Deformable Image Registration with Automatic Non-Correspondence Detection

Kanglin Chen; Alexander Derksen; Stefan Heldmann; Marc Hallmann; Benjamin Berkels

Deformable Image Registration with Automatic Non-Correspondence Detection

Kanglin Chen, Alexander Derksen^*, Stefan Heldmann, Marc Hallmann, Benjamin Berkels

^*Corresponding author for this work

Institute of Mathematics and Image Computing

Abstract

Image registration aims at establishing pointwise correspondences between given images. However, in many practical applications, no correspondences can be established in certain parts of the images. A typical example is the tumor resection area in pre- and post-operative medical images. In this paper, we introduce a novel variational framework that combines registration with an automatic detection of non-correspondence regions. The formulation of the proposed approach is simple but efficient, and compatible with a large class of image registration similarity measures and regularizers. The resulting minimization problem is solved numerically with a non-alternating gradient flow scheme. Furthermore, the method is validated on synthetic data as well as axial slices of pre-, post- and intra-operative MR T1 head scans.

Original language	English
Title of host publication	International Conference on Scale Space and Variational Methods in Computer Vision : SSVM 2015: Scale Space and Variational Methods in Computer Vision
Publisher	Springer Verlag
Publication date	01.01.2015
Publication status	Published - 01.01.2015

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Cite this

@inproceedings{d772e504785f4522baf37636a04de39f,

title = "Deformable Image Registration with Automatic Non-Correspondence Detection",

abstract = "Image registration aims at establishing pointwise correspondences between given images. However, in many practical applications, no correspondences can be established in certain parts of the images. A typical example is the tumor resection area in pre- and post-operative medical images. In this paper, we introduce a novel variational framework that combines registration with an automatic detection of non-correspondence regions. The formulation of the proposed approach is simple but efficient, and compatible with a large class of image registration similarity measures and regularizers. The resulting minimization problem is solved numerically with a non-alternating gradient flow scheme. Furthermore, the method is validated on synthetic data as well as axial slices of pre-, post- and intra-operative MR T1 head scans.",

author = "Kanglin Chen and Alexander Derksen and Stefan Heldmann and Marc Hallmann and Benjamin Berkels",

note = "Publisher Copyright: {\textcopyright} Springer International Publishing Switzerland 2015.",

year = "2015",

month = jan,

day = "1",

language = "English",

booktitle = "International Conference on Scale Space and Variational Methods in Computer Vision",

publisher = "Springer Verlag",

}

Deformable Image Registration with Automatic Non-Correspondence Detection. / Chen, Kanglin; Derksen, Alexander; Heldmann, Stefan et al.
International Conference on Scale Space and Variational Methods in Computer Vision: SSVM 2015: Scale Space and Variational Methods in Computer Vision. Springer Verlag, 2015.

Research output: Chapters in Books/Reports/Conference Proceedings › Conference contribution › peer-review

TY - GEN

T1 - Deformable Image Registration with Automatic Non-Correspondence Detection

AU - Chen, Kanglin

AU - Derksen, Alexander

AU - Heldmann, Stefan

AU - Hallmann, Marc

AU - Berkels, Benjamin

PY - 2015/1/1

Y1 - 2015/1/1

N2 - Image registration aims at establishing pointwise correspondences between given images. However, in many practical applications, no correspondences can be established in certain parts of the images. A typical example is the tumor resection area in pre- and post-operative medical images. In this paper, we introduce a novel variational framework that combines registration with an automatic detection of non-correspondence regions. The formulation of the proposed approach is simple but efficient, and compatible with a large class of image registration similarity measures and regularizers. The resulting minimization problem is solved numerically with a non-alternating gradient flow scheme. Furthermore, the method is validated on synthetic data as well as axial slices of pre-, post- and intra-operative MR T1 head scans.

AB - Image registration aims at establishing pointwise correspondences between given images. However, in many practical applications, no correspondences can be established in certain parts of the images. A typical example is the tumor resection area in pre- and post-operative medical images. In this paper, we introduce a novel variational framework that combines registration with an automatic detection of non-correspondence regions. The formulation of the proposed approach is simple but efficient, and compatible with a large class of image registration similarity measures and regularizers. The resulting minimization problem is solved numerically with a non-alternating gradient flow scheme. Furthermore, the method is validated on synthetic data as well as axial slices of pre-, post- and intra-operative MR T1 head scans.

UR - https://link.springer.com/book/10.1007/978-3-319-18461-6

M3 - Conference contribution

BT - International Conference on Scale Space and Variational Methods in Computer Vision

PB - Springer Verlag

ER -

Deformable Image Registration with Automatic Non-Correspondence Detection

Abstract

UN SDGs

Other files and links

Cite this