Multi-modality network based on CGAN and attention mechanism for glaucoma grading

Ling Liu; Yuanyuan Peng; Dehui Xiang; Fei Shi; Xinjian Chen

doi:10.1117/12.2654113

3 April 2023 Multi-modality network based on CGAN and attention mechanism for glaucoma grading

Ling Liu, Yuanyuan Peng, Dehui Xiang, Fei Shi, Xinjian Chen

Proceedings Volume 12464, Medical Imaging 2023: Image Processing; 124643L (2023) https://doi.org/10.1117/12.2654113
Event: SPIE Medical Imaging, 2023, San Diego, California, United States

Conference Poster

Abstract

Glaucoma is a progressive optic neuropathy characterized by changes in the structure of the optic nerve head and visual field which is one of the major irreversible blinding eye diseases worldwide. Early screening and timely diagnosis of glaucoma is of significant importance. In recent years, multi-modal deep learning methods have shown great advantages in image classification and segmentation tasks. In this paper, we propose a multi-modal glaucoma grading network with two main contributions: (1) To address the inherent shortage of multi-modal training data, conditional generative adversarial network (CGAN) is used to generate more synthetic images, extending the dataset over the only available dataset. (2) A multi-modality cross-attention (MMCA) module is proposed to further improve the classification accuracy.

Citation Download Citation

Ling Liu, Yuanyuan Peng, Dehui Xiang, Fei Shi, and Xinjian Chen "Multi-modality network based on CGAN and attention mechanism for glaucoma grading", Proc. SPIE 12464, Medical Imaging 2023: Image Processing, 124643L (3 April 2023); https://doi.org/10.1117/12.2654113

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