Improved registration of DCE-MR images of the liver using a prior segmentation of the region of interest

Improved registration of DCE-MR images of the liver using a prior segmentation of the region of interest

Zhang, T. (TU Delft ImPhys/Quantitative Imaging)
Li, Z. (National University of Defense Technology)
Runge, Jurgen H. (Universiteit van Amsterdam)
Lavini, Cristina (Universiteit van Amsterdam)
Stoker, Jaap (Universiteit van Amsterdam)
Van Gulik, Thomas (Universiteit van Amsterdam)
van Vliet, L.J. (TU Delft ImPhys/Quantitative Imaging)
Vos, F.M. (TU Delft ImPhys/Quantitative Imaging; Universiteit van Amsterdam)

Styner, Martin A. (editor)
Angelini, Elsa D. (editor)

2016

In Dynamic Contrast-Enhanced MRI (DCE-MRI) of the liver, a series of images is acquired over a period of 20 minutes. Due to the patient's breathing, the liver is subject to a substantial displacement between acquisitions. Furthermore, due to its location in the abdomen, the liver also undergoes marked deformation. The large deformations combined with variation in image contrast make accurate liver registration challenging. We present a registration framework that incorporates a liver segmentation to improve the registration accuracy. The segmented liver serves as region-of-interest to our in-house developed registration method called ALOST (autocorrelation of local image structure). ALOST is a continuous optimization method that uses local phase features to overcome space-variant intensity distortions. The proposed framework can confine the solution field to the liver and allow for ALOST to obtain a more accurate solution. For the segmentation part, we use a level-set method to delineate the liver in a so-called contrast enhancement map. This map is obtained by computing the difference between the last and registered first volume from the DCE series. Subsequently, we slightly dilate the segmentation, and apply it as the mask to the other DCE-MRI volumes during registration. It is shown that the registration result becomes more accurate compared with the original ALOST approach.

ALOST
DCE-MRI
Level-set
Liver Segmentation
Registration

http://resolver.tudelft.nl/uuid:3460968e-08f0-458d-a67b-3f3e366768b1

https://doi.org/10.1117/12.2216668

SPIE

978-1-510600195

Medical Imaging 2016: Image Processing, 9784

Medical Imaging 2016: Image Processing, 2016-03-01 → 2016-03-03, San Diego, United States

Proceedings of SPIE, 1605-7422, 9784

Institutional Repository

conference paper

© 2016 T. Zhang, Z. Li, Jurgen H. Runge, Cristina Lavini, Jaap Stoker, Thomas Van Gulik, L.J. van Vliet, F.M. Vos