Cross-Adversarial Local Distribution regularization for semi-supervised medical image segmentation

Thanh Nguyen-Duc; Trung Le; Roland Bammer; He Zhao; Jianfei Cai; Dinh Phung

doi:10.1007/978-3-031-43907-0_18

Cross-Adversarial Local Distribution regularization for semi-supervised medical image segmentation

Thanh Nguyen-Duc, Trung Le, Roland Bammer, He Zhao, Jianfei Cai, Dinh Phung

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

8 Citations (Scopus)

Abstract

Medical semi-supervised segmentation is a technique where a model is trained to segment objects of interest in medical images with limited annotated data. Existing semi-supervised segmentation methods are usually based on the smoothness assumption. This assumption implies that the model output distributions of two similar data samples are encouraged to be invariant. In other words, the smoothness assumption states that similar samples (e.g., adding small perturbations to an image) should have similar outputs. In this paper, we introduce a novel cross-adversarial local distribution (Cross-ALD) regularization to further enhance the smoothness assumption for semi-supervised medical image segmentation task. We conducted comprehensive experiments that the Cross-ALD archives state-of-the-art performance against many recent methods on the public LA and ACDC datasets.

Original language	English
Title of host publication	Medical Image Computing and Computer Assisted Intervention – 26th International Conference Vancouver, BC, Canada, October 8–12, 2023 Proceedings, Part I
Editors	Hayit Greenspan, Anant Madabhushi, Parvin Mousavi, Septimiu Salcudean, James Duncan, Tanveer Syeda-Mahmood, Russell Taylor
Place of Publication	Cham Switzerland
Publisher	Springer
Pages	183-194
Number of pages	12
ISBN (Electronic)	9783031439070
ISBN (Print)	9783031439063
DOIs	https://doi.org/10.1007/978-3-031-43907-0_18
Publication status	Published - 2023
Event	Medical Image Computing and Computer-Assisted Intervention 2023 - Vancouver, Canada Duration: 8 Oct 2023 → 12 Oct 2023 Conference number: 26th https://link.springer.com/book/10.1007/978-3-031-43901-8 (Proceedings) https://conferences.miccai.org/2023/en/ (Website)

Publication series

Name	Lecture Notes in Computer Science
Publisher	Springer
Volume	14220
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Conference

Conference	Medical Image Computing and Computer-Assisted Intervention 2023
Abbreviated title	MICCAI 2023
Country/Territory	Canada
City	Vancouver
Period	8/10/23 → 12/10/23
Internet address	https://link.springer.com/book/10.1007/978-3-031-43901-8 (Proceedings) https://conferences.miccai.org/2023/en/ (Website)

Keywords

Adversarial examples
Adversarial local distribution
Cross-adversarial local distribution
Semi-supervised segmentation

Access to Document

10.1007/978-3-031-43907-0_18

Cite this

Nguyen-Duc, T., Le, T., Bammer, R., Zhao, H., Cai, J., & Phung, D. (2023). Cross-Adversarial Local Distribution regularization for semi-supervised medical image segmentation. In H. Greenspan, A. Madabhushi, P. Mousavi, S. Salcudean, J. Duncan, T. Syeda-Mahmood, & R. Taylor (Eds.), Medical Image Computing and Computer Assisted Intervention – 26th International Conference Vancouver, BC, Canada, October 8–12, 2023 Proceedings, Part I (pp. 183-194). (Lecture Notes in Computer Science; Vol. 14220). Springer. https://doi.org/10.1007/978-3-031-43907-0_18

Nguyen-Duc, Thanh ; Le, Trung ; Bammer, Roland et al. / Cross-Adversarial Local Distribution regularization for semi-supervised medical image segmentation. Medical Image Computing and Computer Assisted Intervention – 26th International Conference Vancouver, BC, Canada, October 8–12, 2023 Proceedings, Part I. editor / Hayit Greenspan ; Anant Madabhushi ; Parvin Mousavi ; Septimiu Salcudean ; James Duncan ; Tanveer Syeda-Mahmood ; Russell Taylor. Cham Switzerland : Springer, 2023. pp. 183-194 (Lecture Notes in Computer Science).

@inproceedings{ec4f1f632e1749b4977854b525ec9427,

title = "Cross-Adversarial Local Distribution regularization for semi-supervised medical image segmentation",

abstract = "Medical semi-supervised segmentation is a technique where a model is trained to segment objects of interest in medical images with limited annotated data. Existing semi-supervised segmentation methods are usually based on the smoothness assumption. This assumption implies that the model output distributions of two similar data samples are encouraged to be invariant. In other words, the smoothness assumption states that similar samples (e.g., adding small perturbations to an image) should have similar outputs. In this paper, we introduce a novel cross-adversarial local distribution (Cross-ALD) regularization to further enhance the smoothness assumption for semi-supervised medical image segmentation task. We conducted comprehensive experiments that the Cross-ALD archives state-of-the-art performance against many recent methods on the public LA and ACDC datasets.",

keywords = "Adversarial examples, Adversarial local distribution, Cross-adversarial local distribution, Semi-supervised segmentation",

author = "Thanh Nguyen-Duc and Trung Le and Roland Bammer and He Zhao and Jianfei Cai and Dinh Phung",

note = "Funding Information: This work was partially supported by the Australian Defence Science and Technology (DST) Group under the Next Generation Technology Fund (NGTF) scheme. Dinh Phung further gratefully acknowledges the partial support from the Australian Research Council, project ARC DP230101176. Publisher Copyright: {\textcopyright} 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.; Medical Image Computing and Computer-Assisted Intervention 2023, MICCAI 2023 ; Conference date: 08-10-2023 Through 12-10-2023",

year = "2023",

doi = "10.1007/978-3-031-43907-0_18",

language = "English",

isbn = "9783031439063",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

pages = "183--194",

editor = "Hayit Greenspan and Anant Madabhushi and Parvin Mousavi and Septimiu Salcudean and James Duncan and Tanveer Syeda-Mahmood and Russell Taylor",

booktitle = "Medical Image Computing and Computer Assisted Intervention – 26th International Conference Vancouver, BC, Canada, October 8–12, 2023 Proceedings, Part I",

address = "Switzerland",

url = "https://link.springer.com/book/10.1007/978-3-031-43901-8, https://conferences.miccai.org/2023/en/",

}

Nguyen-Duc, T, Le, T , Bammer, R, Zhao, H, Cai, J & Phung, D 2023, Cross-Adversarial Local Distribution regularization for semi-supervised medical image segmentation. in H Greenspan, A Madabhushi, P Mousavi, S Salcudean, J Duncan, T Syeda-Mahmood & R Taylor (eds), Medical Image Computing and Computer Assisted Intervention – 26th International Conference Vancouver, BC, Canada, October 8–12, 2023 Proceedings, Part I. Lecture Notes in Computer Science, vol. 14220, Springer, Cham Switzerland, pp. 183-194, Medical Image Computing and Computer-Assisted Intervention 2023, Vancouver, British Columbia, Canada, 8/10/23. https://doi.org/10.1007/978-3-031-43907-0_18

Cross-Adversarial Local Distribution regularization for semi-supervised medical image segmentation. / Nguyen-Duc, Thanh; Le, Trung ; Bammer, Roland et al.
Medical Image Computing and Computer Assisted Intervention – 26th International Conference Vancouver, BC, Canada, October 8–12, 2023 Proceedings, Part I. ed. / Hayit Greenspan; Anant Madabhushi; Parvin Mousavi; Septimiu Salcudean; James Duncan; Tanveer Syeda-Mahmood; Russell Taylor. Cham Switzerland: Springer, 2023. p. 183-194 (Lecture Notes in Computer Science; Vol. 14220).

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

TY - GEN

T1 - Cross-Adversarial Local Distribution regularization for semi-supervised medical image segmentation

AU - Nguyen-Duc, Thanh

AU - Le, Trung

AU - Bammer, Roland

AU - Zhao, He

AU - Cai, Jianfei

AU - Phung, Dinh

N1 - Conference code: 26th

PY - 2023

Y1 - 2023

N2 - Medical semi-supervised segmentation is a technique where a model is trained to segment objects of interest in medical images with limited annotated data. Existing semi-supervised segmentation methods are usually based on the smoothness assumption. This assumption implies that the model output distributions of two similar data samples are encouraged to be invariant. In other words, the smoothness assumption states that similar samples (e.g., adding small perturbations to an image) should have similar outputs. In this paper, we introduce a novel cross-adversarial local distribution (Cross-ALD) regularization to further enhance the smoothness assumption for semi-supervised medical image segmentation task. We conducted comprehensive experiments that the Cross-ALD archives state-of-the-art performance against many recent methods on the public LA and ACDC datasets.

AB - Medical semi-supervised segmentation is a technique where a model is trained to segment objects of interest in medical images with limited annotated data. Existing semi-supervised segmentation methods are usually based on the smoothness assumption. This assumption implies that the model output distributions of two similar data samples are encouraged to be invariant. In other words, the smoothness assumption states that similar samples (e.g., adding small perturbations to an image) should have similar outputs. In this paper, we introduce a novel cross-adversarial local distribution (Cross-ALD) regularization to further enhance the smoothness assumption for semi-supervised medical image segmentation task. We conducted comprehensive experiments that the Cross-ALD archives state-of-the-art performance against many recent methods on the public LA and ACDC datasets.

KW - Adversarial examples

KW - Adversarial local distribution

KW - Cross-adversarial local distribution

KW - Semi-supervised segmentation

UR - http://www.scopus.com/inward/record.url?scp=85174584730&partnerID=8YFLogxK

U2 - 10.1007/978-3-031-43907-0_18

DO - 10.1007/978-3-031-43907-0_18

M3 - Conference Paper

AN - SCOPUS:85174584730

SN - 9783031439063

T3 - Lecture Notes in Computer Science

SP - 183

EP - 194

BT - Medical Image Computing and Computer Assisted Intervention – 26th International Conference Vancouver, BC, Canada, October 8–12, 2023 Proceedings, Part I

A2 - Greenspan, Hayit

A2 - Madabhushi, Anant

A2 - Mousavi, Parvin

A2 - Salcudean, Septimiu

A2 - Duncan, James

A2 - Syeda-Mahmood, Tanveer

A2 - Taylor, Russell

PB - Springer

CY - Cham Switzerland

T2 - Medical Image Computing and Computer-Assisted Intervention 2023

Y2 - 8 October 2023 through 12 October 2023

ER -

Nguyen-Duc T, Le T , Bammer R, Zhao H, Cai J , Phung D. Cross-Adversarial Local Distribution regularization for semi-supervised medical image segmentation. In Greenspan H, Madabhushi A, Mousavi P, Salcudean S, Duncan J, Syeda-Mahmood T, Taylor R, editors, Medical Image Computing and Computer Assisted Intervention – 26th International Conference Vancouver, BC, Canada, October 8–12, 2023 Proceedings, Part I. Cham Switzerland: Springer. 2023. p. 183-194. (Lecture Notes in Computer Science). doi: 10.1007/978-3-031-43907-0_18

Cross-Adversarial Local Distribution regularization for semi-supervised medical image segmentation

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Exploiting Geometries of Learning for Fast, Adaptive and Robust AI

Cite this

Cross-Adversarial Local Distribution regularization for semi-supervised medical image segmentation

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Projects

Exploiting Geometries of Learning for Fast, Adaptive and Robust AI

Cite this