Discriminative Structured Feature Engineering for Macroscale Brain Connectomes
文献类型：期刊论文
| 作者 | Pu, J; Wang, J; Yu, WW; Shen, ZM; Lv, Q; Zeljic, K; Zhang, CC; Sun, BM; Liu, GX; Wang, Z |
| 刊名 | IEEE TRANSACTIONS ON MEDICAL IMAGING
 |
| 出版日期 | 2015 |
| 卷号 | 34期号:11页码:2333-2342 |
| 关键词 | OBSESSIVE-COMPULSIVE DISORDER RICH-CLUB ORGANIZATION FEATURE-SELECTION NETWORKS HUBS PREDICTION KETAMINE CONNECTIVITY STABILITY GRAPHS |
| 通讯作者 | Wang, Z (reprint author), Chinese Acad Sci, Inst Neurosci, Key Lab Primate Neurobiol, Shanghai Inst Biol Sci, Shanghai 200031, Peoples R China.,jianpu@ion.ac.cn ; zheng.wang@ion.ac.cn |
| 英文摘要 | Neuroimaging techniques can measure structural and functional brain connectivity with unprecedented detail in vivo. This so-called brain connectome can be represented as high dimensional matrices corresponding to edge weights in graphs. After measuring the matrices of two cohorts (i.e., patients and healthy controls), one is often required to formulate computational network models for effective feature engineering to draw discriminative distinctions between the cohorts, as well as estimate the associated statistical significance. We designed a novel method to reveal the intrinsic features of functional matrices of discriminative power for group comparison. More specifically, by encouraging co-selection of edges connected to the same node, we preserved the discriminative edges to maximum extent. To reduce the false positive rate of the extracted discriminative edges, an optimization procedure was developed to evaluate the significance of these edges and remove trivial ones. We validated the proposed method using both synthetic data and real benchmarks, and compared it to regularized logistic regression, univariate t-test and stability selection. The experimental results clearly showed that the proposed approach outperformed the three competing methods under various settings. In addition to increasing the F-measure of feature selection, our approach captured the endogenous, discriminative connectivity patterns consistent with recent findings in biomedical literature. This data-driven method paves a new avenue of enquiry into the inherent nature of network models for functional brain connectomes. |
| WOS标题词 | Computer Science ; Engineering ; Imaging Science & Photographic Technology ; Radiology, Nuclear Medicine & Medical Imaging |
| 学科主题 | Computer Science, Interdisciplinary Applications; Engineering, Biomedical; Engineering, Electrical & Electronic; Imaging Science & Photographic Technology; Radiology, Nuclear Medicine & Medical Imaging |
| 收录类别 | SCI |
| 语种 | 英语 |
| WOS记录号 | WOS:000364461000011 |
| 公开日期 | 2016-02-26 |
| 源URL | [http://ir.sibs.ac.cn/handle/331001/3926]  |
| 专题 | 上海神经科学研究所_神经所(总) |
| 推荐引用方式 GB/T 7714 | Pu, J,Wang, J,Yu, WW,et al. Discriminative Structured Feature Engineering for Macroscale Brain Connectomes[J]. IEEE TRANSACTIONS ON MEDICAL IMAGING,2015,34(11):2333-2342. |
| APA | Pu, J.,Wang, J.,Yu, WW.,Shen, ZM.,Lv, Q.,...&Wang, Z.(2015).Discriminative Structured Feature Engineering for Macroscale Brain Connectomes.IEEE TRANSACTIONS ON MEDICAL IMAGING,34(11),2333-2342. |
| MLA | Pu, J,et al."Discriminative Structured Feature Engineering for Macroscale Brain Connectomes".IEEE TRANSACTIONS ON MEDICAL IMAGING 34.11(2015):2333-2342. |
入库方式： OAI收割
来源：上海神经科学研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。