Class-Based Attention Mechanism for Chest Radiograph Multi-Label Categorization

David Sriker; Hayit Greenspan; Jacob Goldberger

doi:10.1109/isbi52829.2022.9761667

Class-Based Attention Mechanism for Chest Radiograph Multi-Label Categorization

David Sriker, Hayit Greenspan, Jacob Goldberger

Tel Aviv University

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

2 Scopus citations

Abstract

This work focuses on a new methodology for class-based attention, which is an extension to the more common image-based attention mechanism. The class-based attention mechanism learns a different attention mask for each class. This enables to simultaneously apply a different localization procedure for different pathologies in the same image, thus important for a multilabel categorization. We apply the method to detect and localize a set of pathologies in chest Radiographs. The proposed network architecture was evaluated on publicly available X-ray datasets and yielded improved classification results compared to standard image based attention.

Original language	English
Title of host publication	ISBI 2022 - Proceedings
Subtitle of host publication	2022 IEEE International Symposium on Biomedical Imaging
Publisher	IEEE Computer Society
ISBN (Electronic)	9781665429238
DOIs	https://doi.org/10.1109/isbi52829.2022.9761667
State	Published - 2022
Event	19th IEEE International Symposium on Biomedical Imaging, ISBI 2022 - Kolkata, India Duration: 28 Mar 2022 → 31 Mar 2022

Publication series

Name	Proceedings - International Symposium on Biomedical Imaging
Volume	2022-March
ISSN (Print)	1945-7928
ISSN (Electronic)	1945-8452

Conference

Conference	19th IEEE International Symposium on Biomedical Imaging, ISBI 2022
Country/Territory	India
City	Kolkata
Period	28/03/22 → 31/03/22

Bibliographical note

Publisher Copyright:
© 2022 IEEE.

Funding

This research was supported by the Ministry of Science & Technology, Israel.

Funders	Funder number
Ministry of science and technology, Israel

Keywords

X-ray
attention mechanism
chest
localization

Access to Document

10.1109/isbi52829.2022.9761667

Cite this

@inproceedings{0a4141a063274ff5a0ac33d44d46700c,

title = "Class-Based Attention Mechanism for Chest Radiograph Multi-Label Categorization",

abstract = "This work focuses on a new methodology for class-based attention, which is an extension to the more common image-based attention mechanism. The class-based attention mechanism learns a different attention mask for each class. This enables to simultaneously apply a different localization procedure for different pathologies in the same image, thus important for a multilabel categorization. We apply the method to detect and localize a set of pathologies in chest Radiographs. The proposed network architecture was evaluated on publicly available X-ray datasets and yielded improved classification results compared to standard image based attention.",

keywords = "X-ray, attention mechanism, chest, localization",

author = "David Sriker and Hayit Greenspan and Jacob Goldberger",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 19th IEEE International Symposium on Biomedical Imaging, ISBI 2022 ; Conference date: 28-03-2022 Through 31-03-2022",

year = "2022",

doi = "10.1109/isbi52829.2022.9761667",

language = "אנגלית",

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

publisher = "IEEE Computer Society",

booktitle = "ISBI 2022 - Proceedings",

address = "ארצות הברית",

}

Sriker, D, Greenspan, H & Goldberger, J 2022, Class-Based Attention Mechanism for Chest Radiograph Multi-Label Categorization. in ISBI 2022 - Proceedings: 2022 IEEE International Symposium on Biomedical Imaging. Proceedings - International Symposium on Biomedical Imaging, vol. 2022-March, IEEE Computer Society, 19th IEEE International Symposium on Biomedical Imaging, ISBI 2022, Kolkata, India, 28/03/22. https://doi.org/10.1109/isbi52829.2022.9761667

Class-Based Attention Mechanism for Chest Radiograph Multi-Label Categorization. / Sriker, David; Greenspan, Hayit; Goldberger, Jacob.
ISBI 2022 - Proceedings: 2022 IEEE International Symposium on Biomedical Imaging. IEEE Computer Society, 2022. (Proceedings - International Symposium on Biomedical Imaging; Vol. 2022-March).

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

TY - GEN

T1 - Class-Based Attention Mechanism for Chest Radiograph Multi-Label Categorization

AU - Sriker, David

AU - Greenspan, Hayit

AU - Goldberger, Jacob

PY - 2022

Y1 - 2022

N2 - This work focuses on a new methodology for class-based attention, which is an extension to the more common image-based attention mechanism. The class-based attention mechanism learns a different attention mask for each class. This enables to simultaneously apply a different localization procedure for different pathologies in the same image, thus important for a multilabel categorization. We apply the method to detect and localize a set of pathologies in chest Radiographs. The proposed network architecture was evaluated on publicly available X-ray datasets and yielded improved classification results compared to standard image based attention.

AB - This work focuses on a new methodology for class-based attention, which is an extension to the more common image-based attention mechanism. The class-based attention mechanism learns a different attention mask for each class. This enables to simultaneously apply a different localization procedure for different pathologies in the same image, thus important for a multilabel categorization. We apply the method to detect and localize a set of pathologies in chest Radiographs. The proposed network architecture was evaluated on publicly available X-ray datasets and yielded improved classification results compared to standard image based attention.

KW - X-ray

KW - attention mechanism

KW - chest

KW - localization

UR - http://www.scopus.com/inward/record.url?scp=85129643358&partnerID=8YFLogxK

U2 - 10.1109/isbi52829.2022.9761667

DO - 10.1109/isbi52829.2022.9761667

M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???

AN - SCOPUS:85129643358

T3 - Proceedings - International Symposium on Biomedical Imaging

BT - ISBI 2022 - Proceedings

PB - IEEE Computer Society

T2 - 19th IEEE International Symposium on Biomedical Imaging, ISBI 2022

Y2 - 28 March 2022 through 31 March 2022

ER -

Class-Based Attention Mechanism for Chest Radiograph Multi-Label Categorization

Abstract

Publication series

Conference

Bibliographical note

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this