Topic 15: PCA-LDA analysis of normals, subjects with mild cognitive impairment and Alzheimer’s disease¶

1. Find out how Linear Discriminant Analysis works. Start by reading the paper by Caan et al. .
2. Find out how to efficiently perform PCA on high-dimensional data (i.e. with a low number of datapoints).
3. Download the Alzheimer-data from brightspace (see the data for assignments-tab). These data concern 50 volumes from normals and 50 volumes from subjects with MCI (mild cognitive impairment, find out what this is). All data is already registered. The fileformat can be read in MATLAB: oasis_load_data.m contains a small script showing how to load the data.
4. Implement the PCA-LDA algorithm in MATLAB and use it to study the differences in the signal values between the three populations of subjects.
5. Discuss your results.

References

1. M.W.A. Caan, K.A. Vermeer, L.J. van Vliet, C.B.L.M. Majoie, B.D. Peters, G.J. den Heeten, and F.M. Vos, Shaving diffusion tensor images in discriminant analysis: A study into schizophrenia, Medical Image Analysis, vol. 10, no. 6, 2006, 841-849.