A Novel Knowledge Keeper Network for 7T-Free but 7T-Guided Brain Tissue Segmentation

Jieun Lee; Kwanseok Oh; Dinggang Shen; Heung Il Suk

doi:10.1007/978-3-031-16443-9_32

A Novel Knowledge Keeper Network for 7T-Free but 7T-Guided Brain Tissue Segmentation

Jieun Lee, Kwanseok Oh, Dinggang Shen, Heung Il Suk

Department of Artificial Intelligence

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

2 Citations (Scopus)

Abstract

An increase in signal-to-noise ratio (SNR) and susceptibility-induced contrast at higher field strengths, e.g., 7T, is crucial for medical image analysis by providing better insights for the pathophysiology, diagnosis, and treatment of several disease entities. However, it is difficult to obtain 7T images in real clinical practices due to the high cost and low accessibility. In this paper, we propose a novel knowledge keeper network (KKN) to guide brain tissue segmentation by taking advantage of 7T representations without explicitly using 7T images. By extracting features of a 3T input image substantially and then transforming them to 7T features via knowledge distillation (KD), our method achieves deriving 7T-like representations from a given 3T image and exploits them for tissue segmentation. On two independent datasets, we evaluated our method’s validity in qualitative and quantitative manners on 7T-like image synthesis and 7T-guided tissue segmentation by comparing with the comparative methods in the literature.

Original language	English
Title of host publication	Medical Image Computing and Computer Assisted Intervention – MICCAI 2022 - 25th International Conference, Proceedings
Editors	Linwei Wang, Qi Dou, P. Thomas Fletcher, Stefanie Speidel, Shuo Li
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	330-339
Number of pages	10
ISBN (Print)	9783031164422
DOIs	https://doi.org/10.1007/978-3-031-16443-9_32
Publication status	Published - 2022
Event	25th International Conference on Medical Image Computing and Computer-Assisted Intervention, MICCAI 2022 - Singapore, Singapore Duration: 2022 Sept 18 → 2022 Sept 22

Publication series

Name	Lecture Notes in Computer Science
Volume	13435 LNCS
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Conference

Conference	25th International Conference on Medical Image Computing and Computer-Assisted Intervention, MICCAI 2022
Country/Territory	Singapore
City	Singapore
Period	22/9/18 → 22/9/22

Bibliographical note

Publisher Copyright:
© 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Keywords

7T MRI
Brain tissue segmentation
Knowledge distillation
Medical image synthesis

ASJC Scopus subject areas

Theoretical Computer Science
General Computer Science

Access to Document

10.1007/978-3-031-16443-9_32

Cite this

Lee, J., Oh, K., Shen, D., & Suk, H. I. (2022). A Novel Knowledge Keeper Network for 7T-Free but 7T-Guided Brain Tissue Segmentation. In L. Wang, Q. Dou, P. T. Fletcher, S. Speidel, & S. Li (Eds.), Medical Image Computing and Computer Assisted Intervention – MICCAI 2022 - 25th International Conference, Proceedings (pp. 330-339). (Lecture Notes in Computer Science; Vol. 13435 LNCS). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-031-16443-9_32

A Novel Knowledge Keeper Network for 7T-Free but 7T-Guided Brain Tissue Segmentation. / Lee, Jieun; Oh, Kwanseok; Shen, Dinggang et al.
Medical Image Computing and Computer Assisted Intervention – MICCAI 2022 - 25th International Conference, Proceedings. ed. / Linwei Wang; Qi Dou; P. Thomas Fletcher; Stefanie Speidel; Shuo Li. Springer Science and Business Media Deutschland GmbH, 2022. p. 330-339 (Lecture Notes in Computer Science; Vol. 13435 LNCS).

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

Lee, J, Oh, K, Shen, D & Suk, HI 2022, A Novel Knowledge Keeper Network for 7T-Free but 7T-Guided Brain Tissue Segmentation. in L Wang, Q Dou, PT Fletcher, S Speidel & S Li (eds), Medical Image Computing and Computer Assisted Intervention – MICCAI 2022 - 25th International Conference, Proceedings. Lecture Notes in Computer Science, vol. 13435 LNCS, Springer Science and Business Media Deutschland GmbH, pp. 330-339, 25th International Conference on Medical Image Computing and Computer-Assisted Intervention, MICCAI 2022, Singapore, Singapore, 22/9/18. https://doi.org/10.1007/978-3-031-16443-9_32

Lee J, Oh K, Shen D, Suk HI. A Novel Knowledge Keeper Network for 7T-Free but 7T-Guided Brain Tissue Segmentation. In Wang L, Dou Q, Fletcher PT, Speidel S, Li S, editors, Medical Image Computing and Computer Assisted Intervention – MICCAI 2022 - 25th International Conference, Proceedings. Springer Science and Business Media Deutschland GmbH. 2022. p. 330-339. (Lecture Notes in Computer Science). doi: 10.1007/978-3-031-16443-9_32

Lee, Jieun ; Oh, Kwanseok ; Shen, Dinggang et al. / A Novel Knowledge Keeper Network for 7T-Free but 7T-Guided Brain Tissue Segmentation. Medical Image Computing and Computer Assisted Intervention – MICCAI 2022 - 25th International Conference, Proceedings. editor / Linwei Wang ; Qi Dou ; P. Thomas Fletcher ; Stefanie Speidel ; Shuo Li. Springer Science and Business Media Deutschland GmbH, 2022. pp. 330-339 (Lecture Notes in Computer Science).

@inproceedings{7cfc0a0795164b7dad38a1c536ab96ce,

title = "A Novel Knowledge Keeper Network for 7T-Free but 7T-Guided Brain Tissue Segmentation",

abstract = "An increase in signal-to-noise ratio (SNR) and susceptibility-induced contrast at higher field strengths, e.g., 7T, is crucial for medical image analysis by providing better insights for the pathophysiology, diagnosis, and treatment of several disease entities. However, it is difficult to obtain 7T images in real clinical practices due to the high cost and low accessibility. In this paper, we propose a novel knowledge keeper network (KKN) to guide brain tissue segmentation by taking advantage of 7T representations without explicitly using 7T images. By extracting features of a 3T input image substantially and then transforming them to 7T features via knowledge distillation (KD), our method achieves deriving 7T-like representations from a given 3T image and exploits them for tissue segmentation. On two independent datasets, we evaluated our method{\textquoteright}s validity in qualitative and quantitative manners on 7T-like image synthesis and 7T-guided tissue segmentation by comparing with the comparative methods in the literature.",

keywords = "7T MRI, Brain tissue segmentation, Knowledge distillation, Medical image synthesis",

author = "Jieun Lee and Kwanseok Oh and Dinggang Shen and Suk, {Heung Il}",

note = "Publisher Copyright: {\textcopyright} 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.; 25th International Conference on Medical Image Computing and Computer-Assisted Intervention, MICCAI 2022 ; Conference date: 18-09-2022 Through 22-09-2022",

year = "2022",

doi = "10.1007/978-3-031-16443-9_32",

language = "English",

isbn = "9783031164422",

series = "Lecture Notes in Computer Science",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "330--339",

editor = "Linwei Wang and Qi Dou and Fletcher, {P. Thomas} and Stefanie Speidel and Shuo Li",

booktitle = "Medical Image Computing and Computer Assisted Intervention – MICCAI 2022 - 25th International Conference, Proceedings",

address = "Germany",

}

TY - GEN

T1 - A Novel Knowledge Keeper Network for 7T-Free but 7T-Guided Brain Tissue Segmentation

AU - Lee, Jieun

AU - Oh, Kwanseok

AU - Shen, Dinggang

AU - Suk, Heung Il

PY - 2022

Y1 - 2022

N2 - An increase in signal-to-noise ratio (SNR) and susceptibility-induced contrast at higher field strengths, e.g., 7T, is crucial for medical image analysis by providing better insights for the pathophysiology, diagnosis, and treatment of several disease entities. However, it is difficult to obtain 7T images in real clinical practices due to the high cost and low accessibility. In this paper, we propose a novel knowledge keeper network (KKN) to guide brain tissue segmentation by taking advantage of 7T representations without explicitly using 7T images. By extracting features of a 3T input image substantially and then transforming them to 7T features via knowledge distillation (KD), our method achieves deriving 7T-like representations from a given 3T image and exploits them for tissue segmentation. On two independent datasets, we evaluated our method’s validity in qualitative and quantitative manners on 7T-like image synthesis and 7T-guided tissue segmentation by comparing with the comparative methods in the literature.

AB - An increase in signal-to-noise ratio (SNR) and susceptibility-induced contrast at higher field strengths, e.g., 7T, is crucial for medical image analysis by providing better insights for the pathophysiology, diagnosis, and treatment of several disease entities. However, it is difficult to obtain 7T images in real clinical practices due to the high cost and low accessibility. In this paper, we propose a novel knowledge keeper network (KKN) to guide brain tissue segmentation by taking advantage of 7T representations without explicitly using 7T images. By extracting features of a 3T input image substantially and then transforming them to 7T features via knowledge distillation (KD), our method achieves deriving 7T-like representations from a given 3T image and exploits them for tissue segmentation. On two independent datasets, we evaluated our method’s validity in qualitative and quantitative manners on 7T-like image synthesis and 7T-guided tissue segmentation by comparing with the comparative methods in the literature.

KW - 7T MRI

KW - Brain tissue segmentation

KW - Knowledge distillation

KW - Medical image synthesis

UR - http://www.scopus.com/inward/record.url?scp=85138990141&partnerID=8YFLogxK

U2 - 10.1007/978-3-031-16443-9_32

DO - 10.1007/978-3-031-16443-9_32

M3 - Conference contribution

AN - SCOPUS:85138990141

SN - 9783031164422

T3 - Lecture Notes in Computer Science

SP - 330

EP - 339

BT - Medical Image Computing and Computer Assisted Intervention – MICCAI 2022 - 25th International Conference, Proceedings

A2 - Wang, Linwei

A2 - Dou, Qi

A2 - Fletcher, P. Thomas

A2 - Speidel, Stefanie

A2 - Li, Shuo

PB - Springer Science and Business Media Deutschland GmbH

T2 - 25th International Conference on Medical Image Computing and Computer-Assisted Intervention, MICCAI 2022

Y2 - 18 September 2022 through 22 September 2022

ER -