man behind the concept.
Published by Liam Croy for The West Australian.
The founder and CEO of TeleMedC, Para Segaram, said that Remote-I is opening up new market opportunities for the company.
Published by CSIRO.
Remote-I: our new healthcare technology that uses satellite broadband to help prevent blindness in remote communities.
Published by Nicholas Kachel for CSIROscope.
We aimed to investigate the intergrader and intragrader reliability of human graders and an automated algorithm for vertical cup-disc ratio (CDR) grading in colour fundus photographs.
The results suggest that AA is comparable to and may have more consistent performance than human graders in CDR grading of fundus photographs.
This may have potential application as a screening tool to help detect asymptomatic glaucoma-suspect patients in the community.
In this paper, we developed a robust segmentation method for optic disc and cup segmentation using a modified U-Net architecture, which combines the widely adopted pre-trained ResNet-34 model as encoding layers with classical U-Net decoding layers.
The model was trained on the newly available RIGA dataset, and achieved an average dice value of 97.31% for disc segmentation and 87.61% for cup segmentation, comparable to that of the experts’ performance for optic disc/cup segmentation and Cup-Disc-Ratio (CDR) calculation on a reserved RIGA dataset.
.svg){kind=icon}
