Shuomei Chen
ABSTRACT
Research on Alzheimer's Disease auxiliary diagnosis based on deep learning has been receiving more and more attention. However, in existing AD classification research based on T1-weighted structural Magnetic Resonance Imaging, the influence of different MRI scanning modes (i.e., 1.5T and 3T) of ADNI database is not well considered. In addition, there are few attempts to use the Voxel-Based Morphometry-Diffeomorphic Anatomical Registration Through Exponential Lie algebra method for data preprocessing in AD classification experiments. Therefore, the VBM-DARTEL method is used to preprocess the sMRI data. Then, based on different scanning methods, the preprocessed ADNI subsets are further divided according to three data partitioning methods (subject, MRI and visit-history), on which five representative convolutional neural networks are adopted for classification and evaluation. The experimental results demonstrate that the overall classification performance on both 1.5T and 3T datasets is visit-history>MRI>subject. Meanwhile, the best accuracy rates 95.87% and 97.15% are achieved by GoogLeNet on 1.5T and 3T datasets in visit-history level. In addition, preprocessing operation improves the accuracy rate of AD classification to a certain extent and the performance of the five CNN models is equivalent in preprocessed datasets, while there is obviously accuracy difference on none-preprocessed datasets.
- Marie Chupin, Emilie Gerardin, Remi Cuingnet, C Boutet., Louis Lemieux, Stéphane Lehéricy, Habib Benali, Line Garnero and Olivier Colliot. 2009. Fully Automatic Hippocampus Segmentation and Classification in Alzheimer's Disease and Mild Cognitive Impairment Applied on Data From ADNI. Hippocampus 19, 6(May 2009), 579-587. https://doi.org/10.1002/hipo.20626Google Scholar
- Daoqiang, Zhang, Yaping Wang, Luping Zhou, Hong Yuan and Dinggang Shen. 2011. Multimodal classification of Alzheimer's disease and mild cognitive impairment. NeuroImage 55, 3(April 2011), 856-867. https://linkinghub.elsevier.com/retrieve/pii/S1053811911000267Google Scholar
- H Braak, and E Braak. 1991. Neuropathological stageing of Alzheimer-related changes. Acta neuropathologica 82, 4(September 1991), 239-259. https://link.springer.com/article/10.1007/BF00308809Google Scholar
- Rémi Cuingnet, Emilie Gerardin, Jérôme Tessieras, Guillaume Auzias, Stéphane Lehéricy, Marie-Odile Habert, Marie Chupin, Habib Benali and Olivier Colliot. 2011. Automatic classification of patients with Alzheimer's disease from structural MRI: a comparison of ten methods using the ADNI database. NeuroImage 56, 2(May 2011), 766-781. https://linkinghub.elsevier.com/retrieve/pii/S1053811910008578Google Scholar
- Hakim C. Achterberg, Fedde van der Lijn, Tom den Heijer, Meike W Vernooij, M Arfan Ikram, W.J. Niessen and Marleen de Bruijne. 2014. "Hippocampal shape is predictive for the development of dementia in a normal, elderly population." Human Brain Mapping 35, 5 (May 2014), 2359-2371. https://www.onacademic.com/detail/journal_1000035985004710_dae9.htmlGoogle Scholar
- Elaheh Moradi, Jussi Tohka, and Christian Gaser. 2014. Semi-supervised learning in MCI-to-ad conversion prediction — When is unlabeled data useful?. 2014 International Workshop on Pattern Recognition in Neuroimaging, Tubingen, 1-4. https://www.researchgate.net/publication/269294016Google ScholarCross Ref
- Heung-Il Suk, Seong W. Lee and Dinggang Shen. 2014. Hierarchical feature representation and multimodal fusion with deep learning for AD/MCI diagnosis. NeuroImage 101 (June 2014), 569-582. https://linkinghub.elsevier.com/retrieve/pii/S1053811914005540Google Scholar
- Suk, Heung-Il, and Dinggang, Shen. 2014. Deep Learning-Based Feature Representation for AD/MCI Classification. International Conference on Medical Image Computing and Computer-Assisted Intervention, Springer, Heidelberg. 583-590. https://link.springer.com/chapter/10.1007%2F978-3-642-40763-5_72Google Scholar
- Marcia Hon and Naimul M. Khan. 2017. Towards Alzheimer's disease classification through transfer learning. 2017 IEEE International conference on bioinformatics and biomedicine (BIBM). 1166-1169. https://arxiv.org/abs/1711.11117Google Scholar
- N Jain, A Aggarwal, Nikita Jain and Mohd Noordian. 2019. Convolutional neural network based Alzheimer's disease classification from magnetic resonansce brain images. Cognitive Systems Research (January 2019) 57, 147-159. https://www.onacademic.com/detail/journal_1000041583880799_e425.htmlGoogle Scholar
- Saman Sarraf, Ghassem Tofighi. 2016. Classification of alzheimer's disease structural MRI data by deep learning convolutional neural networks. arXiv preprint arXiv:1607.06583. https://arxiv.org/abs/1603.08631Google Scholar
- Naimul M. Khan, Marcia Hon, and Nabila Abraham. 2019. Transfer Learning with Intelligent Training Data Selection for Prediction of Alzheimer's Disease. IEEE Access 7, (June 2019), 72726-72735. https://ieeexplore.ieee.org/document/8727911Google Scholar
- Yi R. Fung, Ziqiang Guan, Ritesh Kumar, Joie Y. Wu and Madalina Fiterau. 2019. Alzheimer's Disease Brain MRI Classification: Challenges and Insights. arXiv preprint arXiv:1906.04231. https://arxiv.org/abs/1906.04231v1Google Scholar
- Sergey Korolev, Amir Safiullin, and Mikhail Belyaev. 2017. Residual and plain convolutional neural networks for 3d brain mri classification. IEEE 14th International Symposium on Biomedical Imaging (ISBI). 835-838. https://arxiv.org/abs/1701.06643Google ScholarCross Ref
- Ehsan Hosseini asl, Robert S Keynton and Ayman S El-Baz. 2016. Alzheimer's disease diagnostics by adaptation of 3D convolutional network. IEEE International Conference on Image Processing (ICIP). 126-130. https://ieeexplore.ieee.org/document/7532332Google Scholar
- Karl Bäckström, Mahmood Nazari, Irene Y. H. Gu and Asgeir Store Jakola. 2018. An efficient 3D deep convolutional network for Alzheimer's disease diagnosis using MR images. IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018). 149-153. https://ieeexplore.ieee.org/document/8363543Google Scholar
- Alzheimer's Disease Neuroimaging Initiative, http://adni.loni.usc.edu/Google Scholar
- Yann Lecun, Leon Bottou, Y. Bengio and Patrick Haffner. 1998. Gradient-based learning applied to document recognition. Proceedings of the IEEE 86, 11(December 1998), 2278-2324. https://www.researchgate.net/publication/2985446_Gradient-Based_Learning_Applied_to_Document_RecognitionGoogle Scholar
- Alex Krizhevsky, Ilya Sutskever and Geoffrey E. Hinton. 2012. Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems. 1097-1105. https://dl.acm.org/doi/10.5555/2999134.2999257Google ScholarDigital Library
- Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. International Conference on Learning Representations. http://arxiv.org/abs/1409.1556Google Scholar
- Christian Szegedy, Wei Liu, Yangqing Jia, Pierre Sermanet, Scott Reed, Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke and Andrew Rabinovich. 2015. Going deeper with convolutions. Proceedings of the IEEE conference on computer vision and pattern recognition. 1-9. https://ieeexplore.ieee.org/document/7298594Google ScholarCross Ref
- Kaiming He, Xiangyu Zhang, Shaoqing Ren and Jian Sun. 2016. Deep residual learning for image recognition. Proceedings of the IEEE conference on computer vision and pattern recognition. 770-778. https://www.researchgate.net/publication/307964703Google ScholarCross Ref
Recommendations
Alzheimer's disease classification using capsule networks on structural MRI
ICBSP '20: Proceedings of the 2020 5th International Conference on Biomedical Imaging, Signal ProcessingAlzheimer's disease (AD) is the most prevalent cause of dementia among elderly people. This paper presents a deep learning model based on capsule networks for the classification of AD and Normal Control (NC) using MRI images taken from the ADNI dataset. ...
Deep sequence modelling for Alzheimer's disease detection using MRI
Abstract BackgroundAlzheimer's disease (AD) is one of the deadliest diseases in developed countries. Treatments following early AD detection can significantly delay institutionalisation and extend patients' independence. There has ...
Highlights- Multiple deep sequence-based models were proposed for AD detection.
- Deep ...
Fast Training of a Convolutional Neural Network for Brain MRI Classification
ACM SE '19: Proceedings of the 2019 ACM Southeast ConferenceThe increase in AD population calls for an automated and accurate method for efficiently diagnosing AD through MRI, preferably at the stage of Early MCI (EMCI). Graphics Processing Unit (GPU), ReLU, Dropout contribute to better performance of Artificial ...
Comments