Five-class differential diagnostics of neurodegenerative diseases using random undersampling boosting

Abstract

Differentiating between different types of neurodegenerative diseases is not only crucial in clinical practice when treatment decisions have to be made, but also has a significant potential for the enrichment of clinical trials. The purpose of this study is to develop a classification framework for distinguishing the four most common neurodegenerative diseases, including Alzheimer's disease, frontotemporal lobe degeneration, Dementia with Lewy bodies and vascular dementia, as well as patients with subjective memory complaints. Different biomarkers including features from images (volume features, region-wise grading features) and non-imaging features (CSF measures) were extracted for each subject. In clinical practice, the prevalence of different dementia types is imbalanced, posing challenges for learning an effective classification model. Therefore, we propose the use of the RUSBoost algorithm in order to train classifiers and to handle the class imbalance training problem. Furthermore, a multi-class feature selection method based on sparsity is integrated into the proposed framework to improve the classification performance. It also provides a way for investigating the importance of different features and regions. Using a dataset of 500 subjects, the proposed framework achieved a high accuracy of 75.2% with a balanced accuracy of 69.3% for the five-class classification using ten-fold cross validation, which is significantly better than the results using support vector machine or random forest, demonstrating the feasibility of the proposed framework to support clinical decision making.

Keywords: Dementia; Differential diagnosis; Imbalance learning; MRI; Multi-class feature selection; Neurodegenerative diseases.

Fig. 1

An example of the calculated segmentations of an T1-weighted MR image. The top row presents the original image and the yellow contour illustrates the result of skull stripping. The second row shows the segmentation of 138 regions and the bottom row adds the further segmentation of the white matter region into 130 subregions. (For interpretation of the references to color in this figure legend, the reader is referred to the web version of this article.)

Fig. 2

The average grading maps for each patient group. For each subject, 682 grading features were extracted, including 138 SMC grading features (the first column), 138 AD grading features (the second column), 138 FTLD grading features (the third column), 138 DLB grading features (the fourth column) and 130 VaD grading features (the fifth column). The VaD grading features were extracted in the white matter subregions using FLAIR images. The other grading features were extracted in the grey matter subregions using T1-weighted images.

Fig. 3

Comparison of classification performance using different classifiers. Results were obtained using 100 runs of 10-fold cross validation. The statistical tests using the Mann Whitney U Test were performed between the results using RUSBoost and those using other methods. * means that the results are significantly different from those using RUSBoost with p-value < 0.001.

Fig. 4

Confusion matrix of the classification results using different classifiers.

Fig. 5

Comparison of classification performance using different types of features. RUSBoost was used for training and testing. Results were obtained using 100 runs of 10-fold cross validation. The statistical tests using the Mann Whitney U Test were performed between the results using all features and those using each individual type of features. * means that the results are significantly different from those using all features with p-value < 0.001.

Fig. 6

Confusion matrix of RUSBoost after feature selection using all available features. The values in the right figure are the corresponding standard variation of the values in the confusion matrix.

Fig. 7

The importance of different features in the MNI152 template space. A high value (in red regions) in the maps means that the corresponding feature extracted in that region was selected with a high frequency, indicating that the feature is important for the five-class classification.

Fig. 8

The distributions of the left and right hippocampus volumes for different groups.

Fig. 9

The distributions of VaD grading features in PrCG and IFO of white matter for different groups.