Chapter title |
Stability-Weighted Matrix Completion of Incomplete Multi-modal Data for Disease Diagnosis
|
---|---|
Chapter number | 11 |
Book title |
Medical Image Computing and Computer-Assisted Intervention – MICCAI 2016
|
Published in |
Lecture notes in computer science, October 2016
|
DOI | 10.1007/978-3-319-46723-8_11 |
Pubmed ID | |
Book ISBNs |
978-3-31-946722-1, 978-3-31-946723-8
|
Authors |
Thung, Kim-Han, Adeli, Ehsan, Yap, Pew-Thian, Shen, Dinggang, Kim-Han Thung, Ehsan Adeli, Pew-Thian Yap, Dinggang Shen |
Abstract |
Effective utilization of heterogeneous multi-modal data for Alzheimer's Disease (AD) diagnosis and prognosis has always been hampered by incomplete data. One method to deal with this is low-rank matrix completion (LRMC), which simultaneous imputes missing data features and target values of interest. Although LRMC yields reasonable results, it implicitly weights features from all the modalities equally, ignoring the differences in discriminative power of features from different modalities. In this paper, we propose stability-weighted LRMC (swLRMC), an LRMC improvement that weights features and modalities according to their importance and reliability. We introduce a method, called stability weighting, to utilize subsampling techniques and outcomes from a range of hyper-parameters of sparse feature learning to obtain a stable set of weights. Incorporating these weights into LRMC, swLRMC can better account for differences in features and modalities for improving diagnosis. Experimental results confirm that the proposed method outperforms the conventional LRMC, feature-selection based LRMC, and other state-of-the-art methods. |
Mendeley readers
Geographical breakdown
Country | Count | As % |
---|---|---|
Unknown | 13 | 100% |
Demographic breakdown
Readers by professional status | Count | As % |
---|---|---|
Student > Ph. D. Student | 4 | 31% |
Researcher | 2 | 15% |
Student > Master | 1 | 8% |
Other | 1 | 8% |
Professor > Associate Professor | 1 | 8% |
Other | 1 | 8% |
Unknown | 3 | 23% |
Readers by discipline | Count | As % |
---|---|---|
Computer Science | 3 | 23% |
Medicine and Dentistry | 2 | 15% |
Engineering | 2 | 15% |
Neuroscience | 1 | 8% |
Psychology | 1 | 8% |
Other | 0 | 0% |
Unknown | 4 | 31% |