Supervisors: Dr Srujana Sahebjada and Professor Mark Daniell

Email: srujana.sahebjada@unimelb.edu.au

Keratoconus is a common condition that affects the cornea and despite its increasing prevalence, the cause of keratoconus is largely unknown. The aim of the projects is to better understand the underlying molecular causes, clinical characteristics and treatment options of keratoconus to develop strategies that can halt the disease progression.

The project also aims at developing machine learning algorithms to identify features that define early subclinical keratoconus that are currently refractory as well as identify a series of features that are involved in a) disease staging, as well as b) risk of progression of keratoconus.

The project involves collection of large datasets from clinical records and images and offers an exciting opportunity to conduct big data analysis and manuscript writing.

Students with a background in either medical, biomedical and computer science, optometry and visual science, or statistics are welcome to apply.