ABSTRACT
Gaussian smoothing (GS) is a spatial low pass filtering method widely used in neuroimaging preprocessing. Full width at half maximum (FWHM) is a common parameter when the imaging data convolved with GS kernel. The convolutional neural networks (CNNs) can be considered as the feature extractor, which is implemented by applying a series of different filters. However, the influence of kernel size of GS for feature extraction remains unclear. In this study, we describe an automatic AD classification algorithm that is built on a pre-trained CNN model, AlexNet for feature extraction and support vector machine (SVM) for classification. The algorithm was trained and tested using the structural Magnetic Resonance Imaging (sMRI) data from Alzheimer's Disease Neuroimaging Initiative (ADNI). The data used in this study include 191 Alzheimer's disease (AD) patients and 103 normal control (NC) subjects. We evaluate the influence of FWHM on classification performance. When FWHM is 0mm, the classification accuracy obtained the highest value for AD and NC, which reached 91.5%, 92.4%, 89.0% for conv3, conv4 and conv5 of AlexNet respectively. The classification accuracy at each layer is relatively low when FWHM is 8mm. The result suggests that the higher smooth value may have a negative effect on feature extraction of CNNs during AD classification.
- Liu, S., Cai, W., Liu, S., Zhang, F., Fulham, M., Feng, D., Kikinis, R. 2015. Multimodal neuroimaging computing: a review of the applications in neuropsychiatric disorders. Brain Informatics. 2, 3 (Sep. 2015), 167--180. DOI= http://dx.doi.org/10.1007/s40708-015-0019-x.Google ScholarCross Ref
- Ruan, Q., D'Onofrio, G., Sancarlo, D., Bao, Z., Greco, A., and Yu, Z. 2016. Potential neuroimaging biomarkers of pathologic brain changes in Mild Cognitive Impairment and Alzheimer's disease: a systematic review. BMC Geriatr. 16, 1 (May. 2016), 104.Google ScholarCross Ref
- Ashburner, J., and Friston, K. J. 2000. Voxel-Based Morphometry-The Methods. Neuroimage. 11, 6 (Jun. 2000), 805--821.Google ScholarCross Ref
- Jones, Derek K., Mark R. Symms, Mara Cercignani, and Robert J. Howard. 2005. The effect of filter size on VBM analyses of DT-MRI data. Neuroimage. 26, 2 (Jun. 2005), 546--554.Google ScholarCross Ref
- Angermueller, C., Pärnamaa, T., Parts, L., and Stegle, O. 2016. Deep learning for computational biology. Mol. Syst. Biol. 12, 7 (Jul. 2016), 878.Google ScholarCross Ref
- Tian, M., Lan, L., Zhang, B.W., and Wu, S.C. Study on the application of deep learning in neuroimaging. China Medical Devices. 31, 12 (Dec. 2016), 4--9.Google Scholar
- Liu, S., Liu, S., Cai, W., Che, H. and Fulham, M. J. 2015. Multimodal neuroimaging feature learning for multiclass diagnosis of Alzheimer's disease. IEEE Transactions on Biomedical Engineering. 62, 4 (Apr. 2015), 1132--1140.Google ScholarCross Ref
- Liu, S., Liu, S., Cai, W., Pujol, S., Kikinis, R., and Feng, D. 2014. Early diagnosis of Alzheimer's disease with deep learning. 2014 IEEE 11th international symposium on biomedical imaging (ISBI). (Apr. 2014), 1015--1018.Google ScholarCross Ref
- Zhang, B.W., Lan, L., and Wu, S.C. Application of deep learning to mild cognitive impairment conversion and classification. Chinese Medical Equipment Journal. 38, 9 (Sep. 2017), 105--111.Google Scholar
- Lan, L., and ZHANG, B.W. 2018. MCI Conversion Prediction Based on Transfer Learning. DEStech Transactions on Computer Science and Engineering(CCNT). 218--222Google Scholar
- Yue, L., Gong, X., Chen, K., Mao, M., Li, J., Nandi, A. K., and Li, M. 2018. Auto-Detection of Alzheimer's Disease Using Deep Convolutional Neural Networks. 2018 14th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD). (Jul. 2018), 228--234.Google ScholarCross Ref
- Weiner, M. W., Veitch, D. P., Aisen, P. S., Beckett, L. A., Cairns, N. J., Green, R. C., and Liu, E. 2013. The Alzheimer's Disease Neuroimaging Initiative: a review of papers published since its inception. Alzheimer's & Dementia. 9, 5 (Sep. 2013), e111-e194.Google ScholarCross Ref
- Busatto, G. F., Garrido, G. E., Almeida, O. P., Castro, C. C., Camargo, C. H., Cid, C. G., and Bottino, C. M. 2003. A voxel-based morphometry study of temporal lobe gray matter reductions in Alzheimer's disease. Neurobiol. Aging. 24, 2 (Mar.-Apr. 2003), 221--231.Google ScholarCross Ref
- Ashburner, J. 2009. Computational anatomy with the SPM software. Magn. Reson. Imaging. 27, 8 (Oct. 2009), 1163--1174.Google ScholarCross Ref
- Ashburner, J. 2007. A fast diffeomorphic image registration algorithm. Neuroimage. 38, 1 (Oct. 2007), 95--113.Google ScholarCross Ref
- Wolk, D. A., Das, S. R., Mueller, S. G., Weiner, M. W., Yushkevich, P. A., and Initiative, A. s. D. N. 2017. Medial temporal lobe subregional morphometry using high resolution MRI in Alzheimer's disease. Neurobiol. aging. 49 (Jan. 2017), 204--213.Google Scholar
- Zhang, B.W., Lan, L., Sun S., and Wu, S.C. Alzheimer's disease diagnosis model based on deep convolutional neural network. Chinese Medical Equipment Journal. 40, 1 (Jan. 2019), 5--9.Google Scholar
- Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., and Darrell, T. 2014. Caffe: Convolutional architecture for fast feature embedding. The 22nd ACM international conference on Multimedia (Orlando, Florida, USA, November 03-07, 2014). ACM. New York, NY, 675--678.Google ScholarDigital Library
- Krizhevsky, A., Sutskever, I., and Hinton, G. E. 2012. Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems. 25, 2 (Jan. 2012), 1079--1105.Google Scholar
- Hotelling, H. 1933. Analysis of a complex of statistical variables into principal components. Journal of educational psychology. 24, 6, 417--441.Google ScholarCross Ref
- Steyerberg, E. W., Eijkemans, M. J., and Habbema, J. D. F. 1999. Stepwise selection in small data sets: a simulation study of bias in logistic regression analysis. Journal of clinical epidemiology. 52, 10 (Oct. 1999), 935--942.Google ScholarCross Ref
- Chang, C. C., and Lin, C. J. 2011. LIBSVM: A library for support vector machines. ACM transactions on intelligent systems and technology (TIST), ACM Trans. Intell. Syst. Technol. 2, 3, Article 27 (April 2011), 27.Google ScholarDigital Library
Index Terms
- The Effect of Smoothing Filter on CNN based AD Classification
Recommendations
Classification of sMRI for Alzheimer's disease Diagnosis with CNN: Single Siamese Networks with 2D+? Approach and Fusion on ADNI
ICMR '17: Proceedings of the 2017 ACM on International Conference on Multimedia RetrievalThe methods of Content-Based visual information indexing and retrieval penetrate into Healthcare and become popular in Computer-Aided Diagnostics. The PhD research we have started 13 months ago is devoted to the multimodal classification of MRI brain ...
Efficient deep CNN-based gender classification using Iris wavelet scattering
AbstractRecognition of gender from iris images can be considered a texture classification task in which a classification model discriminates iris textures of male and female subjects. Although many researchers have proposed efficient iris texture ...
A CNN based framework for classification of Alzheimer’s disease
AbstractIn the current decade, advances in health care are attracting widespread interest due to their contributions to people longer surviving and fitter lives. Alzheimer’s disease (AD) is the commonest neurodegenerative and dementing disease. The ...
Comments