Name
Abstract | ||
|---|---|---|
•A robust and fully-automatic segmentation framework for MR brain scans is proposed.•A heterogeneous cohort of 125 scans of patients who had sustained TBI is segmented.•The approach compares favourably to the state-of-the-art on benchmark and TBI data.•MRI based biomarkers correlate with outcome-relevant clinical variables in TBI.•Evidence that subcortical structures are particularly affected in TBI is presented. |
Year | DOI | Venue |
|---|---|---|
2015 | 10.1016/j.media.2014.12.003 | Medical Image Analysis |
Keywords | Field | DocType |
Traumatic brain injury,Magnetic resonance imaging,Multi-atlas segmentation,Brain image segmentation,Expectation–maximisation | Brain segmentation,Computer vision,Diffusion MRI,Pattern recognition,Segmentation,Midline shift,Robustness (computer science),Artificial intelligence,Neuroimaging,Traumatic brain injury,Mathematics,Magnetic resonance imaging | Journal |
Volume | Issue | ISSN |
21 | 1 | 1361-8415 |
Citations | PageRank | References |
27 | 1.40 | 47 |
Authors | ||
9 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Christian Ledig | 1 | 489 | 27.08 |
| Rolf A. Heckemann | 2 | 697 | 43.14 |
| Alexander Hammers | 3 | 935 | 61.73 |
| Juan Carlos Lopez | 4 | 27 | 1.40 |
| Virginia F J Newcombe | 5 | 27 | 1.74 |
| Antonios Makropoulos | 6 | 27 | 1.40 |
| Jyrki Lötjönen | 7 | 388 | 33.95 |
| David K Menon | 8 | 27 | 1.40 |
| Daniel Rueckert | 9 | 9338 | 637.58 |