论文|Wenjun Xia, Zexin Lu, Yongqiang Huang, Zuoqiang Shi, Yan Liu, Hu Chen, Yang Chen*, Jiliu Zhou, and Yi Zhang*：MAGIC: Manifold and graph integrative convolutional network for low-dose CT reconstruction

本文（MAGIC: Manifold and graph integrative convolutional network for low-dose CT reconstruction）原载IEEE Transactions on Medical Imaging，由四川大学计算机学院张意教授等科研人员创作，系四川大学“智慧法治”超前部署学科系列学术成果。后续会持续分享四川大学“智慧法治”超前部署学科系列学术成果，欢迎大家阅读。

Abstract:Low-dose computed tomography (LDCT) scans, which can effectively alleviate the radiation problem, will degrade the imaging quality. In this paper, we propose a novel LDCT reconstruction network that unrolls the iterative scheme and performs in both image and manifold spaces. Because patch manifolds of medical images have low-dimensional structures, we can build graphs from the manifolds. Then, we simultaneously leverage the spatial convolution to extract the local pixel-level features from the images and incorporate the graph convolution to analyze the nonlocal topological features in manifold space. The experiments show that our proposed method outperforms both the quantitative and qualitative aspects of state-of-the-art methods. In addition, aided by a projection loss component, our proposed method also demonstrates superior performance for semi-supervised learning. The network can remove most noise while maintaining the details of only 10% (40 slices) of the training data labeled.

Wenjun Xia, Zexin Lu, Yongqiang Huang, Zuoqiang Shi, Yan Liu, Hu Chen, Yang Chen*, Jiliu Zhou, and Yi Zhang*. MAGIC: Manifold and graph integrative convolutional network for low-dose CT reconstruction. IEEE Transactions on Medical Imaging, DOI: 10.1109/TMI.2021.3088344, online, 2021.（论文下载）