Automatic segmentation of true lumen and false lumen of aortic dissection based on a two-stage learning framework

Guoliang Cheng; Jiang Xiong; Duanduan Chen

doi:10.1109/ICIBA56860.2023.10165320

Automatic segmentation of true lumen and false lumen of aortic dissection based on a two-stage learning framework

Guoliang Cheng, Jiang Xiong, Duanduan Chen^*

^*Corresponding author for this work

School of Medical and Technology

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

Accurate segmentation for true lumen (TL) and false lumen (FL) is essential for the treatment of aortic dissection (AD) disease. However, the complex morphology of AD raised challenges for AD segmentation, especially for precise TL and FL separation. In this study, a novel two-stage algorithm based on the mesh model was developed to achieve the segmentation of TL and FL. In detail, a MeshSegNet was firstly applied to complete the coarse segmentation of AD and then fast geodesic curvature flow (FGCF) was used to optimize the segmentation result. A total of 150 type B AD cases were included to train and evaluate the effect of the proposed segmentation algorithm. The results showed that FGCF could significantly enhance the segmentation precision with the maximum increasing dice score of 0.18 compared to that with MeshSegNet method only. The average accuracy of all included testing cases was more than 93%. This two-stage segmentation algorithm could achieve precise and efficient segmentation of TL and FL, thus might assist in the treatment of AD in the future.

Original language	English
Title of host publication	Proceedings of 2023 IEEE 3rd International Conference on Information Technology, Big Data and Artificial Intelligence, ICIBA 2023
Editors	Bing Xu, Kefen Mou
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	337-341
Number of pages	5
ISBN (Electronic)	9781665490788
DOIs	https://doi.org/10.1109/ICIBA56860.2023.10165320
Publication status	Published - 2023
Event	3rd IEEE International Conference on Information Technology, Big Data and Artificial Intelligence, ICIBA 2023 - Chongqing, China Duration: 26 May 2023 → 28 May 2023

Publication series

Name	Proceedings of 2023 IEEE 3rd International Conference on Information Technology, Big Data and Artificial Intelligence, ICIBA 2023

Conference

Conference	3rd IEEE International Conference on Information Technology, Big Data and Artificial Intelligence, ICIBA 2023
Country/Territory	China
City	Chongqing
Period	26/05/23 → 28/05/23

Keywords

Aortic dissection
Deep learning
Level set
Mesh segmentation

Access to Document

10.1109/ICIBA56860.2023.10165320

Cite this

Cheng, G., Xiong, J., & Chen, D. (2023). Automatic segmentation of true lumen and false lumen of aortic dissection based on a two-stage learning framework. In B. Xu, & K. Mou (Eds.), Proceedings of 2023 IEEE 3rd International Conference on Information Technology, Big Data and Artificial Intelligence, ICIBA 2023 (pp. 337-341). (Proceedings of 2023 IEEE 3rd International Conference on Information Technology, Big Data and Artificial Intelligence, ICIBA 2023). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICIBA56860.2023.10165320

Cheng, Guoliang ; Xiong, Jiang ; Chen, Duanduan. / Automatic segmentation of true lumen and false lumen of aortic dissection based on a two-stage learning framework. Proceedings of 2023 IEEE 3rd International Conference on Information Technology, Big Data and Artificial Intelligence, ICIBA 2023. editor / Bing Xu ; Kefen Mou. Institute of Electrical and Electronics Engineers Inc., 2023. pp. 337-341 (Proceedings of 2023 IEEE 3rd International Conference on Information Technology, Big Data and Artificial Intelligence, ICIBA 2023).

@inproceedings{cd82e5affb934ddaacfbade5594e68c8,

title = "Automatic segmentation of true lumen and false lumen of aortic dissection based on a two-stage learning framework",

abstract = "Accurate segmentation for true lumen (TL) and false lumen (FL) is essential for the treatment of aortic dissection (AD) disease. However, the complex morphology of AD raised challenges for AD segmentation, especially for precise TL and FL separation. In this study, a novel two-stage algorithm based on the mesh model was developed to achieve the segmentation of TL and FL. In detail, a MeshSegNet was firstly applied to complete the coarse segmentation of AD and then fast geodesic curvature flow (FGCF) was used to optimize the segmentation result. A total of 150 type B AD cases were included to train and evaluate the effect of the proposed segmentation algorithm. The results showed that FGCF could significantly enhance the segmentation precision with the maximum increasing dice score of 0.18 compared to that with MeshSegNet method only. The average accuracy of all included testing cases was more than 93%. This two-stage segmentation algorithm could achieve precise and efficient segmentation of TL and FL, thus might assist in the treatment of AD in the future.",

keywords = "Aortic dissection, Deep learning, Level set, Mesh segmentation",

author = "Guoliang Cheng and Jiang Xiong and Duanduan Chen",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 3rd IEEE International Conference on Information Technology, Big Data and Artificial Intelligence, ICIBA 2023 ; Conference date: 26-05-2023 Through 28-05-2023",

year = "2023",

doi = "10.1109/ICIBA56860.2023.10165320",

language = "English",

series = "Proceedings of 2023 IEEE 3rd International Conference on Information Technology, Big Data and Artificial Intelligence, ICIBA 2023",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "337--341",

editor = "Bing Xu and Kefen Mou",

booktitle = "Proceedings of 2023 IEEE 3rd International Conference on Information Technology, Big Data and Artificial Intelligence, ICIBA 2023",

address = "United States",

}

Cheng, G, Xiong, J & Chen, D 2023, Automatic segmentation of true lumen and false lumen of aortic dissection based on a two-stage learning framework. in B Xu & K Mou (eds), Proceedings of 2023 IEEE 3rd International Conference on Information Technology, Big Data and Artificial Intelligence, ICIBA 2023. Proceedings of 2023 IEEE 3rd International Conference on Information Technology, Big Data and Artificial Intelligence, ICIBA 2023, Institute of Electrical and Electronics Engineers Inc., pp. 337-341, 3rd IEEE International Conference on Information Technology, Big Data and Artificial Intelligence, ICIBA 2023, Chongqing, China, 26/05/23. https://doi.org/10.1109/ICIBA56860.2023.10165320

Automatic segmentation of true lumen and false lumen of aortic dissection based on a two-stage learning framework. / Cheng, Guoliang; Xiong, Jiang; Chen, Duanduan.
Proceedings of 2023 IEEE 3rd International Conference on Information Technology, Big Data and Artificial Intelligence, ICIBA 2023. ed. / Bing Xu; Kefen Mou. Institute of Electrical and Electronics Engineers Inc., 2023. p. 337-341 (Proceedings of 2023 IEEE 3rd International Conference on Information Technology, Big Data and Artificial Intelligence, ICIBA 2023).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Automatic segmentation of true lumen and false lumen of aortic dissection based on a two-stage learning framework

AU - Cheng, Guoliang

AU - Xiong, Jiang

AU - Chen, Duanduan

PY - 2023

Y1 - 2023

N2 - Accurate segmentation for true lumen (TL) and false lumen (FL) is essential for the treatment of aortic dissection (AD) disease. However, the complex morphology of AD raised challenges for AD segmentation, especially for precise TL and FL separation. In this study, a novel two-stage algorithm based on the mesh model was developed to achieve the segmentation of TL and FL. In detail, a MeshSegNet was firstly applied to complete the coarse segmentation of AD and then fast geodesic curvature flow (FGCF) was used to optimize the segmentation result. A total of 150 type B AD cases were included to train and evaluate the effect of the proposed segmentation algorithm. The results showed that FGCF could significantly enhance the segmentation precision with the maximum increasing dice score of 0.18 compared to that with MeshSegNet method only. The average accuracy of all included testing cases was more than 93%. This two-stage segmentation algorithm could achieve precise and efficient segmentation of TL and FL, thus might assist in the treatment of AD in the future.

AB - Accurate segmentation for true lumen (TL) and false lumen (FL) is essential for the treatment of aortic dissection (AD) disease. However, the complex morphology of AD raised challenges for AD segmentation, especially for precise TL and FL separation. In this study, a novel two-stage algorithm based on the mesh model was developed to achieve the segmentation of TL and FL. In detail, a MeshSegNet was firstly applied to complete the coarse segmentation of AD and then fast geodesic curvature flow (FGCF) was used to optimize the segmentation result. A total of 150 type B AD cases were included to train and evaluate the effect of the proposed segmentation algorithm. The results showed that FGCF could significantly enhance the segmentation precision with the maximum increasing dice score of 0.18 compared to that with MeshSegNet method only. The average accuracy of all included testing cases was more than 93%. This two-stage segmentation algorithm could achieve precise and efficient segmentation of TL and FL, thus might assist in the treatment of AD in the future.

KW - Aortic dissection

KW - Deep learning

KW - Level set

KW - Mesh segmentation

UR - http://www.scopus.com/inward/record.url?scp=85165980276&partnerID=8YFLogxK

U2 - 10.1109/ICIBA56860.2023.10165320

DO - 10.1109/ICIBA56860.2023.10165320

M3 - Conference contribution

AN - SCOPUS:85165980276

T3 - Proceedings of 2023 IEEE 3rd International Conference on Information Technology, Big Data and Artificial Intelligence, ICIBA 2023

SP - 337

EP - 341

BT - Proceedings of 2023 IEEE 3rd International Conference on Information Technology, Big Data and Artificial Intelligence, ICIBA 2023

A2 - Xu, Bing

A2 - Mou, Kefen

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 3rd IEEE International Conference on Information Technology, Big Data and Artificial Intelligence, ICIBA 2023

Y2 - 26 May 2023 through 28 May 2023

ER -

Cheng G, Xiong J, Chen D. Automatic segmentation of true lumen and false lumen of aortic dissection based on a two-stage learning framework. In Xu B, Mou K, editors, Proceedings of 2023 IEEE 3rd International Conference on Information Technology, Big Data and Artificial Intelligence, ICIBA 2023. Institute of Electrical and Electronics Engineers Inc. 2023. p. 337-341. (Proceedings of 2023 IEEE 3rd International Conference on Information Technology, Big Data and Artificial Intelligence, ICIBA 2023). doi: 10.1109/ICIBA56860.2023.10165320

Automatic segmentation of true lumen and false lumen of aortic dissection based on a two-stage learning framework

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this