Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2018 Jul 30:2018:4687376.
doi: 10.1155/2018/4687376. eCollection 2018.

Large-Deformation Image Registration of CT-TEE for Surgical Navigation of Congenital Heart Disease

Shuiping Gou  1 , Linlin Chen  1 , Yu Gu  1 , Liyu Huang  2 , Meiping Huang  3 , Jian Zhuang  4
Affiliations

Large-Deformation Image Registration of CT-TEE for Surgical Navigation of Congenital Heart Disease

Shuiping Gou et al. Comput Math Methods Med. .

Abstract

The surgical treatment of congenital heart disease requires navigational assistance with transesophageal echocardiography (TEE); however, TEE images are often difficult to interpret and provide very limited anatomical information. Registering preoperative CT images to intraoperative TEE images provides surgeons with richer and more useful anatomical information. Yet, CT and TEE images differ substantially in terms of scale and geometry. In the present research, we propose a novel method for the registration of CT and TEE images for navigation during surgical repair of large defects in patients with congenital heart disease. Valve data was used for the coarse registration to determine the basic location. This was followed by the use of an enhanced probability model map to overcome gray-level differences between the two imaging modalities. Finally, the rapid optimization of mutual information was achieved by migrating parameters. This method was tested on a dataset of 240 images from 12 infant, children (≤ 3 years old), and adult patients with congenital heart disease. Compared to the "bronze standard" registration, the proposed method was more accurate with an average Dice coefficient of 0.91 and an average root mean square of target registration error of 1.2655 mm.

PubMed Disclaimer

Figures

Figure 1
Figure 1
Flowchart of the proposed algorithm. CT, computed tomography; TEE, transesophageal echocardiography.
Figure 2
Figure 2
The process of interactive segmentation. (a) Interactive segmentation of a CT image. (b) The result of CT image segmentation. (c) Interactive segmentation of a TEE image. (d) The result of TEE image segmentation. Note: during interactive segmentation, the user selected a region of interest (yellow box) and marked the target (red dots) and the background areas (blue dots). CT, computed tomography; TEE, transesophageal echocardiography.
Figure 3
Figure 3
The process of region enhancement. (a) Original CT image IR(x). (b) Enhancement matrix VR(x). (c) Enhanced CT image. CT, computed tomography; ROI, region of interest.
Figure 4
Figure 4
CT and TEE probability maps. (a) The original CT image. (b) The CT probability map. (c) The original TEE image. (d) The TEE probability map. CT, computed tomography; TEE, transesophageal electrocardiography.
Figure 5
Figure 5
Registration process for a set of sections from an infant patient (Patient 8 in Table 1). (a) The original CT image. (b) The original TEE image. (c) The result of basic registration. (d) The result of final registration. (e) The fusion result based on the basic registration. (f) The fusion result based on the final registration. (g) The fusion result obtained from the comparison algorithm VMI. (h) The fusion result obtained from the comparison algorithm ICPMI. Note: the yellow arrows in (e), (f), and (h) indicate the alignment of the heart valves. CT, computed tomography; TEE, transesophageal electrocardiography; VMI and ICPMI, comparison algorithms.
Figure 6
Figure 6
Registration process for a set of sections from an adult patient (Patient 12 in Table 1). (a) The original CT image. (b) The original TEE image. (c) The results of the basic registration. (d) The result of the final registration. (e) The fusion result based on the basic registration. (f) The fusion result based on the final registration. (g) The fusion result obtained from the comparison algorithm VMI. (h) The fusion result obtained from the comparison algorithm ICPMI. Note: the yellow arrows in (e), (f), and (h) indicate the alignment of the heart valves. CT, computed tomography; TEE, transesophageal electrocardiography; VMI and ICPMI, comparison algorithms.
Algorithm 1
Algorithm 1
Procedure of the proposed method.
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

References

    1. Manjunath B. S., Shekhar C., Chellappa R. A new approach to image feature detection with applications. Pattern Recognition. 1996;29(4):627–640. doi: 10.1016/0031-3203(95)00115-8. - DOI
    1. Fonseca L. M. G., Costa M. H. M. Automatic registration of satellite images. Proceedings of the 1997 10th Brazilian Symposium of Computer Graphic and Image Processing, SIBGRAPI 97; October 1997; Campos do Jordao, Brazil. pp. 219–226.
    1. Feng Y., Schlichting A., Brenner C. 3D Feature point extraction from lidar data using a neural network. International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives 41. 2016;XLI-B1:563–569. doi: 10.5194/isprs-archives-XLI-B1-563-2016. - DOI
    1. Cheng Y., Dubois T. Object Recognition by Using Multi-level Feature Point Extraction. Computer Vision and Pattern Recognition. 2017
    1. Chen W. Y., Pan T. F., Chen L. G. A spatial first 3-D XYT feature point extraction algorithm for efficient human action recognition. Proceedings of the 2014 IEEE International Conference on Consumer Electronics - Taiwan (ICCE-TW); May 2014; Taipei, Taiwan. pp. 101–102. - DOI

LinkOut - more resources