Artificial Intelligence in Tele-Health

Shaun Frost
Team Leader
Artificial Intelligence in Tele-Health

The AITH Team develop diagnostic and decision support systems for remote delivery of health services. The multi-disciplinary team brings together expertise in clinical research, telemedicine systems and artificial intelligence (AI) for medical image and data analysis. The team works with key stakeholders and collaborators to develop and trial these solutions to demonstrate improved health outcomes and health service delivery.

Our Science
Diagnostic systems and decision support are tested in hospital and primary healthcare environments, applying image and data analysis including artificial intelligence and deep learning. We investigate the use of telemedicine to provide healthcare to metro, rural and remote Australia and to identify new screening methods for systemic diseases. A current focus is the development of novel diagnostic technologies in the form of non-invasive ocular imaging techniques for ocular disease, diabetes, hypertension and neuro-degenerative diseases (Alzheimer’s disease and stroke).

Impact on the Health System
We aim to improve health outcomes and produce cost savings to the healthcare system. This is achieved through rapid and accurate image interpretation, improved health system workflow and enabling patients to process their own data to promote health.

Our Solutions
Research projects investigate the use of tele-medicine to provide healthcare to metro, rural and remote Australia, internationally and even for astronaut health during space travel and colonisation (through the Space FSP).

New disease screening methods that are possible to implement using tele-medicine include;

Early detection of Alzheimer’s disease using imaging of the eye:

  • Monitoring end-organ damage in resistant hypertension and cardiovascular disease
  • Automated grading technologies for eye diseases – diabetic and hypertensive retinopathy, age-related macular degeneration
  • Mobile tele-dentistry for school children
  • Monitoring risk for pre-eclampsia in pregnancy
  • Progression analysis for juvenile macular disease

Team Members:

Shaun Frost

Sajib Kumar Saha

Angelina Duan







Shaun Frost
Team leader and AADRF Dementia Research Fellow (NHMRC) – Early detection of Alzheimer’s disease using non-invasive ocular imaging.
CSIRO Profile

Sajib Kumar Saha
Research Scientist at AEHRC, Perth. He is working towards the development of machine learning techniques for the automated detection, prediction and progression analysis of sight threatening eye disease, specifically diabetic retinopathy (DR) and age-related macular degeneration (AMD).
CSIRO Profile

Angelina Duan
Post-doctoral researcher. Early detection of Alzheimer’s disease using non-invasive ocular imaging.
CSIRO Profile

Saptahrshi Seal
Intern, working on Retinal Vessel Analysis Platform.

Matt Watson
MPhil student, working on critical evaluation of deep learning system in diabetic retinopathy.


    1. Frost S, Gregory C, Robinson L, Yu S, Xiao D, Mehdizadeh M, Burnham S, Dehghani C, Vignarajan J, Kanagasingam Y, Schlaich MP. Effect of Pupil Dilation with Tropicamide on Retinal Vascular Caliber. Ophthalmic epidemiology. 2019 Nov 2;26(6):400-7.
    2. Yu S, Xiao D, Frost S, Kanagasingam Y. Robust optic disc and cup segmentation with deep learning for glaucoma detection. Computerized Medical Imaging and Graphics. 2019 Jun 1;74:61-71.
    3. Saha S, Nassisi M, Wang M, Lindenberg S, Sadda S, Hu ZJ. Automated detection and classification of early AMD biomarkers using deep learning. Scientific reports. 2019 Jul 29;9(1):1-9.
    4. Saha SK, Xiao D, Bhuiyan A, Wong TY, Kanagasingam Y. Color fundus image registration techniques and applications for automated analysis of diabetic retinopathy progression: A review. Biomedical Signal Processing and Control. 2019 Jan 1;47:288-302.
    5. Dehghani C, Frost S, Jayasena R, Masters CL, Kanagasingam Y. Ocular Biomarkers of Alzheimer’s Disease: The Role of Anterior Eye and Potential Future Directions. Investigative ophthalmology & visual science. 2018 Jul 2;59(8):3554-63.
    6. Saha SK, Xiao D, Frost S, Kanagasingam Y. Performance Evaluation of State-of-the-Art Local Feature Detectors and Descriptors in the Context of Longitudinal Registration of Retinal Images. Journal of medical systems. 2018 Apr 1;42(4):57.
    7. Saha S, Fletcher A, Xiao D, Kanagasingam Y. A novel method for automated correction of non-uniform/poor illumination of retinal images without creating false artifacts. Journal of Visual Communication and Image Representation. 2018 Feb 1;51:95-103.
    8. Martins RN, Villemagne V, Sohrabi HR, Chatterjee P, Shah TM, Verdile G, Fraser P, Taddei K, Gupta VB, Rainey-Smith SR, Hone E. Pedrini S, Lim WL, Martins I, Frost S, Gupta S, O’Bryant S, Rembach A, Ames D, Ellis K, Fuller SJ, Brown B, Gardener SL, Fernando B, Bharadwaj P, Burnham S, Laws SM, Barron AM, Goozee K, Wahjoepramono EJ, Asih PR, Doecke JD, Salvado O, Bush AI, Rowe CC, Gandy SE, Masters CL, Alzheimer’s disease: a journey from amyloid peptides and oxidative stress, to biomarker technologies and disease prevention strategies—gains from AIBL and DIAN cohort studies. Journal of Alzheimer’s Disease. 2018 Jan 1;62(3):965-92.