A texture-aware U-Net for identifying incomplete blinking from eye videography. (May 2022)

• Record Type: Journal Article
• Authors: Zheng, Qinxiang; Zhang, Xin; Zhang, Juan; Bai, Furong; Huang, Shenghai; Pu, Jiantao; Chen, Wei; Wang, Lei
• Is Part Of: Biomedical signal processing and control. Volume 75(2022)
• Publication Date: 2022-05
• Subjects: Incomplete blinking -- Eye videography -- Image segmentation -- Convolutional blocks; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2022.103630
• Languages: English
• ISSNs: 1746-8094

Abstract

Highlights: Three convolutional blocks were introduced based on element-wise subtraction operations. A novel segmentation network was developed by integrating the introduced blocks with the classical U-Net. Extensive experiments showed a unique advantage of the developed network in extracting palpebral fissures from frame images of eye videography. The developed network showed the feasibility of identifying incomplete blinking based on eye videography. Abstract: Accurate identification of incomplete blinking from eye videography is critical for the early detection of eye disorders or diseases (e.g., dry eye). In this study, we develop a texture-aware neural network based on the classical U-Net (termed TAU-Net) to accurately extract palpebral fissures from each frame of eye videography for assessing incomplete blinking. We introduced three different convolutional blocks based on element-wise subtraction operations to highlight subtle textures associated with target objects and integrated these blocks with the U-Net to improve the segmentation of palpebral fissures. Quantitative experiments on 1396 frame images showed that the developed network achieved an average Dice index of 0.9587 and a Hausdorff distance (HD) of 4.9462 pixels when applied to segment palpebral fissures. It outperformed the U-Net and its several variants, demonstrating a promising performance in identifying incomplete blinking based on eye videography.