All Attention U-NET for Semantic Segmentation of Intracranial Hemorrhages In Head CT Images

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

doi:10.1109/BioCAS54905.2022.9948588

All Attention U-NET for Semantic Segmentation of Intracranial Hemorrhages In Head CT Images

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

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

4 Scopus citations

Abstract

Intracranial hemorrhages in head CT scans serve as a first line tool to help specialists diagnose different types. However, their types have diverse shapes in the same type but similar confusing shape, size and location between types. To solve this problem, this paper proposes an all attention U-Net. It uses channel attentions in the U-Net encoder side to enhance class specific feature extraction, and space and channel attentions in the U-Net decoder side for more accurate shape extraction and type classification. The simulation results show up to a 31.8% improvement compared to baseline, ResNet50 + U-Net, and better performance than in cases with limited attention.

Original language	English
Title of host publication	BioCAS 2022 - IEEE Biomedical Circuits and Systems Conference
Subtitle of host publication	Intelligent Biomedical Systems for a Better Future, Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	600-604
Number of pages	5
ISBN (Electronic)	9781665469173
DOIs	https://doi.org/10.1109/BioCAS54905.2022.9948588
State	Published - 2022
Externally published	Yes
Event	2022 IEEE Biomedical Circuits and Systems Conference, BioCAS 2022 - Taipei, Taiwan Duration: 13 10 2022 → 15 10 2022

Publication series

Name	BioCAS 2022 - IEEE Biomedical Circuits and Systems Conference: Intelligent Biomedical Systems for a Better Future, Proceedings

Conference

Conference	2022 IEEE Biomedical Circuits and Systems Conference, BioCAS 2022
Country/Territory	Taiwan
City	Taipei
Period	13/10/22 → 15/10/22

Bibliographical note

Publisher Copyright:
© 2022 IEEE.

Keywords

Deep Learning
Head CT Scan
Intracranial Hemorrhage
Semantic Segmentation

Access to Document

10.1109/BioCAS54905.2022.9948588

Cite this

Shuo Chang, C., Sheuan Chang, T., Lin Yan, J., & Ko, L. (2022). All Attention U-NET for Semantic Segmentation of Intracranial Hemorrhages In Head CT Images. In BioCAS 2022 - IEEE Biomedical Circuits and Systems Conference: Intelligent Biomedical Systems for a Better Future, Proceedings (pp. 600-604). (BioCAS 2022 - IEEE Biomedical Circuits and Systems Conference: Intelligent Biomedical Systems for a Better Future, Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/BioCAS54905.2022.9948588

Shuo Chang, Chia ; Sheuan Chang, Tian ; Lin Yan, Jiun et al. / All Attention U-NET for Semantic Segmentation of Intracranial Hemorrhages In Head CT Images. BioCAS 2022 - IEEE Biomedical Circuits and Systems Conference: Intelligent Biomedical Systems for a Better Future, Proceedings. Institute of Electrical and Electronics Engineers Inc., 2022. pp. 600-604 (BioCAS 2022 - IEEE Biomedical Circuits and Systems Conference: Intelligent Biomedical Systems for a Better Future, Proceedings).

@inproceedings{8408f1a7c5ab46be8e3984cc1d620375,

title = "All Attention U-NET for Semantic Segmentation of Intracranial Hemorrhages In Head CT Images",

abstract = "Intracranial hemorrhages in head CT scans serve as a first line tool to help specialists diagnose different types. However, their types have diverse shapes in the same type but similar confusing shape, size and location between types. To solve this problem, this paper proposes an all attention U-Net. It uses channel attentions in the U-Net encoder side to enhance class specific feature extraction, and space and channel attentions in the U-Net decoder side for more accurate shape extraction and type classification. The simulation results show up to a 31.8\% improvement compared to baseline, ResNet50 + U-Net, and better performance than in cases with limited attention.",

keywords = "Deep Learning, Head CT Scan, Intracranial Hemorrhage, Semantic Segmentation",

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

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 2022 IEEE Biomedical Circuits and Systems Conference, BioCAS 2022 ; Conference date: 13-10-2022 Through 15-10-2022",

year = "2022",

doi = "10.1109/BioCAS54905.2022.9948588",

language = "英语",

series = "BioCAS 2022 - IEEE Biomedical Circuits and Systems Conference: Intelligent Biomedical Systems for a Better Future, Proceedings",

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

pages = "600--604",

booktitle = "BioCAS 2022 - IEEE Biomedical Circuits and Systems Conference",

address = "美国",

}

Shuo Chang, C, Sheuan Chang, T, Lin Yan, J & Ko, L 2022, All Attention U-NET for Semantic Segmentation of Intracranial Hemorrhages In Head CT Images. in BioCAS 2022 - IEEE Biomedical Circuits and Systems Conference: Intelligent Biomedical Systems for a Better Future, Proceedings. BioCAS 2022 - IEEE Biomedical Circuits and Systems Conference: Intelligent Biomedical Systems for a Better Future, Proceedings, Institute of Electrical and Electronics Engineers Inc., pp. 600-604, 2022 IEEE Biomedical Circuits and Systems Conference, BioCAS 2022, Taipei, Taiwan, 13/10/22. https://doi.org/10.1109/BioCAS54905.2022.9948588

All Attention U-NET for Semantic Segmentation of Intracranial Hemorrhages In Head CT Images. / Shuo Chang, Chia; Sheuan Chang, Tian; Lin Yan, Jiun et al.
BioCAS 2022 - IEEE Biomedical Circuits and Systems Conference: Intelligent Biomedical Systems for a Better Future, Proceedings. Institute of Electrical and Electronics Engineers Inc., 2022. p. 600-604 (BioCAS 2022 - IEEE Biomedical Circuits and Systems Conference: Intelligent Biomedical Systems for a Better Future, Proceedings).

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

TY - GEN

T1 - All Attention U-NET for Semantic Segmentation of Intracranial Hemorrhages In Head CT Images

AU - Shuo Chang, Chia

AU - Sheuan Chang, Tian

AU - Lin Yan, Jiun

AU - Ko, Li

PY - 2022

Y1 - 2022

N2 - Intracranial hemorrhages in head CT scans serve as a first line tool to help specialists diagnose different types. However, their types have diverse shapes in the same type but similar confusing shape, size and location between types. To solve this problem, this paper proposes an all attention U-Net. It uses channel attentions in the U-Net encoder side to enhance class specific feature extraction, and space and channel attentions in the U-Net decoder side for more accurate shape extraction and type classification. The simulation results show up to a 31.8% improvement compared to baseline, ResNet50 + U-Net, and better performance than in cases with limited attention.

AB - Intracranial hemorrhages in head CT scans serve as a first line tool to help specialists diagnose different types. However, their types have diverse shapes in the same type but similar confusing shape, size and location between types. To solve this problem, this paper proposes an all attention U-Net. It uses channel attentions in the U-Net encoder side to enhance class specific feature extraction, and space and channel attentions in the U-Net decoder side for more accurate shape extraction and type classification. The simulation results show up to a 31.8% improvement compared to baseline, ResNet50 + U-Net, and better performance than in cases with limited attention.

KW - Deep Learning

KW - Head CT Scan

KW - Intracranial Hemorrhage

KW - Semantic Segmentation

UR - https://www.scopus.com/pages/publications/85142936553

U2 - 10.1109/BioCAS54905.2022.9948588

DO - 10.1109/BioCAS54905.2022.9948588

M3 - 会议稿件

AN - SCOPUS:85142936553

T3 - BioCAS 2022 - IEEE Biomedical Circuits and Systems Conference: Intelligent Biomedical Systems for a Better Future, Proceedings

SP - 600

EP - 604

BT - BioCAS 2022 - IEEE Biomedical Circuits and Systems Conference

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2022 IEEE Biomedical Circuits and Systems Conference, BioCAS 2022

Y2 - 13 October 2022 through 15 October 2022

ER -

Shuo Chang C, Sheuan Chang T, Lin Yan J, Ko L. All Attention U-NET for Semantic Segmentation of Intracranial Hemorrhages In Head CT Images. In BioCAS 2022 - IEEE Biomedical Circuits and Systems Conference: Intelligent Biomedical Systems for a Better Future, Proceedings. Institute of Electrical and Electronics Engineers Inc. 2022. p. 600-604. (BioCAS 2022 - IEEE Biomedical Circuits and Systems Conference: Intelligent Biomedical Systems for a Better Future, Proceedings). doi: 10.1109/BioCAS54905.2022.9948588

All Attention U-NET for Semantic Segmentation of Intracranial Hemorrhages In Head CT Images

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this