Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2021 Sep 24:15:748689.
doi: 10.3389/fnins.2021.748689. eCollection 2021.

Interpretable Recognition for Dementia Using Brain Images

Xinjian Song  1 , Feng Gu  2 , Xiude Wang  2 , Songhua Ma  3 , Li Wang  4   5   6
Affiliations

Interpretable Recognition for Dementia Using Brain Images

Xinjian Song et al. Front Neurosci. .

Abstract

Machine learning-based models are widely used for neuroimage-based dementia recognition and achieve great success. However, most models omit the interpretability that is a very important factor regarding the confidence of a model. Takagi-Sugeno-Kang (TSK) fuzzy classifiers as the high interpretability and promising classification performance have widely used in many scenarios. TSK fuzzy classifier can generate interpretable fuzzy rules showing the reasoning process. However, when facing high-dimensional data, the antecedent become complex which may reduce the interpretability. In this study, to keep the antecedent of fuzzy rule concise, we introduce the subspace clustering technique and use it for antecedent learning. Experimental results show that the used model can generate promising recognition performance as well as concise fuzzy rules.

Keywords: Alzheimer’s disease; TSK fuzzy systems; brain images; dementia; interpretability.

PubMed Disclaimer

Conflict of interest statement

The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.

Figures

FIGURE 1
FIGURE 1
Data preprocessing pipeline of positron emission tomography (PET) images.
FIGURE 2
FIGURE 2
Learning framework of Takagi–Sugeno–Kang (TSK) fuzzy classifiers.
FIGURE 3
FIGURE 3
Activation of features by the subspace clustering under different thresholds: (A) 0.03, (B) 0.06, (C) 0.09, and (D) 0.2.
FIGURE 4
FIGURE 4
Model complexity and accuracy under different thresholds.
FIGURE 5
FIGURE 5
Linguistic meaning of activated features of each rule.
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

References

    1. Bansal D., Chhikara R., Khanna K., Gupta P. (2018). Comparative analysis of various machine learning algorithms for detecting dementia. Procedia Comput. Sci. 132 1497–1502. 10.1016/j.procs.2018.05.102 - DOI
    1. Chen R., Herskovits E. H. (2010). Machine-learning techniques for building a diagnostic model for very mild dementia. Neuroimage 52 234–244. 10.1016/j.neuroimage.2010.03.084 - DOI - PMC - PubMed
    1. Cuingnet R., Gerardin E., Tessieras J., Auzias G., Lehéricy S., Habert M. O., et al. (2011). Automatic classification of patients with Alzheimer’s disease from structural MRI: a comparison of ten methods using the ADNI database. Neuroimage 56 766–781. 10.1016/j.neuroimage.2010.06.013 - DOI - PubMed
    1. Frigui H., Nasraoui O. (2004). Unsupervised learning of prototypes and attribute weights. Pattern Recognit. 37 567–581. 10.1016/j.patcog.2003.08.002 - DOI
    1. Jiang K., Tang J., Wang Y., Qiu C., Zhang Y., Lin C. (2020b). EEG feature selection via stacked deep embedded regression with joint sparsity. Front. Neurosci. 14:829. 10.3389/fnins.2020.00829 - DOI - PMC - PubMed

LinkOut - more resources