On the design of convolutional neural networks for automatic detection of Alzheimer’s disease

Sheng Liu, Chhavi Yadav, Carlos Fernandez-Granda, Narges Razavian
Proceedings of the Machine Learning for Health NeurIPS Workshop, PMLR 116:184-201, 2020.

Abstract

Early detection is a crucial goal in the study of Alzheimer’s Disease (AD). In this work, we describe several techniques to boost the performance of 3D convolutional neural networks trained to detect AD using structural brain MRI scans. Specifically, we provide evidence that (1) instance normalization outperforms batch normalization, (2) early spatial downsampling negatively affects performance, (3) widening the model brings consistent gains while increasing the depth does not, and (4) incorporating age information yields moderate improvement. Together, these insights yield an increment of approximately 14{%} in test accuracy over existing models when distinguishing between patients with AD, mild cognitive impairment, and controls in the ADNI dataset. Similar performance is achieved on an independent dataset.

Cite this Paper

BibTeX
@InProceedings{pmlr-v116-liu20a, title = {{On the design of convolutional neural networks for automatic detection of Alzheimer’s disease}}, author = {Liu, Sheng and Yadav, Chhavi and Fernandez-Granda, Carlos and Razavian, Narges}, booktitle = {Proceedings of the Machine Learning for Health NeurIPS Workshop}, pages = {184--201}, year = {2020}, editor = {Dalca, Adrian V. and McDermott, Matthew B.A. and Alsentzer, Emily and Finlayson, Samuel G. and Oberst, Michael and Falck, Fabian and Beaulieu-Jones, Brett}, volume = {116}, series = {Proceedings of Machine Learning Research}, month = {13 Dec}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v116/liu20a/liu20a.pdf}, url = {https://proceedings.mlr.press/v116/liu20a.html}, abstract = {Early detection is a crucial goal in the study of Alzheimer’s Disease (AD). In this work, we describe several techniques to boost the performance of 3D convolutional neural networks trained to detect AD using structural brain MRI scans. Specifically, we provide evidence that (1) instance normalization outperforms batch normalization, (2) early spatial downsampling negatively affects performance, (3) widening the model brings consistent gains while increasing the depth does not, and (4) incorporating age information yields moderate improvement. Together, these insights yield an increment of approximately 14{%} in test accuracy over existing models when distinguishing between patients with AD, mild cognitive impairment, and controls in the ADNI dataset. Similar performance is achieved on an independent dataset.} }
Endnote
%0 Conference Paper %T On the design of convolutional neural networks for automatic detection of Alzheimer’s disease %A Sheng Liu %A Chhavi Yadav %A Carlos Fernandez-Granda %A Narges Razavian %B Proceedings of the Machine Learning for Health NeurIPS Workshop %C Proceedings of Machine Learning Research %D 2020 %E Adrian V. Dalca %E Matthew B.A. McDermott %E Emily Alsentzer %E Samuel G. Finlayson %E Michael Oberst %E Fabian Falck %E Brett Beaulieu-Jones %F pmlr-v116-liu20a %I PMLR %P 184--201 %U https://proceedings.mlr.press/v116/liu20a.html %V 116 %X Early detection is a crucial goal in the study of Alzheimer’s Disease (AD). In this work, we describe several techniques to boost the performance of 3D convolutional neural networks trained to detect AD using structural brain MRI scans. Specifically, we provide evidence that (1) instance normalization outperforms batch normalization, (2) early spatial downsampling negatively affects performance, (3) widening the model brings consistent gains while increasing the depth does not, and (4) incorporating age information yields moderate improvement. Together, these insights yield an increment of approximately 14{%} in test accuracy over existing models when distinguishing between patients with AD, mild cognitive impairment, and controls in the ADNI dataset. Similar performance is achieved on an independent dataset.
APA
Liu, S., Yadav, C., Fernandez-Granda, C. & Razavian, N.. (2020). On the design of convolutional neural networks for automatic detection of Alzheimer’s disease. Proceedings of the Machine Learning for Health NeurIPS Workshop, in Proceedings of Machine Learning Research 116:184-201 Available from https://proceedings.mlr.press/v116/liu20a.html.

Related Material