Natural Image Bases to Represent Neuroimaging Data

Ashish Gupta, Murat Ayhan, Anthony Maida
Proceedings of the 30th International Conference on Machine Learning, PMLR 28(3):987-994, 2013.

Abstract

Visual inspection of neuroimagery is susceptible to human eye limitations. Computerized methods have been shown to be equally or more effective than human clinicians in diagnosing dementia from neuroimages. Nevertheless, much of the work involves the use of domain expertise to extract hand-crafted features. The key technique in this paper is the use of cross-domain features to represent MRI data. We used a sparse autoencoder to learn a set of bases from natural images and then applied convolution to extract features from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) dataset.Using this new representation, we classify MRI instances into three categories: Alzheimer’s Disease (AD), Mild Cognitive Impairment (MCI) and Healthy Control (HC).Our approach, in spite of being very simple, achieved high classification performance, which is competitive with or better than other approaches.

Cite this Paper

BibTeX
@InProceedings{pmlr-v28-gupta13b, title = {Natural Image Bases to Represent Neuroimaging Data}, author = {Gupta, Ashish and Ayhan, Murat and Maida, Anthony}, booktitle = {Proceedings of the 30th International Conference on Machine Learning}, pages = {987--994}, year = {2013}, editor = {Dasgupta, Sanjoy and McAllester, David}, volume = {28}, number = {3}, series = {Proceedings of Machine Learning Research}, address = {Atlanta, Georgia, USA}, month = {17--19 Jun}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v28/gupta13b.pdf}, url = {https://proceedings.mlr.press/v28/gupta13b.html}, abstract = {Visual inspection of neuroimagery is susceptible to human eye limitations. Computerized methods have been shown to be equally or more effective than human clinicians in diagnosing dementia from neuroimages. Nevertheless, much of the work involves the use of domain expertise to extract hand-crafted features. The key technique in this paper is the use of cross-domain features to represent MRI data. We used a sparse autoencoder to learn a set of bases from natural images and then applied convolution to extract features from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) dataset.Using this new representation, we classify MRI instances into three categories: Alzheimer’s Disease (AD), Mild Cognitive Impairment (MCI) and Healthy Control (HC).Our approach, in spite of being very simple, achieved high classification performance, which is competitive with or better than other approaches.} }
Endnote
%0 Conference Paper %T Natural Image Bases to Represent Neuroimaging Data %A Ashish Gupta %A Murat Ayhan %A Anthony Maida %B Proceedings of the 30th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2013 %E Sanjoy Dasgupta %E David McAllester %F pmlr-v28-gupta13b %I PMLR %P 987--994 %U https://proceedings.mlr.press/v28/gupta13b.html %V 28 %N 3 %X Visual inspection of neuroimagery is susceptible to human eye limitations. Computerized methods have been shown to be equally or more effective than human clinicians in diagnosing dementia from neuroimages. Nevertheless, much of the work involves the use of domain expertise to extract hand-crafted features. The key technique in this paper is the use of cross-domain features to represent MRI data. We used a sparse autoencoder to learn a set of bases from natural images and then applied convolution to extract features from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) dataset.Using this new representation, we classify MRI instances into three categories: Alzheimer’s Disease (AD), Mild Cognitive Impairment (MCI) and Healthy Control (HC).Our approach, in spite of being very simple, achieved high classification performance, which is competitive with or better than other approaches.
RIS
TY - CPAPER TI - Natural Image Bases to Represent Neuroimaging Data AU - Ashish Gupta AU - Murat Ayhan AU - Anthony Maida BT - Proceedings of the 30th International Conference on Machine Learning DA - 2013/05/26 ED - Sanjoy Dasgupta ED - David McAllester ID - pmlr-v28-gupta13b PB - PMLR DP - Proceedings of Machine Learning Research VL - 28 IS - 3 SP - 987 EP - 994 L1 - http://proceedings.mlr.press/v28/gupta13b.pdf UR - https://proceedings.mlr.press/v28/gupta13b.html AB - Visual inspection of neuroimagery is susceptible to human eye limitations. Computerized methods have been shown to be equally or more effective than human clinicians in diagnosing dementia from neuroimages. Nevertheless, much of the work involves the use of domain expertise to extract hand-crafted features. The key technique in this paper is the use of cross-domain features to represent MRI data. We used a sparse autoencoder to learn a set of bases from natural images and then applied convolution to extract features from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) dataset.Using this new representation, we classify MRI instances into three categories: Alzheimer’s Disease (AD), Mild Cognitive Impairment (MCI) and Healthy Control (HC).Our approach, in spite of being very simple, achieved high classification performance, which is competitive with or better than other approaches. ER -
APA
Gupta, A., Ayhan, M. & Maida, A.. (2013). Natural Image Bases to Represent Neuroimaging Data. Proceedings of the 30th International Conference on Machine Learning, in Proceedings of Machine Learning Research 28(3):987-994 Available from https://proceedings.mlr.press/v28/gupta13b.html.

Related Material