Visualisation in biomedicine as a means of data evaluation
- 103 Downloads
Visualisation of complex phenomena can aid in understanding the interactions of multiple feature parameters that underlie such phenomena. One such example is the study of dementia, where fractal image measures obtained from post-mortem cortex images have been found useful in studying the relationship between micro-vascular structure and disease. In this research, we analyse the correlation differences in these measures between cases classified as control (non-diseased) and those classified as having either Alzheimer’s disease, small vessel disease or both (diseased). Correlations between feature parameters within these groups indicate that a relationship exists between vessel structure and the parietal and occipital brain regions not identified previously. A simple visualisation method allows these differences to be readily identified. These differences may lead to new insights about the difference in disease progression in different brain areas, and could assist in identifying useful parameters for automated classification.
KeywordsDementia Visualisation Multifractal Lacunarity Correlation
The authors would like to thank Patricia Waley, The University of Sydney, Australia for providing the microscope images and Cherryl Kolbe for technical assistance.
- Dzemyda G, Kurasova O (2007) Dimensionality problem in the visualization of correlation-based data. In: Lecture notes in computer science: adaptive and natural computing algorithms, vol 4432/2007. Springer, Berlin, pp 544–553. doi: 10.1007/978-3-540-71629-7_61
- Erbacher RF (2007) Exemplifying the inter-disciplinary nature of visualization research. Paper presented at the proceedings of IV07: 11th international conference information visualisation, Zurich, SwitzerlandGoogle Scholar
- Plotnick RE, Gardner RH, Hargrove WW, Prestegaard K, Perlmutter M (1996) Lacunarity analysis: a general technique for the analysis of spatial patterns. Am Phys Soc 53(5):5461–5468Google Scholar
- Witten H, Frank E (1999) Data Mining: practical machine learning tools and techniques with Java implementations. Morgan Kaufmann, SydneyGoogle Scholar