Graph loss function for unsupervised learning-based deformable medical image registration

Sheng Lan; Bo Yuan; Zhenhua Guo

doi:10.1117/12.2580634

15 February 2021 Graph loss function for unsupervised learning-based deformable medical image registration

Sheng Lan, Bo Yuan, Zhenhua Guo

Proceedings Volume 11596, Medical Imaging 2021: Image Processing; 115960P (2021) https://doi.org/10.1117/12.2580634
Event: SPIE Medical Imaging, 2021, Online Only

Abstract

Establishing accurate spatial correspondences is the main purpose for deformable medical image registration. Although many unsupervised learning-based methods have been proposed in this field and achieved fairly good results, because of their strong feature extraction ability and no need of the ground truth, they are often limited by relying on similarity of the spatially adjacent pixels which could not fully utilize geometrical feature for robust registration. To address this limitation, we propose a new graph loss function to represent the non-adjacent geometrical similarity. We divide the algorithm into two branches. The first branch takes pairs of medical images as input directly and obtains the loss term ^LCNN by typical convolution operation. In the second branch, we convert the images to forms of graph represents, and then obtain the loss term ^LGCN by graph convolution operation. Finally, the sum of the two loss terms constitute the total loss function. We verify our method on two datasets including LPBA40 and ADNI, and the experimental results demonstrate a marked improvement, with higher average Dice and lower registration errors of MSE compared with state-of-the-art methods.

Conference Presentation

Citation Download Citation

Sheng Lan, Bo Yuan, and Zhenhua Guo "Graph loss function for unsupervised learning-based deformable medical image registration", Proc. SPIE 11596, Medical Imaging 2021: Image Processing, 115960P (15 February 2021); https://doi.org/10.1117/12.2580634

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
9 PAGES + PRESENTATION

DOWNLOAD PAPER SAVE TO MY LIBRARY

WATCH
PRESENTATION

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Image registration

Medical imaging

Convolution

Machine learning

Surgery

Feature extraction

RELATED CONTENT

An optimized volumetric approach to unsupervised image registration
Proceedings of SPIE (May 31 2022)

Application of attention mechanism in image search
Proceedings of SPIE (March 28 2023)

Quadratic autoencoder for low-dose CT denoising
Proceedings of SPIE (May 28 2019)

A novel approach for tuberculosis screening based on deep convolutional...
Proceedings of SPIE (March 24 2016)

A machine learning approach for classification of anatomical coverage in...
Proceedings of SPIE (March 24 2016)

Colonoscopic polyp detection using convolutional neural networks
Proceedings of SPIE (March 24 2016)

Fast interpolation operations in non-rigid image registration
Proceedings of SPIE (April 29 2005)

Subscribe to Digital Library

Receive Erratum Email Alert

Keywords/Phrases

Search In:

Publication Years