Automated classification of dementia subtypes from post-mortem cortex images

Authors:
David Cornforth;Herbert Jelinek
Affiliations:
Australian Defence Force Academy, Canberra, ACT, Australia;Charles Sturt University, Albury, NSW, Australia
Venue:
AI'05 Proceedings of the 18th Australian Joint conference on Advances in Artificial Intelligence
Year:
2005

Citing 2
Cited 1

Data mining: practical machine learning tools and techniques with Java implementations

Data mining: practical machine learning tools and techniques with Java implementations
A Comparison of Machine Learning Approaches for the Automated Classification of Dementia

AI '02 Proceedings of the 15th Australian Joint Conference on Artificial Intelligence: Advances in Artificial Intelligence

Automated classification reveals morphological factors associated with dementia

Applied Soft Computing

Quantified Score

Hi-index	0.00

Visualization

Abstract

We apply automated classification techniques to determine whether dementia is associated with changes in the physical structure of small blood vessels in the brain. A successful predictive model would imply such an association. The use of measures derived from fractal analysis, and the use of machine learning classification algorithms, allow exploration of highly complex relationships. Results suggest that although physiological differences are difficult to detect, and vary between different areas of brain tissue, there is evidence for such an association. If such changes can be detected from images of post mortem tissue, this implies that investigation of the medical significance of these changes could provide greater understanding of this class of diseases.