Fast Segmentation From Blurred Data in 3D Fluorescence Microscopy
Fast Segmentation From Blurred Data in 3D Fluorescence Microscopy
复制标题
DOI：
10.1109/tip.2017.2716843
复制
发表时间：
2017-06
影响因子：
10.6
通讯作者：
M. Storath;Dennis Rickert;M. Unser;A. Weinmann
中科院分区：
文献类型：
--
作者：
M. Storath;Dennis Rickert;M. Unser;A. Weinmann
我们开发了一个快速算法分割的三维图像从线性测量的基础上Potts模型（或分段常数Mumford-Shah模型）。为此，我们首先推导出合适的空间离散化的3D波茨模型，这是能够处理定义在非立方网格的3D图像。我们的离散化使我们能够利用一个特定的分裂方法，这将导致解耦的子问题的中等大小。在3D设置的关键点是，独立的子问题的数量是如此之大，我们可以合理地利用图形处理单元（GPU）的并行处理能力。我们的GPU实现比顺序CPU版本快18倍。这允许在可接受的运行时间内处理甚至大的卷。作为进一步的贡献，我们扩展了算法，以处理非负约束。我们证明了我们的方法的效率相结合的图像去卷积和分割模拟数据和真实的三维宽场荧光显微镜数据。
We develop a fast algorithm for segmenting 3D images from linear measurements based on the Potts model (or piecewise constant Mumford-Shah model). To that end, we first derive suitable space discretizations of the 3D Potts model, which are capable of dealing with 3D images defined on non-cubic grids. Our discretization allows us to utilize a specific splitting approach, which results in decoupled subproblems of moderate size. The crucial point in the 3D setup is that the number of independent subproblems is so large that we can reasonably exploit the parallel processing capabilities of the graphics processing units (GPUs). Our GPU implementation is up to 18 times faster than the sequential CPU version. This allows to process even large volumes in acceptable runtimes. As a further contribution, we extend the algorithm in order to deal with non-negativity constraints. We demonstrate the efficiency of our method for combined image deconvolution and segmentation on simulated data and on real 3D wide field fluorescence microscopy data.