Author : Arpit Chaudhary 1
Date of Publication :25th April 2018
Abstract: In the recent years there have been a number of studies that applied deep learn-ing algorithms to neuroimaging data. Pipelines used in those studies mostly require multiple processing steps for feature extraction, although modern ad-vancements in deep learning for image classi cation can provide a powerful framework for automatic feature generation and more straightforward analy-sis. In this report, we show how similar performance can be achieved skipping these feature extraction steps with the 3D convolutional neural network archi-tectures. An accuracy of 84% has been achieved with a precision of 95%. The performance of the proposed approach outperforms various statistical machine learning based approaches such as SVM, Random Forest, Ada Boost etc.
Reference :
-
- http://www.oasis-brains.org/
- Siqi Liu, Sidong Liu, Weidong Cai, Sonia Pujol, Ron Kikinis, and Dagan Feng, Early diagnosis of Alzheimer's disease with deep learning," 2014 IEEE 11th International Symposium on Biomedical Imaging (ISBI), pp. 1015{1018, 2014.
- K. Simonyan and A. Zisserman, Very deep convolutional networks for large-scale image recognition," CoRR, vol. abs/1409.1556, 2014.
- Tom Brosch and Roger Tam, Manifold learning of brain mris by deep learning," International Conference on Medical Image Computing and Computer-Assisted Intervention, vol. 16, no. Pt 2, pp. 633{640, 2013.
- Heung Il Suk, Seong Whan Lee, and Dinggang Shen, Hierarchical feature representation and multimodal fusion with deep learning for AD/MCI diagnosis," NeuroImage, vol. 101, pp. 569{582, 2014.