Meibomian glands dysfunction (MGD) is the main cause of dry eyes. The degree of meibomian gland atrophy plays an important role in the clinical diagnosis of MGD. The automatic quantification of meibomian gland area (MGA) and meibomian gland atrophy area (MGAA) is challenging due to the blurred boundary and various shapes. A U-shaped information fusion network (IF-Net) is proposed for the segmentation of MGA and MGAA in this paper. The contributions of this paper are as follows: (1) An information fusion (IF) module is designed to fuse the context information from the spatial dimension and the channel dimension respectively, which effectively reduces the loss of information caused by continuous downsampling. (2) A parallel path connection (PPC) is proposed and inserted into skip connections. On one hand, it can suppress the noise of different levels of information. On the other hand, it can make up the lack of information via the original simple skip connection of U-Net. Our proposed IF-Net has been evaluated on 505 infrared MG images from 300 subjects and achieves the average Dice similarity coefficient (DSC) of 84.81% and the average intersection over union (IoU) of 74.44% on MGAA segmentation, which indicates the primary effectiveness of the proposed method.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
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.