by Wei Wei, Haishan Xu, Julian Alpers, Zhang Tianbao, Lei Wang, Marko Rak, Christian Hansen
Abstract:
In recent years, image-guided thermal ablations have become a considerable treatment method for cancer patients, including support through navigational systems. One of the most critical challenges in these systems is the registration between the intraoperative images and the preoperative volume. The motion secondary to inspiration makes registration even more difficult. In this work, we propose a coarse-fine fast patient registration technique to solve the problem of motion compensation. In contrast to other state-of-the-art methods , we focus on improving the convergence range of registration. To this end, we make use of a Deep Learning 2D U-Net framework to extract the vessels and liver borders from intraoperative ultrasound images and employ the segmenta-tion results as regions of interest in the registration. After an initial 3D-3D registration during breath hold, the following motion compensation is achieved using a 2D-3D registration. Our approach yields a convergence rate of over 70\% with an accuracy of 1.97 ± 1.07 mm regarding the target registration error. The 2D-3D registration is GPU-accelerated with a time cost of less than 200 ms.
Reference:
Fast Registration for Liver Motion Compensation in Ultrasound-guided Navigation (Wei Wei, Haishan Xu, Julian Alpers, Zhang Tianbao, Lei Wang, Marko Rak, Christian Hansen), In 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019), 2019.
Bibtex Entry:
@inproceedings{wei_fast_2019,
address = {Venice, Italy},
title = {Fast {Registration} for {Liver} {Motion} {Compensation} in {Ultrasound}-guided {Navigation}},
doi = {10.1109/ISBI.2019.8759464},
abstract = {In recent years, image-guided thermal ablations have become a considerable treatment method for cancer patients, including support through navigational systems. One of the most critical challenges in these systems is the registration between the intraoperative images and the preoperative volume. The motion secondary to inspiration makes registration even more difficult. In this work, we propose a coarse-fine fast patient registration technique to solve the problem of motion compensation. In contrast to other state-of-the-art methods , we focus on improving the convergence range of registration. To this end, we make use of a Deep Learning 2D U-Net framework to extract the vessels and liver borders from intraoperative ultrasound images and employ the segmenta-tion results as regions of interest in the registration. After an initial 3D-3D registration during breath hold, the following motion compensation is achieved using a 2D-3D registration. Our approach yields a convergence rate of over 70\% with an accuracy of 1.97 ± 1.07 mm regarding the target registration error. The 2D-3D registration is GPU-accelerated with a time cost of less than 200 ms.},
booktitle = {2019 {IEEE} 16th {International} {Symposium} on {Biomedical} {Imaging} ({ISBI} 2019)},
author = {Wei, Wei and Xu, Haishan and Alpers, Julian and Tianbao, Zhang and Wang, Lei and Rak, Marko and Hansen, Christian},
month = jan,
year = {2019}
}