Semantic segmentation of intracranial hemorrhages in head CT scans

Yuhang Qiu; Chia Shuo Chang; Jiun Lin Yan; Li Ko; Tian Sheuan Chang

doi:10.1109/ICSESS47205.2019.9040733

Semantic segmentation of intracranial hemorrhages in head CT scans

Yuhang Qiu, Chia Shuo Chang, Jiun Lin Yan, Li Ko, Tian Sheuan Chang

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

42 Scopus citations

Abstract

This paper presents a semantic segmentation method that can distinguish six different types of intracranial hemorrhage and calculate the amount of blood loss. The major challenge of medical image segmentation are the lack of enough data due to the difficulty of data collection and labeling. In this paper, we propose to adopt a pretrained U-Net model with fine tuning to solve this problem. The best final test accuracy can reach 94.1%, which is 10.5% higher than the model training from scratch, proving its advantages in dealing with relatively complex datasets with a small amount of data, and the success of the proposed segmentation method.

Original language	English
Title of host publication	Proceedings of 2019 IEEE 10th International Conference on Software Engineering and Service Science, ICSESS 2019
Editors	Wenzheng Li, M. Surendra Prasad Babu
Publisher	IEEE Computer Society
Pages	112-115
Number of pages	4
ISBN (Electronic)	9781728109459
DOIs	https://doi.org/10.1109/ICSESS47205.2019.9040733
State	Published - 10 2019
Externally published	Yes
Event	10th IEEE International Conference on Software Engineering and Service Science, ICSESS 2019 - Beijing, China Duration: 18 10 2019 → 20 10 2019

Publication series

Name	Proceedings of the IEEE International Conference on Software Engineering and Service Sciences, ICSESS
Volume	2019-October
ISSN (Print)	2327-0586
ISSN (Electronic)	2327-0594

Conference

Conference	10th IEEE International Conference on Software Engineering and Service Science, ICSESS 2019
Country/Territory	China
City	Beijing
Period	18/10/19 → 20/10/19

Bibliographical note

Publisher Copyright:
© 2019 IEEE.

Keywords

Blood loss
Intracranial hemorrhage
Pretrained
Segmentation
U-Net

Access to Document

10.1109/ICSESS47205.2019.9040733

Cite this

Qiu, Y., Chang, C. S., Yan, J. L., Ko, L., & Chang, T. S. (2019). Semantic segmentation of intracranial hemorrhages in head CT scans. In W. Li, & M. S. P. Babu (Eds.), Proceedings of 2019 IEEE 10th International Conference on Software Engineering and Service Science, ICSESS 2019 (pp. 112-115). Article 9040733 (Proceedings of the IEEE International Conference on Software Engineering and Service Sciences, ICSESS; Vol. 2019-October). IEEE Computer Society. https://doi.org/10.1109/ICSESS47205.2019.9040733

Qiu, Yuhang ; Chang, Chia Shuo ; Yan, Jiun Lin et al. / Semantic segmentation of intracranial hemorrhages in head CT scans. Proceedings of 2019 IEEE 10th International Conference on Software Engineering and Service Science, ICSESS 2019. editor / Wenzheng Li ; M. Surendra Prasad Babu. IEEE Computer Society, 2019. pp. 112-115 (Proceedings of the IEEE International Conference on Software Engineering and Service Sciences, ICSESS).

@inproceedings{3e21ec85ae63486dacf2a5dfd1875a18,

title = "Semantic segmentation of intracranial hemorrhages in head CT scans",

abstract = "This paper presents a semantic segmentation method that can distinguish six different types of intracranial hemorrhage and calculate the amount of blood loss. The major challenge of medical image segmentation are the lack of enough data due to the difficulty of data collection and labeling. In this paper, we propose to adopt a pretrained U-Net model with fine tuning to solve this problem. The best final test accuracy can reach 94.1\%, which is 10.5\% higher than the model training from scratch, proving its advantages in dealing with relatively complex datasets with a small amount of data, and the success of the proposed segmentation method.",

keywords = "Blood loss, Intracranial hemorrhage, Pretrained, Segmentation, U-Net",

author = "Yuhang Qiu and Chang, \{Chia Shuo\} and Yan, \{Jiun Lin\} and Li Ko and Chang, \{Tian Sheuan\}",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 10th IEEE International Conference on Software Engineering and Service Science, ICSESS 2019 ; Conference date: 18-10-2019 Through 20-10-2019",

year = "2019",

month = oct,

doi = "10.1109/ICSESS47205.2019.9040733",

language = "英语",

series = "Proceedings of the IEEE International Conference on Software Engineering and Service Sciences, ICSESS",

publisher = "IEEE Computer Society",

pages = "112--115",

editor = "Wenzheng Li and Babu, \{M. Surendra Prasad\}",

booktitle = "Proceedings of 2019 IEEE 10th International Conference on Software Engineering and Service Science, ICSESS 2019",

address = "美国",

}

Qiu, Y, Chang, CS, Yan, JL, Ko, L & Chang, TS 2019, Semantic segmentation of intracranial hemorrhages in head CT scans. in W Li & MSP Babu (eds), Proceedings of 2019 IEEE 10th International Conference on Software Engineering and Service Science, ICSESS 2019., 9040733, Proceedings of the IEEE International Conference on Software Engineering and Service Sciences, ICSESS, vol. 2019-October, IEEE Computer Society, pp. 112-115, 10th IEEE International Conference on Software Engineering and Service Science, ICSESS 2019, Beijing, China, 18/10/19. https://doi.org/10.1109/ICSESS47205.2019.9040733

Semantic segmentation of intracranial hemorrhages in head CT scans. / Qiu, Yuhang; Chang, Chia Shuo; Yan, Jiun Lin et al.
Proceedings of 2019 IEEE 10th International Conference on Software Engineering and Service Science, ICSESS 2019. ed. / Wenzheng Li; M. Surendra Prasad Babu. IEEE Computer Society, 2019. p. 112-115 9040733 (Proceedings of the IEEE International Conference on Software Engineering and Service Sciences, ICSESS; Vol. 2019-October).

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

TY - GEN

T1 - Semantic segmentation of intracranial hemorrhages in head CT scans

AU - Qiu, Yuhang

AU - Chang, Chia Shuo

AU - Yan, Jiun Lin

AU - Ko, Li

AU - Chang, Tian Sheuan

PY - 2019/10

Y1 - 2019/10

N2 - This paper presents a semantic segmentation method that can distinguish six different types of intracranial hemorrhage and calculate the amount of blood loss. The major challenge of medical image segmentation are the lack of enough data due to the difficulty of data collection and labeling. In this paper, we propose to adopt a pretrained U-Net model with fine tuning to solve this problem. The best final test accuracy can reach 94.1%, which is 10.5% higher than the model training from scratch, proving its advantages in dealing with relatively complex datasets with a small amount of data, and the success of the proposed segmentation method.

AB - This paper presents a semantic segmentation method that can distinguish six different types of intracranial hemorrhage and calculate the amount of blood loss. The major challenge of medical image segmentation are the lack of enough data due to the difficulty of data collection and labeling. In this paper, we propose to adopt a pretrained U-Net model with fine tuning to solve this problem. The best final test accuracy can reach 94.1%, which is 10.5% higher than the model training from scratch, proving its advantages in dealing with relatively complex datasets with a small amount of data, and the success of the proposed segmentation method.

KW - Blood loss

KW - Intracranial hemorrhage

KW - Pretrained

KW - Segmentation

KW - U-Net

UR - https://www.scopus.com/pages/publications/85082847186

U2 - 10.1109/ICSESS47205.2019.9040733

DO - 10.1109/ICSESS47205.2019.9040733

M3 - 会议稿件

AN - SCOPUS:85082847186

T3 - Proceedings of the IEEE International Conference on Software Engineering and Service Sciences, ICSESS

SP - 112

EP - 115

BT - Proceedings of 2019 IEEE 10th International Conference on Software Engineering and Service Science, ICSESS 2019

A2 - Li, Wenzheng

A2 - Babu, M. Surendra Prasad

PB - IEEE Computer Society

T2 - 10th IEEE International Conference on Software Engineering and Service Science, ICSESS 2019

Y2 - 18 October 2019 through 20 October 2019

ER -

Qiu Y, Chang CS, Yan JL, Ko L, Chang TS. Semantic segmentation of intracranial hemorrhages in head CT scans. In Li W, Babu MSP, editors, Proceedings of 2019 IEEE 10th International Conference on Software Engineering and Service Science, ICSESS 2019. IEEE Computer Society. 2019. p. 112-115. 9040733. (Proceedings of the IEEE International Conference on Software Engineering and Service Sciences, ICSESS). doi: 10.1109/ICSESS47205.2019.9040733

Semantic segmentation of intracranial hemorrhages in head CT scans

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this