arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2108.05269eess.IVcs.CGcs.CVcs.LG
收藏

光滑流形三角剖分中二值分割模板中体素重排的学习

Learning to Rearrange Voxels in Binary Segmentation Masks for Smooth Manifold Triangulation

Graz University of Technology(格拉茨技术大学);Computer Algorithms for Medicine Laboratory (Café-Lab)(医学计算机算法实验室(Café-Lab));Medical University Graz(格拉茨医科大学);University Hospital Essen(埃森大学医院);ZhejiangLab(之江实验室)

Jianning Li, Antonio Pepe, Christina Gsaxner, Yuan Jin, Jan Egger

摘要:

医学图像,特别是体积图像,具有高分辨率,通常超过标准桌面GPU的容量。因此,大多数基于深度学习的医学图像分析任务需要对输入图像进行下采样,通常是大幅下采样,然后才能将这些图像馈送到神经网络。然而,下采样可能导致图像质量的损失,这是不期望的,特别是在需要保留精细几何细节的重建任务中。在本文中,我们提出可以以粗到细的方式重建高分辨率图像,其中深度学习算法仅负责生成图像的粗略表示,这会消耗适度的GPU内存。为了产生高分辨率的结果,我们提出了两种新的方法:学习体素重排的粗输出和分层图像合成。与粗略的输出相比,高分辨率的对应部分允许平滑的表面三角测量,可以以最高的质量进行3D打印。本文的实验是在AutoImplant 2021(https://autoimplant2021.grand-challenge.org/)数据集上进行的,这是一个关于颅骨植入物设计的MICCAI挑战。该数据集包含高分辨率的头骨,可以被视为嵌入在3D空间中的2D流形。与本研究相关的代码可访问https://github.com/Jianningli/voxel_rearrangement。

英文摘要:

Medical images, especially volumetric images, are of high resolution and often exceed the capacity of standard desktop GPUs. As a result, most deep learning-based medical image analysis tasks require the input images to be downsampled, often substantially, before these can be fed to a neural network. However, downsampling can lead to a loss of image quality, which is undesirable especially in reconstruction tasks, where the fine geometric details need to be preserved. In this paper, we propose that high-resolution images can be reconstructed in a coarse-to-fine fashion, where a deep learning algorithm is only responsible for generating a coarse representation of the image, which consumes moderate GPU memory. For producing the high-resolution outcome, we propose two novel methods: learned voxel rearrangement of the coarse output and hierarchical image synthesis. Compared to the coarse output, the high-resolution counterpart allows for smooth surface triangulation, which can be 3D-printed in the highest possible quality. Experiments of this paper are carried out on the dataset of AutoImplant 2021 (https://autoimplant2021.grand-challenge.org/), a MICCAI challenge on cranial implant design. The dataset contains high-resolution skulls that can be viewed as 2D manifolds embedded in a 3D space. Codes associated with this study can be accessed at https://github.com/Jianningli/voxel_rearrangement.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑