Surgical Planning Laboratory - Brigham & Women's Hospital - Boston, Massachusetts USA - a teaching affiliate of Harvard Medical School

Surgical Planning Laboratory

The Publication Database hosted by SPL

All Publications | Upload | Advanced Search | Gallery View | Download Statistics | Help | Import | Log in

Preliminary Analysis using Multi-Atlas Labeling Algorithms for Tracing Longitudinal Change

1Department of Psychiatry, University of Iowa, Iowa City, IA, USA.
2Department of Biostatistics, College of Public Health, University of Iowa, Iowa City, IA, USA.
Publication Date:
Volume Number:
Front Neurosci. 2015 Jul; 9: 242.
PubMed ID:
brain MRI, longitudinal data analysis, multicenter study, machine learning, multi-atlas label fusion, validation
Appears in Collections:
R01 NS050568/NS/NINDS NIH HHS/United States
R01 EB000975/EB/NIBIB NIH HHS/United States
R01 NS040068/NS/NINDS NIH HHS/United States
R01 NS054893/NS/NINDS NIH HHS/United States
P41 RR015241/RR/NCRR NIH HHS/United States
S10 RR023392/RR/NCRR NIH HHS/United States
U54 EB005149/EB/NIBIB NIH HHS/United States
R03 EB008673/EB/NIBIB NIH HHS/United States
Generated Citation:
Kim R.E., Lourens S., Long J.D., Paulsen J.S., Johnson H.J. Preliminary Analysis using Multi-Atlas Labeling Algorithms for Tracing Longitudinal Change. Front Neurosci. 2015 Jul; 9: 242. PMID: 26236182. PMCID: PMC4500912.
Downloaded: 875 times. [view map]
Paper: Download, View online
Export citation:
Google Scholar: link

Multicenter longitudinal neuroimaging has great potential to provide efficient and consistent biomarkers for research of neurodegenerative diseases and aging. In rare disease studies it is of primary importance to have a reliable tool that performs consistently for data from many different collection sites to increase study power. A multi-atlas labeling algorithm is a powerful brain image segmentation approach that is becoming increasingly popular in image processing. The present study examined the performance of multi-atlas labeling tools for subcortical identification using two types of in-vivo image database: Traveling Human Phantom (THP) and PREDICT-HD. We compared the accuracy (Dice Similarity Coefficient; DSC and intraclass correlation; ICC), multicenter reliability (Coefficient of Variance; CV), and longitudinal reliability (volume trajectory smoothness and Akaike Information Criterion; AIC) of three automated segmentation approaches: two multi-atlas labeling tools, MABMIS and MALF, and a machine-learning-based tool, BRAINSCut. In general, MALF showed the best performance (higher DSC, ICC, lower CV, AIC, and smoother trajectory) with a couple of exceptions. First, the results of accumben, where BRAINSCut showed higher reliability, were still premature to discuss their reliability levels since their validity is still in doubt (DSC < 0.7, ICC < 0.7). For caudate, BRAINSCut presented slightly better accuracy while MALF showed significantly smoother longitudinal trajectory. We discuss advantages and limitations of these performance variations and conclude that improved segmentation quality can be achieved using multi-atlas labeling methods. While multi-atlas labeling methods are likely to help improve overall segmentation quality, caution has to be taken when one chooses an approach, as our results suggest that segmentation outcome can vary depending on research interest.

Additional Material
1 File (120.517kB)
Kim-FrontNeurosci2015-fig4..jpg (120.517kB)