TY - GEN
T1 - High-order concept discovery in functional brain imaging
AU - Barnathan, Michael
AU - Megalooikonomou, Vasileios
AU - Faloutsos, Christos
AU - Mohamed, Feroze B.
AU - Faro, Scott
PY - 2010
Y1 - 2010
N2 - Many spatiotemporal medical image datasets exhibit "high-order" structure, in which many independent variables exist (e.g. space and time) or features are not scalar at all. We analyze these datasets as tensors (high-order generalizations of matrices), preprocessing our dataset using wavelets to improve efficiency and performing latent concept discovery using parallel factor analysis. Both our method and naive tensor approaches discovered concepts representing handedness in an 11 subject motor task fMRI dataset. However, our method compressed the dataset by 98% and completed in 2 hours vs. 8 days, suggesting that a wavelet and tensor approach gains the benefits of high-order analysis while preserving the efficiency of low-order techniques.
AB - Many spatiotemporal medical image datasets exhibit "high-order" structure, in which many independent variables exist (e.g. space and time) or features are not scalar at all. We analyze these datasets as tensors (high-order generalizations of matrices), preprocessing our dataset using wavelets to improve efficiency and performing latent concept discovery using parallel factor analysis. Both our method and naive tensor approaches discovered concepts representing handedness in an 11 subject motor task fMRI dataset. However, our method compressed the dataset by 98% and completed in 2 hours vs. 8 days, suggesting that a wavelet and tensor approach gains the benefits of high-order analysis while preserving the efficiency of low-order techniques.
KW - Concept discovery
KW - Latent semantic analysis
KW - Parallel factor analysis
KW - Tensors
KW - Wavelets
KW - fMRI
UR - http://www.scopus.com/inward/record.url?scp=77955181442&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=77955181442&partnerID=8YFLogxK
U2 - 10.1109/ISBI.2010.5490087
DO - 10.1109/ISBI.2010.5490087
M3 - Conference contribution
AN - SCOPUS:77955181442
SN - 9781424441266
T3 - 2010 7th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2010 - Proceedings
SP - 664
EP - 667
BT - 2010 7th IEEE International Symposium on Biomedical Imaging
T2 - 7th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2010
Y2 - 14 April 2010 through 17 April 2010
ER -