EUVIMEDUpptäck EUVIMED
Crossref

A robust and automatic CT‐3D ultrasound registration method based on segmentation, context, and edge hybrid metric

Baochun He, Sheng Zhao, Yanmei Dai, Jiaqi Wu, Huoling Luo, Jianxi Guo, Zhipeng Ni, Tianchong Wu, Fangyuan Kuang, Huijie Jiang, Yanfang Zhang, Fucang Jia

Medical Physics · 2023-10 · 50 (10) · 6243-6258

DOI: 10.1002/mp.16396 ↗

At a glance

Journal article in Medical Physics, published online on 2023-04-06. Written by Baochun He and 11 co-authors. Institution: Center for Medical AI, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China. Major MEDLINE topics: Imaging, Three-Dimensional, Liver. Cited 10 times so far (Crossref); 39 references. Funded by: National Key Research and Development Program of China, National Natural Science Foundation of China, Natural Science Foundation of Guangdong Province.

AbstractSubjectsBibliografiska uppgifterCiteRelated studies

Abstract (original language)

Background

The fusion of computed tomography (CT) and ultrasound (US) image can enhance lesion detection ability and improve the success rate of liver interventional radiology. The image‐based fusion methods encounter the challenge of registration initialization due to the random scanning pose and limited field of view of US. Existing automatic methods those used vessel geometric information and intensity‐based metric are sensitive to parameters and have low success rate. The learning‐based methods require a large number of registered datasets for training.

Purpose

The aim of this study is to provide a fully automatic and robust US‐3D CT registration method without registered training data and user‐specified parameters assisted by the revolutionary deep learning‐based segmentation, which can further be used for preparing training samples for the study of learning‐based methods.

Methods

We propose a fully automatic CT‐3D US registration method by two improved registration metrics. We propose to use 3D U‐Net‐based multi‐organ segmentation of US and CT to assist the conventional registration. The rigid transform is searched in the space of any paired vessel bifurcation planes where the best transform is decided by a segmentation overlap metric, which is more related to the segmentation precision than Dice coefficient. In nonrigid registration phase, we propose a hybrid context and edge based image similarity metric with a simple mask that can remove most noisy US voxels to guide the B‐spline transform registration. We evaluate our method on 42 paired CT‐3D US datasets scanned with two different US devices from two hospitals. We compared our methods with other exsiting methods with both quantitative measures of target registration error (TRE) and the Jacobian determinent with paired t ‐test and qualitative registration imaging results.

Results

The results show that our method achieves fully automatic rigid registration TRE of 4.895 mm, deformable registration TRE of 2.995 mm in average, which outperforms state‐of‐the‐art automatic linear methods and nonlinear registration metrics with paired t ‐test's p value less than 0.05. The proposed overlap metric achieves better results than self similarity description (SSD), edge matching (EM), and block matching (BM) with p values of 1.624E‐10, 4.235E‐9, and 0.002, respectively. The proposed hybrid edge and context‐based metric outperforms context‐only, edge‐only, and intensity statistics‐only‐based metrics with p values of 0.023, 3.81E‐5, and 1.38E‐15, respectively. The 3D US segmentation has achieved mean Dice similarity coefficient (DSC) of 0.799, 0.724, 0.788, and precision of 0.871, 0.769, 0.862 for gallbladder, vessel, and branch vessel, respectively.

Conclusions

The deep learning‐based US segmentation can achieve satisfied result to assist robust conventional rigid registration. The Dice similarity coefficient‐based metrics, hybrid context, and edge image similarity metric contribute to robust and accurate registration.

Subjects

MeSH terms (MEDLINE)

Imaging, Three-DimensionalLiverUltrasonographyTomography, X-Ray ComputedImage Processing, Computer-Assisted

Author keywords

US-CT registrationimage fusioninterventional radiologyliver ultrasound segmentationregistration metrics

Authors and institutions

  • Center for Medical AI, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China.
  • Shenzhen College of Advanced Technology, University of Chinese Academy of Sciences, Shenzhen, China.
  • Department of Radiology, The Second Affiliated Hospital of Harbin Medical University, Harbin, China.
  • Department of Inpatient Ultrasound, The Second Affiliated Hospital of Harbin Medical University, Harbin, China.
  • Department of Interventional Radiology, Shenzhen People's Hospital, Shenzhen, China.
  • Department of Ultrasound, Shenzhen People's Hospital, Shenzhen, China.

Funding

  • National Key Research and Development Program of China
  • National Natural Science Foundation of China
  • Natural Science Foundation of Guangdong Province
  • Shenzhen Science and Technology Program
  • Zhuhai Science and Technology Program
  • Guangdong Key Area Research and Development Program
  • Shenzhen Key Laboratory Program

Cite

APA

He, B., Zhao, S., Dai, Y., Wu, J., Luo, H., Guo, J., Ni, Z., Wu, T., Kuang, F., Jiang, H., Zhang, Y., & Jia, F. (2023). A robust and automatic CT‐3D ultrasound registration method based on segmentation, context, and edge hybrid metric. Medical Physics, 50(10), 6243-6258. https://doi.org/10.1002/mp.16396

Vancouver

He B, Zhao S, Dai Y, Wu J, Luo H, Guo J, et al. A robust and automatic CT‐3D ultrasound registration method based on segmentation, context, and edge hybrid metric. Medical Physics. 2023;50(10):6243-6258. doi:10.1002/mp.16396

BibTeX
@article{He2023,
  author = {He, Baochun and Zhao, Sheng and Dai, Yanmei and Wu, Jiaqi and Luo, Huoling and Guo, Jianxi and Ni, Zhipeng and Wu, Tianchong and Kuang, Fangyuan and Jiang, Huijie and Zhang, Yanfang and Jia, Fucang},
  title = {A robust and automatic CT‐3D ultrasound registration method based on segmentation, context, and edge hybrid metric},
  journal = {Medical Physics},
  year = {2023},
  volume = {50},
  number = {10},
  pages = {6243--6258},
  doi = {10.1002/mp.16396}
}
Start for free →