Translator Disclaimer
Paper
10 March 2020 Group-wise attention fusion network for choroid segmentation in OCT images
Author Affiliations +
Abstract
The choroid is an important structure of the eye and choroid thickness distribution estimated from optical coherence tomography (OCT) images plays a vital role in analysis of many retinal diseases. This paper proposes a novel group-wise attention fusion network (referred to as GAF-Net) to segment the choroid layer, which can effectively work for both normal and pathological myopia retina. Currently, most networks perform unified processing of all feature maps in the same layer, which leads to not satisfactory choroid segmentation results. In order to improve this , GAF-Net proposes a group-wise channel module (GCM) and a group-wise spatial module (GSM) to fuse group-wise information. The GCM uses channel information to guide the fusion of group-wise context information, while the GSM uses spatial information to guide the fusion of group-wise context information. Furthermore, we adopt a joint loss to solve the problem of data imbalance and the uneven choroid target area. Experimental evaluations on a dataset composed of 1650 clinically obtained B-scans show that the proposed GAF-Net can achieve a Dice similarity coefficient of 95.21±0.73%.
© (2020) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Xuena Cheng, Xinjian Chen, Shuanglang Feng, Weifang Zhu, Dehui Xiang, Qiuying Chen, Xun Xu, Ying Fan, and Fei Shi "Group-wise attention fusion network for choroid segmentation in OCT images", Proc. SPIE 11313, Medical Imaging 2020: Image Processing, 1131332 (10 March 2020); https://doi.org/10.1117/12.2548277
PROCEEDINGS
7 PAGES


SHARE
Advertisement
Advertisement
Back to Top