Automated layer segmentation of macular OCT images via graph-based SLIC superpixels and manifold ranking approach

详细信息    查看全文

• 作者：Zhijun Gao^a ; ^b ; ^{zhjgao@163.com} ; Wei Bu^c ; ^{buwei@hit.edu.cn} ; Yalin Zheng^d ; Xiangqian Wu^a
• 关键词：Optical coherence tomography (OCT) ; Segmentation ; Graph ; SLIC superpixels ; Manifold ranking
• 刊名：Computerized Medical Imaging and Graphics
• 出版年：2017
• 出版时间：January 2017
• 年：2017
• 卷：55
• 期：Complete
• 页码：42-53
• 全文大小：5443 K
• 卷排序：55

文摘

The weighted graphs are constructed to well represent OCT images. The connected components can avoid some disturbs from the intrinsic speckle noise and organic texture artifacts. The SLIC superpixels method is used to segment 2D OCT images. The manifold ranking method is used to exactly detect the boundaries of 2D OCT images.