Interpreting PET scans by structured patient data: a data mining case study in dementia research
- 163 Downloads
One of the goals of medical research in the area of dementia is to correlate images of the brain with clinical tests. Our approach is to start with the images and explain the differences and commonalities in terms of the other variables. First, we cluster Positron emission tomography (PET) scans of patients to form groups sharing similar features in brain metabolism. To the best of our knowledge, it is the first time ever that clustering is applied to whole PET scans. Second, we explain the clusters by relating them to non-image variables. To do so, we employ RSD, an algorithm for relational subgroup discovery, with the cluster membership of patients as target variable. Our results enable interesting interpretations of differences in brain metabolism in terms of demographic and clinical variables. The approach was implemented and tested on an exceptionally large data collection of patients with different types of dementia. It comprises 10 GB of image data from 454 PET scans, and 42 variables from psychological and demographical data organized in 11 relations of a relational database. We believe that explaining medical images in terms of other variables (patient records, demographic information, etc.) is a challenging new and rewarding area for data mining research.
KeywordsPET Clustering Subgroup discovery Alzheimer’s disease Dementia Brain Neuro imaging CERAD CDR
Unable to display preview. Download preview PDF.
- 1.Bär H, Sauer J (2006) Diagnostik und Therapie häufiger Demenzen. In: Ärzteblatt Thüringen. Jena, Germany, pp 413–414Google Scholar
- 2.Böhm C, Kailing K, Kriegel H-P, Kröger P (2004) Density connected clustering with local subspace preferences. In: ICDM ’04: Proceedings of the fourth IEEE international conference on data mining (ICDM’04). IEEE Computer Society, Washington, DC, pp 27–34Google Scholar
- 5.Clark P, Niblett T (1989) The CN2 induction algorithm. Mach Learn 3(4): 261–283Google Scholar
- 6.Corani G, Edgar C, Marshall I, Wesnes K, Zaffalon M (2006) Classification of dementia types from cognitive profiles data. In: Proceedings of the 10th european conference on principle and practice of knowledge discovery in databases (PKDD 2006). Springer, Heidelberg, pp 470–477Google Scholar
- 8.Kalbfleisch J (1985) Probability and statistical inference: statistical inference, vol 2. Springer, HeidelbergGoogle Scholar
- 9.Kaufman L, Rousseeuw PJ (1990) Finding groups in data: an introduction to cluster analysis. Wiley, New YorkGoogle Scholar
- 10.Lavrač N, Železný F, Flach PA (2003) RSD: Relational subgroup discovery through first-order feature construction. In: Matwin S, Sammut C (eds) Proceedings of the 12th international conference on inductive logic programming. Lecture Notes in Artificial Intelligence, vol 2583. Springer, Heidelberg, pp 149–165Google Scholar
- 11.Mani S, Shankle W, Pazzani MJ, Smyth P, Dick MB (1997) Differential diagnosis of dementia: a knowledge discovery and data mining (KDD) approach. American Medical Informatics Association (AMIA) Annual Fall SymposiumGoogle Scholar
- 16.Železný F (2003) RSD—a system for relational subgroup discovery through first-order feature construction—user‘s manual. 2003. v1.0Google Scholar
- 19.World Health Organization (2005) ICD-10: International statistical classification of diseases and related health problems (Tenth Revision), 2nd edn. World Health Organization, Geneva, SwitzerlandGoogle Scholar