Chapter title |
Hierarchical Region-Network Sparsity for High-Dimensional Inference in Brain Imaging
|
---|---|
Chapter number | 26 |
Book title |
Information Processing in Medical Imaging
|
Published in |
Information processing in medical imaging proceedings of the conference, June 2017
|
DOI | 10.1007/978-3-319-59050-9_26 |
Pubmed ID | |
Book ISBNs |
978-3-31-959049-3, 978-3-31-959050-9
|
Authors |
Danilo Bzdok, Michael Eickenberg, Gaël Varoquaux, Bertrand Thirion |
Abstract |
Structured sparsity penalization has recently improved statistical models applied to high-dimensional data in various domains. As an extension to medical imaging, the present work incorporates priors on network hierarchies of brain regions into logistic-regression to distinguish neural activity effects. These priors bridge two separately studied levels of brain architecture: functional segregation into regions and functional integration by networks. Hierarchical region-network priors are shown to better classify and recover 18 psychological tasks than other sparse estimators. Varying the relative importance of region and network structure within the hierarchical tree penalty captured complementary aspects of the neural activity patterns. Local and global priors of neurobiological knowledge are thus demonstrated to offer advantages in generalization performance, sample complexity, and domain interpretability. |
X Demographics
Geographical breakdown
Country | Count | As % |
---|---|---|
Netherlands | 1 | 33% |
United States | 1 | 33% |
Canada | 1 | 33% |
Demographic breakdown
Type | Count | As % |
---|---|---|
Scientists | 2 | 67% |
Members of the public | 1 | 33% |
Mendeley readers
Geographical breakdown
Country | Count | As % |
---|---|---|
Malaysia | 1 | 4% |
Unknown | 23 | 96% |
Demographic breakdown
Readers by professional status | Count | As % |
---|---|---|
Student > Ph. D. Student | 6 | 25% |
Researcher | 5 | 21% |
Professor | 3 | 13% |
Student > Doctoral Student | 2 | 8% |
Other | 2 | 8% |
Other | 4 | 17% |
Unknown | 2 | 8% |
Readers by discipline | Count | As % |
---|---|---|
Computer Science | 5 | 21% |
Engineering | 4 | 17% |
Neuroscience | 4 | 17% |
Psychology | 4 | 17% |
Agricultural and Biological Sciences | 1 | 4% |
Other | 3 | 13% |
Unknown | 3 | 13% |