Chapter title |
A Hybrid of Deep Network and Hidden Markov Model for MCI Identification with Resting-State fMRI.
|
---|---|
Chapter number | 70 |
Book title |
Medical Image Computing and Computer-Assisted Intervention -- MICCAI 2015
|
Published in |
Lecture notes in computer science, November 2015
|
DOI | 10.1007/978-3-319-24553-9_70 |
Pubmed ID | |
Book ISBNs |
978-3-31-924552-2, 978-3-31-924553-9
|
Authors |
Heung-Il Suk, Seong-Whan Lee, Dinggang Shen |
Editors |
Nassir Navab, Joachim Hornegger, William M. Wells, Alejandro F. Frangi |
Abstract |
In this paper, we propose a novel method for modelling functional dynamics in resting-state fMRI (rs-fMRI) for Mild Cognitive Impairment (MCI) identification. Specifically, we devise a hybrid architecture by combining Deep Auto-Encoder (DAE) and Hidden Markov Model (HMM). The roles of DAE and HMM are, respectively, to discover hierarchical non-linear relations among features, by which we transform the original features into a lower dimension space, and to model dynamic characteristics inherent in rs-fMRI, i.e., internal state changes. By building a generative model with HMMs for each class individually, we estimate the data likelihood of a test subject as MCI or normal healthy control, based on which we identify the clinical label. In our experiments, we achieved the maximal accuracy of 81.08% with the proposed method, outperforming state-of-the-art methods in the literature. |
Mendeley readers
Geographical breakdown
Country | Count | As % |
---|---|---|
United States | 1 | 4% |
Unknown | 23 | 96% |
Demographic breakdown
Readers by professional status | Count | As % |
---|---|---|
Student > Ph. D. Student | 7 | 29% |
Student > Master | 5 | 21% |
Researcher | 4 | 17% |
Student > Bachelor | 2 | 8% |
Student > Doctoral Student | 2 | 8% |
Other | 1 | 4% |
Unknown | 3 | 13% |
Readers by discipline | Count | As % |
---|---|---|
Engineering | 6 | 25% |
Computer Science | 5 | 21% |
Neuroscience | 3 | 13% |
Psychology | 1 | 4% |
Mathematics | 1 | 4% |
Other | 2 | 8% |
Unknown | 6 | 25% |