Consecutive Context Perceive Generative Adversarial Networks for Serial Sections Inpainting
Consecutive Context Perceive Generative Adversarial Networks for Serial Sections Inpainting
复制标题
DOI：
10.1109/access.2020.3031973
复制
发表时间：
2020
期刊：
影响因子：
3.9
通讯作者：
Siqi Zhang;Lei Wang;Jie Zhang;Ling Gu;Xiran Jiang;Xiaoyue Zhai;Xianzheng Sha;Shijie Chang
中科院分区：
文献类型：
--
作者：
Siqi Zhang;Lei Wang;Jie Zhang;Ling Gu;Xiran Jiang;Xiaoyue Zhai;Xianzheng Sha;Shijie Chang
图像修复是计算机视觉领域的一个研究热点，已成功地应用于传统和数字媒体，如油画或旧照片修补、图像或视频去噪和超分辨率等。随着人工智能的引入，以语义修复为代表的一系列修复算法得到了发展，并取得了较好的效果。医学图像修复是医学图像修复中要求最高的应用之一，它既要满足视觉效果，又要满足严格的内容正确性要求。在组织学研究中，基于连续切片的显微结构三维重建可以提供更多的空间信息，帮助我们理解生理或病理生理机制，这就要求获得无缺陷的高质量连续图像。在这篇文章中，我们提出了一种新的用于连续切片修复的Concretive Context Perceive Generative Adversarial Networks（CCPGAN）。该方法能够从相邻图像中学习语义信息，最大限度地恢复连续切片图像的受损部分。用2组小鼠肾脏连续切片图像进行验证，定性和定量结果表明，我们的方法可以鲁棒地恢复任何大小和位置的破损，同时实现近实时性能。
Image inpainting is a hot topic in computer vision research and has been successfully applied to both traditional and digital mediums, such as oil paintings or old photos mending, image or video denoising and super-resolution. With the introduction of artificial intelligence (AI), a series of algorithms, represented by semantic inpainting, have been developed and better results were achieved. Medical image inpainting, as one of the most demanding applications, needs to meet both the visual effects and strict content correctness. 3D reconstruction of microstructures, based on serial sections, could provide more spatial information and help us understand the physiology or pathophysiology mechanism in histology study, in which extremely high-quality continuous images without any defects are required. In this article, we proposed a novel Consecutive Context Perceive Generative Adversarial Networks (CCPGAN) for serial sections inpainting. Our method can learn semantic information from its neighboring image, and restore the damaged parts of serial sectioning images to maximum extent. Validated with 2 sets of serial sectioning images of mouse kidney, qualitative and quantitative results suggested that our method could robustly restore breakage of any size and location while achieving near realtime performance.