​​​

THEIA™ development, and testing of artificial intelligence‐based primary triage of diabetic retinopathy screening images in New Zealand

- In Publication 

Prospective Study

• 712 patients

• 100% Imageability

• 94.2% Sensitivity 

• 96.0% Specificity

THEIA development, and testing of artificial intelligence-based primary triage of diabetic retinopathy screening images in New Zealand 

- In Publication 

Towards implementation of AI in New Zealand national diabetic screening program: Cloud-based, robust, and bespoke

THEIA's performance assessed using a cloud platform

THEIA used OCTA for diagnosis of AMD

Quantification of optical coherence tomography angiography in age and age-related macular degeneration using vessel density analysis

THEIA as multi-modal imaging AI for detection of AMD

Multimodal Retinal Image Analysis via Deep Learning for the Diagnosis of Intermediate Dry Age-Related Macular Degeneration: A Feasibility Study

Retrospective Study

• 66,000 patient

• graded by at least 3 clinicians

• 95.8% sensitivity

• 99.5 % Negative predictive value

Towards implementation of AI in New Zealand national screening program: Cloud-based, Robust, and Bespoke

THEIA as a smoking detection tool

Detection of smoking status from retinal images; a Convolutional Neural Network study