Focal-balanced attention u-net with dynamic thresholding by spatial regression for segmentation of aortic dissection in CT imagery

Tsung Han Lee; Li Ting Huang; Paul Kuo; Chien Kuo Wang; Jiun In Guo

doi:10.1109/ISBI48211.2021.9434028

Focal-balanced attention u-net with dynamic thresholding by spatial regression for segmentation of aortic dissection in CT imagery

Tsung Han Lee, Li Ting Huang, Paul Kuo, Chien Kuo Wang, Jiun In Guo

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

6 Citations (Scopus)

Abstract

An aortic dissection has been reported a mortality of 50% within the first 48 hours and an increase of 1-2% per hour. Therefore, rapid diagnosis of intimal flap would be very important for the emergency treatment of patients. In order to accurately present the affected part of AD and reduce the time for doctors to diagnose, image segmentation is the most effective way of presentation. We used the U-Net model in this study and focus on AD (including ascending, arch, and descending part) in the detection process. Furthermore, we design the site and area regression (SAR) module. With this help of accurate prediction, we achieved slice-level sensitivity and specificity of 99.1 % and 93.2%, respectively.

Original language	English
Title of host publication	2021 IEEE 18th International Symposium on Biomedical Imaging, ISBI 2021
Publisher	IEEE Computer Society
Pages	541-544
Number of pages	4
ISBN (Electronic)	9781665412469
DOIs	https://doi.org/10.1109/ISBI48211.2021.9434028
Publication status	Published - 2021 Apr 13
Event	18th IEEE International Symposium on Biomedical Imaging, ISBI 2021 - Nice, France Duration: 2021 Apr 13 → 2021 Apr 16

Publication series

Name	Proceedings - International Symposium on Biomedical Imaging
Volume	2021-April
ISSN (Print)	1945-7928
ISSN (Electronic)	1945-8452

Conference

Conference	18th IEEE International Symposium on Biomedical Imaging, ISBI 2021
Country/Territory	France
City	Nice
Period	21-04-13 → 21-04-16

All Science Journal Classification (ASJC) codes

Biomedical Engineering
Radiology Nuclear Medicine and imaging

Access to Document

10.1109/ISBI48211.2021.9434028

Cite this

Lee, T. H., Huang, L. T., Kuo, P., Wang, C. K., & Guo, J. I. (2021). Focal-balanced attention u-net with dynamic thresholding by spatial regression for segmentation of aortic dissection in CT imagery. In 2021 IEEE 18th International Symposium on Biomedical Imaging, ISBI 2021 (pp. 541-544). Article 9434028 (Proceedings - International Symposium on Biomedical Imaging; Vol. 2021-April). IEEE Computer Society. https://doi.org/10.1109/ISBI48211.2021.9434028

@inproceedings{0ec6b05e73674224a54e86c8bf58b33b,

title = "Focal-balanced attention u-net with dynamic thresholding by spatial regression for segmentation of aortic dissection in CT imagery",

abstract = "An aortic dissection has been reported a mortality of 50% within the first 48 hours and an increase of 1-2% per hour. Therefore, rapid diagnosis of intimal flap would be very important for the emergency treatment of patients. In order to accurately present the affected part of AD and reduce the time for doctors to diagnose, image segmentation is the most effective way of presentation. We used the U-Net model in this study and focus on AD (including ascending, arch, and descending part) in the detection process. Furthermore, we design the site and area regression (SAR) module. With this help of accurate prediction, we achieved slice-level sensitivity and specificity of 99.1 % and 93.2%, respectively. ",

author = "Lee, {Tsung Han} and Huang, {Li Ting} and Paul Kuo and Wang, {Chien Kuo} and Guo, {Jiun In}",

note = "Publisher Copyright: {\textcopyright} 2021 IEEE.; 18th IEEE International Symposium on Biomedical Imaging, ISBI 2021 ; Conference date: 13-04-2021 Through 16-04-2021",

year = "2021",

month = apr,

day = "13",

doi = "10.1109/ISBI48211.2021.9434028",

language = "English",

series = "Proceedings - International Symposium on Biomedical Imaging",

publisher = "IEEE Computer Society",

pages = "541--544",

booktitle = "2021 IEEE 18th International Symposium on Biomedical Imaging, ISBI 2021",

address = "United States",

}

Lee, TH, Huang, LT, Kuo, P, Wang, CK & Guo, JI 2021, Focal-balanced attention u-net with dynamic thresholding by spatial regression for segmentation of aortic dissection in CT imagery. in 2021 IEEE 18th International Symposium on Biomedical Imaging, ISBI 2021., 9434028, Proceedings - International Symposium on Biomedical Imaging, vol. 2021-April, IEEE Computer Society, pp. 541-544, 18th IEEE International Symposium on Biomedical Imaging, ISBI 2021, Nice, France, 21-04-13. https://doi.org/10.1109/ISBI48211.2021.9434028

Focal-balanced attention u-net with dynamic thresholding by spatial regression for segmentation of aortic dissection in CT imagery. / Lee, Tsung Han; Huang, Li Ting; Kuo, Paul et al.
2021 IEEE 18th International Symposium on Biomedical Imaging, ISBI 2021. IEEE Computer Society, 2021. p. 541-544 9434028 (Proceedings - International Symposium on Biomedical Imaging; Vol. 2021-April).

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

TY - GEN

T1 - Focal-balanced attention u-net with dynamic thresholding by spatial regression for segmentation of aortic dissection in CT imagery

AU - Lee, Tsung Han

AU - Huang, Li Ting

AU - Kuo, Paul

AU - Wang, Chien Kuo

AU - Guo, Jiun In

PY - 2021/4/13

Y1 - 2021/4/13

N2 - An aortic dissection has been reported a mortality of 50% within the first 48 hours and an increase of 1-2% per hour. Therefore, rapid diagnosis of intimal flap would be very important for the emergency treatment of patients. In order to accurately present the affected part of AD and reduce the time for doctors to diagnose, image segmentation is the most effective way of presentation. We used the U-Net model in this study and focus on AD (including ascending, arch, and descending part) in the detection process. Furthermore, we design the site and area regression (SAR) module. With this help of accurate prediction, we achieved slice-level sensitivity and specificity of 99.1 % and 93.2%, respectively.

AB - An aortic dissection has been reported a mortality of 50% within the first 48 hours and an increase of 1-2% per hour. Therefore, rapid diagnosis of intimal flap would be very important for the emergency treatment of patients. In order to accurately present the affected part of AD and reduce the time for doctors to diagnose, image segmentation is the most effective way of presentation. We used the U-Net model in this study and focus on AD (including ascending, arch, and descending part) in the detection process. Furthermore, we design the site and area regression (SAR) module. With this help of accurate prediction, we achieved slice-level sensitivity and specificity of 99.1 % and 93.2%, respectively.

UR - http://www.scopus.com/inward/record.url?scp=85107207690&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85107207690&partnerID=8YFLogxK

U2 - 10.1109/ISBI48211.2021.9434028

DO - 10.1109/ISBI48211.2021.9434028

M3 - Conference contribution

AN - SCOPUS:85107207690

T3 - Proceedings - International Symposium on Biomedical Imaging

SP - 541

EP - 544

BT - 2021 IEEE 18th International Symposium on Biomedical Imaging, ISBI 2021

PB - IEEE Computer Society

T2 - 18th IEEE International Symposium on Biomedical Imaging, ISBI 2021

Y2 - 13 April 2021 through 16 April 2021

ER -

Lee TH, Huang LT, Kuo P, Wang CK, Guo JI. Focal-balanced attention u-net with dynamic thresholding by spatial regression for segmentation of aortic dissection in CT imagery. In 2021 IEEE 18th International Symposium on Biomedical Imaging, ISBI 2021. IEEE Computer Society. 2021. p. 541-544. 9434028. (Proceedings - International Symposium on Biomedical Imaging). doi: 10.1109/ISBI48211.2021.9434028

Focal-balanced attention u-net with dynamic thresholding by spatial regression for segmentation of aortic dissection in CT imagery

Abstract

Publication series

Conference

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this