Abstract
In this work, we are interested in predicting the diagnostic statuses of potentially neurodegenerated patients using feature values derived from multi-modality neuroimaging data and biological data, which might be incomplete. Collecting the feature values into a matrix, with each row containing a feature vector of a sample, we propose a framework to predict the corresponding associated multiple target outputs (e.g., diagnosis label and clinical scores) from this feature matrix by performing matrix shrinkage following matrix completion. Specifically, we first combine the feature and target output matrices into a large matrix and then partition this large incomplete matrix into smaller submatrices, each consisting of samples with complete feature values (corresponding to a certain combination of modalities) and target outputs. Treating each target output as the outcome of a prediction task, we apply a 2-step multi-task learning algorithm to select the most discriminative features and samples in each submatrix. Features and samples that are not selected in any of the submatrices are discarded, resulting in a shrunk version of the original large matrix. The missing feature values and unknown target outputs of the shrunk matrix is then completed simultaneously. Experimental results using the ADNI dataset indicate that our proposed framework achieves higher classification accuracy at a greater speed when compared with conventional imputation-based classification methods and also yields competitive performance when compared with the state-of-the-art methods.
| Original language | English |
|---|---|
| Pages (from-to) | 386-400 |
| Number of pages | 15 |
| Journal | NeuroImage |
| Volume | 91 |
| DOIs | |
| Publication status | Published - 2014 May 1 |
Fingerprint
Keywords
- Classification
- Data imputation
- Matrix completion
- Multi-task learning
ASJC Scopus subject areas
- Cognitive Neuroscience
- Neurology
Cite this
Neurodegenerative disease diagnosis using incomplete multi-modality data via matrix shrinkage and completion. / Thung, Kim Han; Wee, Chong Yaw; Yap, Pew Thian; Shen, Dinggang.
In: NeuroImage, Vol. 91, 01.05.2014, p. 386-400.Research output: Contribution to journal › Article
}
TY - JOUR
T1 - Neurodegenerative disease diagnosis using incomplete multi-modality data via matrix shrinkage and completion
AU - Thung, Kim Han
AU - Wee, Chong Yaw
AU - Yap, Pew Thian
AU - Shen, Dinggang
PY - 2014/5/1
Y1 - 2014/5/1
N2 - In this work, we are interested in predicting the diagnostic statuses of potentially neurodegenerated patients using feature values derived from multi-modality neuroimaging data and biological data, which might be incomplete. Collecting the feature values into a matrix, with each row containing a feature vector of a sample, we propose a framework to predict the corresponding associated multiple target outputs (e.g., diagnosis label and clinical scores) from this feature matrix by performing matrix shrinkage following matrix completion. Specifically, we first combine the feature and target output matrices into a large matrix and then partition this large incomplete matrix into smaller submatrices, each consisting of samples with complete feature values (corresponding to a certain combination of modalities) and target outputs. Treating each target output as the outcome of a prediction task, we apply a 2-step multi-task learning algorithm to select the most discriminative features and samples in each submatrix. Features and samples that are not selected in any of the submatrices are discarded, resulting in a shrunk version of the original large matrix. The missing feature values and unknown target outputs of the shrunk matrix is then completed simultaneously. Experimental results using the ADNI dataset indicate that our proposed framework achieves higher classification accuracy at a greater speed when compared with conventional imputation-based classification methods and also yields competitive performance when compared with the state-of-the-art methods.
AB - In this work, we are interested in predicting the diagnostic statuses of potentially neurodegenerated patients using feature values derived from multi-modality neuroimaging data and biological data, which might be incomplete. Collecting the feature values into a matrix, with each row containing a feature vector of a sample, we propose a framework to predict the corresponding associated multiple target outputs (e.g., diagnosis label and clinical scores) from this feature matrix by performing matrix shrinkage following matrix completion. Specifically, we first combine the feature and target output matrices into a large matrix and then partition this large incomplete matrix into smaller submatrices, each consisting of samples with complete feature values (corresponding to a certain combination of modalities) and target outputs. Treating each target output as the outcome of a prediction task, we apply a 2-step multi-task learning algorithm to select the most discriminative features and samples in each submatrix. Features and samples that are not selected in any of the submatrices are discarded, resulting in a shrunk version of the original large matrix. The missing feature values and unknown target outputs of the shrunk matrix is then completed simultaneously. Experimental results using the ADNI dataset indicate that our proposed framework achieves higher classification accuracy at a greater speed when compared with conventional imputation-based classification methods and also yields competitive performance when compared with the state-of-the-art methods.
KW - Classification
KW - Data imputation
KW - Matrix completion
KW - Multi-task learning
UR - http://www.scopus.com/inward/record.url?scp=84896353646&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84896353646&partnerID=8YFLogxK
U2 - 10.1016/j.neuroimage.2014.01.033
DO - 10.1016/j.neuroimage.2014.01.033
M3 - Article
C2 - 24480301
AN - SCOPUS:84896353646
VL - 91
SP - 386
EP - 400
JO - NeuroImage
JF - NeuroImage
SN - 1053-8119
ER -