Abstract
In this paper, we propose a novel method for MRI-based AD/MCI diagnosis that systematically integrates voxel-based, region-based, and patch-based approaches in a unified framework. Specifically, we parcellate a brain into predefined regions by using anatomical knowledge, i.e., template, and find complex nonlinear relations among voxels, whose intensity denotes the volumetric measure in our case, within each region. Unlike the existing methods that mostly use a cubical or rectangular shape, we regard the anatomical shape of regions as atypical forms of patches. Using the complex nonlinear relations among voxels in each region learned by deep neural networks, we extract a regional abnormality representation. We then make a final clinical decision by integrating the regional abnormality representations over a whole brain. It is noteworthy that the regional abnormality representations allow us to interpret and understand the symptomatic observations of a subject with AD or MCI by mapping and visualizing them in a brain space individually. We validated the efficacy of our method in experiments with baseline MRI dataset in the ADNI cohort by achieving promising performances in three binary classification tasks.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
- 2.
Available at ‘http://mipav.cit.nih.gov/clickwrap.php’.
- 3.
Available at ‘http://fsl.fmrib.ox.ac.uk/fsl/fslwiki/’.
- 4.
As for the cardinality of a voxel set \(\left| \mathbb {V}^{r}_{i}\right| \), we empirically determined and set it equal to all the sets. In our experiments, we set 200.
- 5.
Since the output probabilities in deep neural networks sum to one, it is enough to consider only one value in binary classification.
- 6.
In our exhaustive experiments, we varied this value in \(\left\{ 100,200,300,400\right\} \) and obtained low performance with 100 but reasonably higher performance with the other values. Thus, by concerning computational complexity, we set the lowest value, i.e., 200, at the end.
- 7.
- 8.
References
Bengio, Y.: Learning deep architectures for AI. Found. \(\text{Trends}{\textregistered }\) Mach. Learn. 2(1), 1–127 (2009)
Davatzikos, C., Genc, A., Xu, D., Resnick, S.M.: Voxel-based morphometry using the RAVENS maps: methods and validation using simulated longitudinal atrophy. NeuroImage 14(6), 1361–1369 (2001)
Fan, Y., Shen, D., Gur, R.C., Gur, R.E., Davatzikos, C.: Compare: classification of morphological patterns using adaptive regional elements. IEEE Trans. Med. Imaging 26(1), 93–105 (2007)
Kabani, N.J.: 3D anatomical atlas of the human brain. NeuroImage 7, P-0717 (1998)
Liu, M., Zhang, D., Shen, D.: Hierarchical fusion of features and classifier decisions for Alzheimer’s disease diagnosis. Hum. Brain Mapp. 35(4), 1305–1319 (2014)
Liu, S., et al.: Multimodal neuroimaging feature learning for multiclass diagnosis of Alzheimer’s disease. IEEE Trans. Biomed. Eng. 62(4), 1132–1140 (2015)
Möller, C., et al.: Alzheimer disease and behavioral variant frontotemporal dementia: automatic classification based on cortical atrophy for single-subject diagnosis. Radiology 279(3), 838–848 (2016)
Rathore, S., Habes, M., Iftikhar, M.A., Shacklett, A., Davatzikos, C.: A review on neuroimaging-based classification studies and associated feature extraction methods for Alzheimer’s disease and its prodromal stages. NeuroImage 155, 530–548 (2017)
Suk, H.I., Lee, S.W., Shen, D., Initiative, A.D.N., et al.: Hierarchical feature representation and multimodal fusion with deep learning for AD/MCI diagnosis. NeuroImage 101, 569–582 (2014)
Tong, T., Wolz, R., Gao, Q., Guerrero, R., Hajnal, J.V., Rueckert, D., et al.: Multiple instance learning for classification of dementia in brain MRI. Med. Image Anal. 18(5), 808–818 (2014)
Vincent, P., Larochelle, H., Lajoie, I., Bengio, Y., Manzagol, P.A.: Stacked denoising autoencoders: learning useful representations in a deep network with a local denoising criterion. J. Mach. Learn. Res. 11(Dec), 3371–3408 (2010)
Ward, A., Tardiff, S., Dye, C., Arrighi, H.M.: Rate of conversion from prodromal Alzheimer’s disease to Alzheimer’s dementia: a systematic review of the literature. Dement. Geriatric Cognit. Disorders Extra 3(1), 320–332 (2013)
Acknowledgement
This work was partially supported by Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Science, ICT & Future Planning (NRF-2015R1C1A1A01052216); and also by the Bio & Medical Technology Development Program of the NRF funded by the Korean government, MSIP (2016941946).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Switzerland AG
About this paper
Cite this paper
Choi, JS., Lee, E., Suk, HI. (2018). Regional Abnormality Representation Learning in Structural MRI for AD/MCI Diagnosis. In: Shi, Y., Suk, HI., Liu, M. (eds) Machine Learning in Medical Imaging. MLMI 2018. Lecture Notes in Computer Science(), vol 11046. Springer, Cham. https://doi.org/10.1007/978-3-030-00919-9_8
Download citation
DOI: https://doi.org/10.1007/978-3-030-00919-9_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-00918-2
Online ISBN: 978-3-030-00919-9
eBook Packages: Computer ScienceComputer Science (R0)