Patch-Based Segmentation from MP2RAGE Images: Comparison to Conventional Techniques: Patch-Based Techniques in Medical Imaging

Erhard T. Næss-Schmidt; Anna Tietze; Irene K. Mikkelsen; Mikkel Petersen; Jakob U. Blicher; Pierrick Coupé; José V. Manjón; Simon F. Eskildsen

doi:10.1007/978-3-319-28194-0_22

Patch-Based Segmentation from MP2RAGE Images: Comparison to Conventional Techniques: Patch-Based Techniques in Medical Imaging

Erhard T. Næss-Schmidt, Anna Tietze, Irene K. Mikkelsen, Mikkel Petersen, Jakob U. Blicher, Pierrick Coupé, José V. Manjón, Simon F. Eskildsen

Department of Clinical Medicine - Center of Functionally Integrative Neuroscience

Research output: Contribution to book/anthology/report/proceeding › Book chapter › Research › peer-review

4 Citations (Scopus)

Abstract

In structural and functional MRI studies there is a need for robust and accurate automatic segmentation of various brain structures. We present a comparison study of three automatic segmentation methods based on the new T1-weighted MR sequence called MP2RAGE, which has superior soft tissue contrast. Automatic segmentations of the thalamus and hippocampus are compared to manual segmentations. In addition, we qualitatively evaluate the segmentations when warped to co-registered maps of the fractional anisotropy (FA) of water diffusion. Compared to manual segmentation, the best results were obtained with a patch-based segmentation method (volBrain) using a library of images from the same scanner (local), followed by volBrain using an external library (external), FSL and Freesurfer. The qualitative evaluation showed that volBrain local and volBrain external produced almost no segmentation errors when overlaid on FA maps, while both FSL and Freesurfer segmentations were found to overlap with white matter tracts. These results underline the importance of applying accurate and robust segmentation methods and demonstrate the superiority of patch-based methods over more conventional methods.

Original language	English
Title of host publication	Patch-Based Techniques in Medical Imaging
Editors	Guorong Wu, Pierrick Coupé, Yiqiang Zhan, Brent Munsell, Daniel Rueckert
Number of pages	8
Volume	9467
Publisher	Springer International Publishing
Publication date	2015
Pages	180-187
ISBN (Print)	978-3-319-28193-3
DOIs	https://doi.org/10.1007/978-3-319-28194-0_22
Publication status	Published - 2015

Keywords

Patch-based segmentation
MRI
volBrain
Freesurfer
FSL
MP2RAGE

Access to Document

10.1007/978-3-319-28194-0_22

Cite this

Næss-Schmidt, E. T., Tietze, A., Mikkelsen, I. K., Petersen, M., Blicher, J. U., Coupé, P., Manjón, J. V., & Eskildsen, S. F. (2015). Patch-Based Segmentation from MP2RAGE Images: Comparison to Conventional Techniques: Patch-Based Techniques in Medical Imaging. In G. Wu, P. Coupé, Y. Zhan, B. Munsell, & D. Rueckert (Eds.), Patch-Based Techniques in Medical Imaging (Vol. 9467, pp. 180-187). Springer International Publishing. https://doi.org/10.1007/978-3-319-28194-0_22

Næss-Schmidt, Erhard T. ; Tietze, Anna ; Mikkelsen, Irene K. et al. / Patch-Based Segmentation from MP2RAGE Images: Comparison to Conventional Techniques : Patch-Based Techniques in Medical Imaging. Patch-Based Techniques in Medical Imaging. editor / Guorong Wu ; Pierrick Coupé ; Yiqiang Zhan ; Brent Munsell ; Daniel Rueckert. Vol. 9467 Springer International Publishing, 2015. pp. 180-187

@inbook{d45cd764e8a74a0f8ed4360b531cafdd,

title = "Patch-Based Segmentation from MP2RAGE Images: Comparison to Conventional Techniques: Patch-Based Techniques in Medical Imaging",

abstract = "In structural and functional MRI studies there is a need for robust and accurate automatic segmentation of various brain structures. We present a comparison study of three automatic segmentation methods based on the new T1-weighted MR sequence called MP2RAGE, which has superior soft tissue contrast. Automatic segmentations of the thalamus and hippocampus are compared to manual segmentations. In addition, we qualitatively evaluate the segmentations when warped to co-registered maps of the fractional anisotropy (FA) of water diffusion. Compared to manual segmentation, the best results were obtained with a patch-based segmentation method (volBrain) using a library of images from the same scanner (local), followed by volBrain using an external library (external), FSL and Freesurfer. The qualitative evaluation showed that volBrain local and volBrain external produced almost no segmentation errors when overlaid on FA maps, while both FSL and Freesurfer segmentations were found to overlap with white matter tracts. These results underline the importance of applying accurate and robust segmentation methods and demonstrate the superiority of patch-based methods over more conventional methods.",

keywords = "Patch-based segmentation, MRI, volBrain, Freesurfer, FSL, MP2RAGE",

author = "N{\ae}ss-Schmidt, {Erhard T.} and Anna Tietze and Mikkelsen, {Irene K.} and Mikkel Petersen and Blicher, {Jakob U.} and Pierrick Coup{\'e} and Manj{\'o}n, {Jos{\'e} V.} and Eskildsen, {Simon F.}",

year = "2015",

doi = "10.1007/978-3-319-28194-0_22",

language = "English",

isbn = "978-3-319-28193-3",

volume = "9467",

pages = "180--187",

editor = "Guorong Wu and Pierrick Coup{\'e} and Yiqiang Zhan and Brent Munsell and Daniel Rueckert",

booktitle = "Patch-Based Techniques in Medical Imaging",

publisher = "Springer International Publishing",

}

Næss-Schmidt, ET, Tietze, A, Mikkelsen, IK , Petersen, M, Blicher, JU, Coupé, P, Manjón, JV & Eskildsen, SF 2015, Patch-Based Segmentation from MP2RAGE Images: Comparison to Conventional Techniques: Patch-Based Techniques in Medical Imaging. in G Wu, P Coupé, Y Zhan, B Munsell & D Rueckert (eds), Patch-Based Techniques in Medical Imaging. vol. 9467, Springer International Publishing, pp. 180-187. https://doi.org/10.1007/978-3-319-28194-0_22

Patch-Based Segmentation from MP2RAGE Images: Comparison to Conventional Techniques: Patch-Based Techniques in Medical Imaging. / Næss-Schmidt, Erhard T.; Tietze, Anna; Mikkelsen, Irene K. et al.
Patch-Based Techniques in Medical Imaging. ed. / Guorong Wu; Pierrick Coupé; Yiqiang Zhan; Brent Munsell; Daniel Rueckert. Vol. 9467 Springer International Publishing, 2015. p. 180-187.

Research output: Contribution to book/anthology/report/proceeding › Book chapter › Research › peer-review

TY - CHAP

T1 - Patch-Based Segmentation from MP2RAGE Images: Comparison to Conventional Techniques

T2 - Patch-Based Techniques in Medical Imaging

AU - Næss-Schmidt, Erhard T.

AU - Tietze, Anna

AU - Mikkelsen, Irene K.

AU - Petersen, Mikkel

AU - Blicher, Jakob U.

AU - Coupé, Pierrick

AU - Manjón, José V.

AU - Eskildsen, Simon F.

PY - 2015

Y1 - 2015

N2 - In structural and functional MRI studies there is a need for robust and accurate automatic segmentation of various brain structures. We present a comparison study of three automatic segmentation methods based on the new T1-weighted MR sequence called MP2RAGE, which has superior soft tissue contrast. Automatic segmentations of the thalamus and hippocampus are compared to manual segmentations. In addition, we qualitatively evaluate the segmentations when warped to co-registered maps of the fractional anisotropy (FA) of water diffusion. Compared to manual segmentation, the best results were obtained with a patch-based segmentation method (volBrain) using a library of images from the same scanner (local), followed by volBrain using an external library (external), FSL and Freesurfer. The qualitative evaluation showed that volBrain local and volBrain external produced almost no segmentation errors when overlaid on FA maps, while both FSL and Freesurfer segmentations were found to overlap with white matter tracts. These results underline the importance of applying accurate and robust segmentation methods and demonstrate the superiority of patch-based methods over more conventional methods.

AB - In structural and functional MRI studies there is a need for robust and accurate automatic segmentation of various brain structures. We present a comparison study of three automatic segmentation methods based on the new T1-weighted MR sequence called MP2RAGE, which has superior soft tissue contrast. Automatic segmentations of the thalamus and hippocampus are compared to manual segmentations. In addition, we qualitatively evaluate the segmentations when warped to co-registered maps of the fractional anisotropy (FA) of water diffusion. Compared to manual segmentation, the best results were obtained with a patch-based segmentation method (volBrain) using a library of images from the same scanner (local), followed by volBrain using an external library (external), FSL and Freesurfer. The qualitative evaluation showed that volBrain local and volBrain external produced almost no segmentation errors when overlaid on FA maps, while both FSL and Freesurfer segmentations were found to overlap with white matter tracts. These results underline the importance of applying accurate and robust segmentation methods and demonstrate the superiority of patch-based methods over more conventional methods.

KW - Patch-based segmentation

KW - MRI

KW - volBrain

KW - Freesurfer

KW - FSL

KW - MP2RAGE

U2 - 10.1007/978-3-319-28194-0_22

DO - 10.1007/978-3-319-28194-0_22

M3 - Book chapter

SN - 978-3-319-28193-3

VL - 9467

SP - 180

EP - 187

BT - Patch-Based Techniques in Medical Imaging

A2 - Wu, Guorong

A2 - Coupé, Pierrick

A2 - Zhan, Yiqiang

A2 - Munsell, Brent

A2 - Rueckert, Daniel

PB - Springer International Publishing

ER -

Næss-Schmidt ET, Tietze A, Mikkelsen IK , Petersen M, Blicher JU, Coupé P et al. Patch-Based Segmentation from MP2RAGE Images: Comparison to Conventional Techniques: Patch-Based Techniques in Medical Imaging. In Wu G, Coupé P, Zhan Y, Munsell B, Rueckert D, editors, Patch-Based Techniques in Medical Imaging. Vol. 9467. Springer International Publishing. 2015. p. 180-187 doi: 10.1007/978-3-319-28194-0_22

Patch-Based Segmentation from MP2RAGE Images: Comparison to Conventional Techniques: Patch-Based Techniques in Medical Imaging

Abstract

Keywords

Access to Document

Fingerprint

Cite this