Abstract
The atlases are used for baseline and aligned follow-up images and are combined with an intensity model to define a weighted graph that connects the timepoints. A minimal cut on this graph yields the segmentation for all timepoints. The resulting segmentations are consistent over time in boundary regions with weak gray scale definition, but reflect atrophy well where the structure boundary is well defined by MR intensity.
The hippocampus was segmented in 568 baseline and follow-up images provided by the Alzheimer's Disease Neuroimaging Initiative (ADNI).
The estimated atrophy rates correctly classified AD patients from controls at a rate of 82% (Atrophy rates: AD 3.85%/y.; MCI 2.31%/y.; controls: 0.85%/y.)
| Original language | English |
|---|---|
| Title of host publication | Proceedings of the 7th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2010 |
| Publisher | Institute of Electrical and Electronic Engineers IEEE |
| Pages | 960-963 |
| ISBN (Print) | 978-1-4244-4125-9, 978-1-4244-4126-6 |
| DOIs | |
| Publication status | Published - 2010 |
| MoE publication type | A4 Article in a conference publication |
| Event | 7th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2010 - Rotterdam, Netherlands Duration: 14 Apr 2010 → 17 Apr 2010 |
Conference
| Conference | 7th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2010 |
|---|---|
| Abbreviated title | ISBI 2010 |
| Country | Netherlands |
| City | Rotterdam |
| Period | 14/04/10 → 17/04/10 |
Fingerprint
Keywords
- Alzheimer's disease
- Graph-cuts
- Hippocampal atrophy
- Structural MR images
Cite this
}
Measuring atrophy by simultaneous segmentation of serial MR images using 4-D graph-cuts. / Wolz, R.; Heckemann, R. A.; Aljabar, P.; Hajnal, J. V.; Hammers, A.; Lötjönen, Jyrki; Rueckert, D.
Proceedings of the 7th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2010. Institute of Electrical and Electronic Engineers IEEE, 2010. p. 960-963.Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review
TY - GEN
T1 - Measuring atrophy by simultaneous segmentation of serial MR images using 4-D graph-cuts
AU - Wolz, R.
AU - Heckemann, R. A.
AU - Aljabar, P.
AU - Hajnal, J. V.
AU - Hammers, A.
AU - Lötjönen, Jyrki
AU - Rueckert, D.
PY - 2010
Y1 - 2010
N2 - We propose a method for simultaneous segmentation of serially acquired magnetic resonance (MR) images. An existing graph-cuts based algorithm is extended and applied to 4-D images. A probabilistic atlas is generated for each baseline scan by intersubject registration of multiple labeled images. The atlases are used for baseline and aligned follow-up images and are combined with an intensity model to define a weighted graph that connects the timepoints. A minimal cut on this graph yields the segmentation for all timepoints. The resulting segmentations are consistent over time in boundary regions with weak gray scale definition, but reflect atrophy well where the structure boundary is well defined by MR intensity. The hippocampus was segmented in 568 baseline and follow-up images provided by the Alzheimer's Disease Neuroimaging Initiative (ADNI). The estimated atrophy rates correctly classified AD patients from controls at a rate of 82% (Atrophy rates: AD 3.85%/y.; MCI 2.31%/y.; controls: 0.85%/y.)
AB - We propose a method for simultaneous segmentation of serially acquired magnetic resonance (MR) images. An existing graph-cuts based algorithm is extended and applied to 4-D images. A probabilistic atlas is generated for each baseline scan by intersubject registration of multiple labeled images. The atlases are used for baseline and aligned follow-up images and are combined with an intensity model to define a weighted graph that connects the timepoints. A minimal cut on this graph yields the segmentation for all timepoints. The resulting segmentations are consistent over time in boundary regions with weak gray scale definition, but reflect atrophy well where the structure boundary is well defined by MR intensity. The hippocampus was segmented in 568 baseline and follow-up images provided by the Alzheimer's Disease Neuroimaging Initiative (ADNI). The estimated atrophy rates correctly classified AD patients from controls at a rate of 82% (Atrophy rates: AD 3.85%/y.; MCI 2.31%/y.; controls: 0.85%/y.)
KW - Alzheimer's disease
KW - Graph-cuts
KW - Hippocampal atrophy
KW - Structural MR images
U2 - 10.1109/ISBI.2010.5490147
DO - 10.1109/ISBI.2010.5490147
M3 - Conference article in proceedings
SN - 978-1-4244-4125-9
SN - 978-1-4244-4126-6
SP - 960
EP - 963
BT - Proceedings of the 7th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2010
PB - Institute of Electrical and Electronic Engineers IEEE
ER -