National Alliance for Medical Image Computing

The Publication Database hosted by SPL

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

Towards Measuring Neuroimage Misalignment

Institution:
Intelligent Systems for Medicine Laboratory, The University of Western Australia, Perth, Australia.
Publisher:
Elsevier Science
Publication Date:
Sep-2015
Journal:
Comput Biol Med
Volume Number:
64
Pages:
12-23
Citation:
Comput Biol Med. 2015 Sep;64:12-23.
PubMed ID:
26112607
PMCID:
PMC4742413
Keywords:
Brain deformation, Hausdorff Distance, Image similarity metrics, Intra-operative registration, Non-rigid registration
Appears in Collections:
NCIGT, NA-MIC, NAC
Sponsors:
P41 EB015902/EB/NIBIB NIH HHS/United States
R01 EB008015/EB/NIBIB NIH HHS/United States
R01 LM010033/LM/NLM NIH HHS/United States
U41 RR019703/RR/NCRR NIH HHS/United States
U54 EB005149/EB/NIBIB NIH HHS/United States
Generated Citation:
Garlapati R.R., Mostayed A., Joldes G.R., Wittek A., Doyle B., Miller K. Towards Measuring Neuroimage Misalignment. Comput Biol Med. 2015 Sep;64:12-23. PMID: 26112607. PMCID: PMC4742413.
Downloaded: 78 times. [view map]
Paper: Download, View online
Export citation:
Google Scholar: link

To enhance neuro-navigation, high quality pre-operative images must be registered onto intra-operative configuration of the brain. Therefore evaluation of the degree to which structures may remain misaligned after registration is critically important. We consider two Hausdorff Distance (HD)-based evaluation approaches: the edge-based HD (EBHD) metric and the Robust HD (RHD) metric as well as various commonly used intensity-based similarity metrics such as Mutual Information (MI), Normalized Mutual Information (NMI), Entropy Correlation Coefficient (ECC), Kullback-Leibler Distance (KLD) and Correlation Ratio (CR). We conducted the evaluation by applying known deformations to simple sample images and real cases of brain shift. We conclude that the intensity-based similarity metrics such as MI, NMI, ECC, KLD and CR do not correlate well with actual alignment errors, and hence are not useful for assessing misalignment. On the contrary, the EBHD and the RHD metrics correlated well with actual alignment errors; however, they have been found to underestimate the actual misalignment. We also note that it is beneficial to present HD results as a percentile-HD curve rather than a single number such as the 95-percentile HD. Percentile-HD curves present the full range of alignment errors and also facilitate the comparison of results obtained using different approaches. Furthermore, the qualities that should be possessed by an ideal evaluation metric were highlighted. Future studies could focus on developing such an evaluation metric.

Additional Material
1 File (46.636kB)
Garlapati-ComputBiolMed2015-fig2.jpg (46.636kB)