Application of manifold-based image analysis to identify subtle changes in digitally-captured pathology samples (2013–2017)

The primary aim of this project is to research and develop advanced computer aided analytics for digital pathology diagnosis and interpretation with the aim to largely automate several common pathology tests. In collaboration with significant partner Sullivan and Nicolaides Pathology, the project team will field trial the new analytics against traditional patient pathology tests to evaluate both efficacy and reliability. Analytics from the rapidly evolving fields of machine learning and pattern recognition will greatly improve the reliability and accuracy of current pathology methods as well as markedly shortening the delays. Likely application areas include auto-immune diseases, malaria, tuberculosis, and possibly breast cancer.
Grant type:
ARC Linkage Projects
  • Professor
    School of Electrical Engineering and Computer Science
    Faculty of Engineering, Architecture and Information Technology
Funded by:
Australian Research Council