Training data independent image registration with gans using transfer learning and segmentation information

Dwarikanath Mahapatra; Zongyuan Ge

doi:10.1109/ISBI.2019.8759247

Training data independent image registration with gans using transfer learning and segmentation information

Dwarikanath Mahapatra, Zongyuan Ge

Monash e-Research Centre

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

18 Citations (Scopus)

Abstract

Registration is an important task in automated medical image analysis. Although deep learning (DL) based image registration methods out perform time consuming conventional approaches, they are heavily dependent on training data and do not generalize well for new images types. We present a DL based approach that can register an image pair which is different from the training images. This is achieved by training generative adversarial networks (GANs) in combination with segmentation information and transfer learning. Experiments on chest Xray and brain MR images show that our method gives better registration performance over conventional methods.

Original language	English
Title of host publication	Proceedings of 2019 IEEE International Symposium on Biomedical Imaging
Editors	Erik Meijering, Marius George Linguraru
Place of Publication	United States
Publisher	IEEE, Institute of Electrical and Electronics Engineers
Pages	709-713
Number of pages	5
ISBN (Electronic)	9781538636411
ISBN (Print)	9781538636404
DOIs	https://doi.org/10.1109/ISBI.2019.8759247
Publication status	Published - 2019
Event	IEEE International Symposium on Biomedical Imaging (ISBI) 2019 - Hilton Molino Stucky, Venice, Italy Duration: 8 Apr 2019 → 11 Apr 2019 Conference number: 16th https://ieeexplore.ieee.org/xpl/conhome/8754684/proceeding (Proceedings)

Publication series

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

Conference

Conference	IEEE International Symposium on Biomedical Imaging (ISBI) 2019
Abbreviated title	ISBI 2019
Country/Territory	Italy
City	Venice
Period	8/04/19 → 11/04/19
Internet address	https://ieeexplore.ieee.org/xpl/conhome/8754684/proceeding (Proceedings)

Keywords

Gans
Mri
Registration
Segmentation
Transfer learning
Xray

Access to Document

10.1109/ISBI.2019.8759247

Cite this

Mahapatra, D., & Ge, Z. (2019). Training data independent image registration with gans using transfer learning and segmentation information. In E. Meijering, & M. G. Linguraru (Eds.), Proceedings of 2019 IEEE International Symposium on Biomedical Imaging (pp. 709-713). (Proceedings - International Symposium on Biomedical Imaging). IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/ISBI.2019.8759247

Mahapatra, Dwarikanath ; Ge, Zongyuan. / Training data independent image registration with gans using transfer learning and segmentation information. Proceedings of 2019 IEEE International Symposium on Biomedical Imaging. editor / Erik Meijering ; Marius George Linguraru. United States : IEEE, Institute of Electrical and Electronics Engineers, 2019. pp. 709-713 (Proceedings - International Symposium on Biomedical Imaging).

@inproceedings{a0232e74c52446308f2ebe4edc05d3dd,

title = "Training data independent image registration with gans using transfer learning and segmentation information",

abstract = "Registration is an important task in automated medical image analysis. Although deep learning (DL) based image registration methods out perform time consuming conventional approaches, they are heavily dependent on training data and do not generalize well for new images types. We present a DL based approach that can register an image pair which is different from the training images. This is achieved by training generative adversarial networks (GANs) in combination with segmentation information and transfer learning. Experiments on chest Xray and brain MR images show that our method gives better registration performance over conventional methods.",

keywords = "Gans, Mri, Registration, Segmentation, Transfer learning, Xray",

author = "Dwarikanath Mahapatra and Zongyuan Ge",

year = "2019",

doi = "10.1109/ISBI.2019.8759247",

language = "English",

isbn = "9781538636404",

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

publisher = "IEEE, Institute of Electrical and Electronics Engineers",

pages = "709--713",

editor = "Erik Meijering and Linguraru, {Marius George}",

booktitle = "Proceedings of 2019 IEEE International Symposium on Biomedical Imaging",

address = "United States of America",

note = "IEEE International Symposium on Biomedical Imaging (ISBI) 2019, ISBI 2019 ; Conference date: 08-04-2019 Through 11-04-2019",

url = "https://ieeexplore.ieee.org/xpl/conhome/8754684/proceeding",

}

Mahapatra, D & Ge, Z 2019, Training data independent image registration with gans using transfer learning and segmentation information. in E Meijering & MG Linguraru (eds), Proceedings of 2019 IEEE International Symposium on Biomedical Imaging. Proceedings - International Symposium on Biomedical Imaging, IEEE, Institute of Electrical and Electronics Engineers, United States, pp. 709-713, IEEE International Symposium on Biomedical Imaging (ISBI) 2019, Venice, Italy, 8/04/19. https://doi.org/10.1109/ISBI.2019.8759247

Training data independent image registration with gans using transfer learning and segmentation information. / Mahapatra, Dwarikanath; Ge, Zongyuan.
Proceedings of 2019 IEEE International Symposium on Biomedical Imaging. ed. / Erik Meijering; Marius George Linguraru. United States: IEEE, Institute of Electrical and Electronics Engineers, 2019. p. 709-713 (Proceedings - International Symposium on Biomedical Imaging).

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

TY - GEN

T1 - Training data independent image registration with gans using transfer learning and segmentation information

AU - Mahapatra, Dwarikanath

AU - Ge, Zongyuan

N1 - Conference code: 16th

PY - 2019

Y1 - 2019

N2 - Registration is an important task in automated medical image analysis. Although deep learning (DL) based image registration methods out perform time consuming conventional approaches, they are heavily dependent on training data and do not generalize well for new images types. We present a DL based approach that can register an image pair which is different from the training images. This is achieved by training generative adversarial networks (GANs) in combination with segmentation information and transfer learning. Experiments on chest Xray and brain MR images show that our method gives better registration performance over conventional methods.

AB - Registration is an important task in automated medical image analysis. Although deep learning (DL) based image registration methods out perform time consuming conventional approaches, they are heavily dependent on training data and do not generalize well for new images types. We present a DL based approach that can register an image pair which is different from the training images. This is achieved by training generative adversarial networks (GANs) in combination with segmentation information and transfer learning. Experiments on chest Xray and brain MR images show that our method gives better registration performance over conventional methods.

KW - Gans

KW - Mri

KW - Registration

KW - Segmentation

KW - Transfer learning

KW - Xray

UR - http://www.scopus.com/inward/record.url?scp=85073913232&partnerID=8YFLogxK

U2 - 10.1109/ISBI.2019.8759247

DO - 10.1109/ISBI.2019.8759247

M3 - Conference Paper

AN - SCOPUS:85073913232

SN - 9781538636404

T3 - Proceedings - International Symposium on Biomedical Imaging

SP - 709

EP - 713

BT - Proceedings of 2019 IEEE International Symposium on Biomedical Imaging

A2 - Meijering, Erik

A2 - Linguraru, Marius George

PB - IEEE, Institute of Electrical and Electronics Engineers

CY - United States

T2 - IEEE International Symposium on Biomedical Imaging (ISBI) 2019

Y2 - 8 April 2019 through 11 April 2019

ER -

Mahapatra D, Ge Z. Training data independent image registration with gans using transfer learning and segmentation information. In Meijering E, Linguraru MG, editors, Proceedings of 2019 IEEE International Symposium on Biomedical Imaging. United States: IEEE, Institute of Electrical and Electronics Engineers. 2019. p. 709-713. (Proceedings - International Symposium on Biomedical Imaging). doi: 10.1109/ISBI.2019.8759247

Training data independent image registration with gans using transfer learning and segmentation information

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Cite this