Interpreting PET Scans by Structured Patient Data: A Data Mining Case Study in Dementia Research

Abstract

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.

Integer Linear Programming Models for Constrained Clustering

“…First we select a subset of patients covered by one frequent itemset. Then we evaluate the similarity of their PET scans by the mean of the pairwise weighted Euclidean distance [15]. In this way, we obtain a mean distance w j for each itemset C j .…”

“…This is known to be a big challenge for integer linear programs. We experiment on two publicly available datasets on thyroid disease 8 (m = 2,659 examples, 16 categorical and 6 numerical attributes 9 ) and on forest cover type 10 (m = 5 For a detailed description of the data see [15]. 6 Note: our base clusters have a minimal size of n · minSupport.…”

Automated fault detection method in process data based on cluster analysis

“…Thus clustering finds its uses in different fields: medicine (e.g. PET scan, genetics) [7], sociology and psychology (determining groups of people) [8], business (market research) [9] and much more.…”

A new neural unsupervised classification approach using amended competitive Hebbian learning: PET image segmentation insights

“…This scan images are more sensitive than other image techniques such CT and MRI because the other imaging techniques only show the physiology of the body parts, whereas the PET scan image shows the internal formation of tumours and cancer cells by means of the metabolism of the body parts (Hapfelmeier et al, 2009). Thus, the purpose of automatic medical image segmentation is to depict the image content based on its features.…”