医学三维影像体数据闭值分割方法

建立医学三维体数据阈值分割描述模型,把OSTU图像分割算法和梯度算子图像分割算法的思想应用于三维体数据,提出并实现了两种医学三维体数据阈值分割算法,并通过实验证明这两种算法获得了较好的分割效果。为进一步对体数据阈值分割算法的性能进行量化评价,定义了两个量化指标:分割准确度和分割平衡度,并通过实验给出了上述两种体数据阈值分割算法的性能评价指标。在给定体数据和标准分割的前提下,OSTU算法比梯度算子算法能取得更好的阈值分割效果。     

GPU-accelerated level-set segmentation

The level-set method, a technique for the computation of evolving interfaces, is a solution commonly used to segment images and volumes in medical applications. GPUs have become a commodity hardware with hundreds of cores that can execute thousands of threads in parallel, and they are nowadays ideal platforms to execute computational intensive tasks, such as the 3D level-set-based segmentation, in real time. In this paper, we propose two GPU implementations of the level-set-based segmentation method called Fast Two-Cycle. Our proposals perform computations in independent domains called tiles and modify the structure of the original algorithm to better exploit the features of the GPU. The implementations were tested with real images of brain vessels and a synthetic MRI image of the brain. Results show that they execute faster than a CPU-sequential implementation of the same method, without any significant loss of the segmentation quality and without requiring distributed parallel computer infrastructures.     

GPU-based point radiation for interactive volume sculpting and segmentation

Internal structures, features, and properties in volumetric datasets are mostly obscured and hidden. In order to reveal and explore them, appropriate tools are required to remove and carve the occluding materials and isolate and extract different regions of interest. We introduce a framework of interactive tools for real-time volume sculpting and segmentation. We utilize a GPU-based point radiation technique as a fundamental building block to create a collection of high-quality volume manipulation tools for direct drilling, lasering, peeling, and cutting/pasting. In addition, we enable interactive parallel region growing segmentation that allows multiple seed planting by direct sketching on different volumetric regions with segmentation results dynamically modified during the process. We use the same point radiation technique to create high-quality real-time feedback of the segmented regions during the seed growing process. We present results obtained from raw and segmented medical volume datasets.     

GPU加速的交互式医学CT图像区域分割

目的 为了解决交互式医学CT图像区域分割问题,本文提出了基于证据推理规则的区域生长算法(ERRG)。方法 算法综合考虑了医学图像的灰度直方图,Gabor特征和灰度共生矩阵能量3个重要特征,采用Bhattacharyya系数度量相邻像素的相似程度,用效用函数将度量系数合并。针对算法计算效率较低问题,对算法进行并行化,采用GPU进行加速处理。结果 本文算法与基于Random-Walk图像分割算法针对医学CT胃部图像,进行对比实验,表明使用本文算法,真阳性目标像素数占目标区域所有正确像素数的比例(TPF)显著提高,背景像素错误地分割为目标像素的数目占背景正确像素数的比例(FPF)显著降低;通过GPU加速后,算法执行效率显著提高,加速比达到12。结论 本文算法减少了医学CT图像过分割现象,采用GPU加速后能够实现实时交互式医学CT图像分割。     

A Variational Framework for Region-Based Segmentation Incorporating Physical Noise Models

Image segmentation is one of the fundamental problems in computer vision and image processing. In the recent years mathematical models based on partial differential equations and variational methods have led to superior results in many applications, e.g., medical imaging. A majority of works on image segmentation implicitly assume the given image to be biased by additive Gaussian noise, for instance the popular Mumford-Shah model. Since this assumption is not suitable for a variety of problems, we propose a region-based variational segmentation framework to segment also images with non-Gaussian noise models. Motivated by applications in biomedical imaging, we discuss the cases of Poisson and multiplicative speckle noise intensively. Analytical results such as the existence of a solution are verified and we investigate the use of different regularization functionals to provide a-priori information regarding the expected solution. The performance of the proposed framework is illustrated by experimental results on synthetic and real data.     

Hybrid multi-GPU computing: accelerated kernels for segmentation and object detection with medical image processing applications

In the last two decades, we have seen an amazing development of image processing techniques targeted for medical applications. We propose multi-GPU-based parallel real-time algorithms for segmentation and shape-based object detection, aiming at accelerating two medical image processing methods: automated blood detection in wireless capsule endoscopy (WCE) images and automated bright lesion detection in retinal fundus images. In the former method we identified segmentation and object detection as being responsible for consuming most of the global processing time. While in the latter, as segmentation was not used, shape-based object detection was the compute-intensive task identified. Experimental results show that the accelerated method running on multi-GPU systems for blood detection in WCE images is on average 265 times faster than the original CPU version and is able to process 344 frames per second. By applying the multi-GPU framework for bright lesion detection in fundus images we are able to process 62 frames per second with a speedup average 667 times faster than the equivalent CPU version.     

Multi-panel medical image segmentation framework for image retrieval system

The automatic segmentation of multi-panel medical images into sub-images improves the retrieval accuracy of medical image retrieval systems. However, the accuracy and efficiency of the available multi-panel medical image segmentation techniques are not satisfactory for multi-panel images containing homogenous color inter-panel borders and image boundary, heterogeneous color inter-panel borders, small size sub-images, or numerous number of sub-images. In order to improve the accuracy and efficiency, a Multi-panel Medical Image Segmentation Framework (MIS-Framework) is proposed and implemented based on locating the longest inter-panel border inside the boundary of the input image. We evaluated the proposed framework on a subset of imageCLEF 2013 dataset containing 2407 images. The proposed framework showed promising experimental results in terms of accuracy and efficiency on single panel as well as multi-panel image class identification and on sub-image separation as compared to the available techniques.     

结合边界的小波域马尔科夫模型的图像分割算法

针对基于马尔科夫随机场(MRF)的分割算法常存在边界块效应,且对整幅图像进行建模运行效率低等问题,提出了结合边界的小波域马尔科夫模型的图像分割算法,把影像的特征场建立在一系列小波域提取的边界上,并建立相应的边界标号场MRF模型,借助贝叶斯框架和SMAP准则实现分割。利用Matlab GUI实现了分割系统,通过医学图像检验,结果表明:相比于小波域分层随机场模型(WMSRF),该算法在有效区分不同区域的同时很好地保留了边界信息,提高了运行效率。     

生成对抗式网络及其医学影像应用研究综述

生成对抗式网络(generative adversarial network, GAN)由负责学习数据分布的生成器和负责鉴别样本真伪的判别器构成,二者在相互对抗过程中互相学习逐渐变强。该网络模型使深度学习方法可以自动学习损失函数,减少了对专家知识的依赖,已经广泛应用于自然图像处理领域,对解决医学影像处理的相关瓶颈问题亦具有巨大应用前景。本文旨在找到生成对抗式网络与医学影像领域面临挑战的结合点,通过分析已有工作对未来研究方向进行展望,为该领域研究提供参考。1)阐述了生成对抗式网络的基本原理,从任务拆分、条件约束以及图像到图像的翻译等角度对其衍生模型进行分析回顾;2)对生成对抗式网络在医学影像领域中的数据增广、模态迁移、图像分割以及去噪等方面的应用进行回顾,分析各方法的优缺点与适用范围;3)对现有图像生成质量评估方法进行小结;4)总结生成对抗式网络在医学影像领域的研究进展,并结合该领域问题特性,指出现有理论应用存在的不足与改进方向。生成对抗式网络提出以来,理论不断完善,在医学影像的处理应用中也取得了长足发展,但仍然存在一些亟待解决的问题,包括3维数据合成、几何结构合理性保持、无标记和未配对...     

Graph-based tools for microscopic cellular image segmentation

We propose a framework of graph-based tools for the segmentation of microscopic cellular images. This framework is based on an object oriented analysis of imaging problems in pathology. Our graph tools rely on a general formulation of discrete functional regularization on weighted graphs of arbitrary topology. It leads to a set of useful tools which can be combined together to address various image segmentation problems in pathology. To provide fast image segmentation algorithms, we also propose an image simplification based on graphs as a pre processing step. The abilities of this set of image processing discrete tools are illustrated through automatic and interactive segmentation schemes for color cytological and histological images segmentation problems.     

Optimal surface segmentation in volumetric images--a graph-theoretic approach

Efficient segmentation of globally optimal surfaces representing object boundaries in volumetric data sets is important and challenging in many medical image analysis applications. We have developed an optimal surface detection method capable of simultaneously detecting multiple interacting surfaces, in which the optimality is controlled by the cost functions designed for individual surfaces and by several geometric constraints defining the surface smoothness and interrelations. The method solves the surface segmentation problem by transforming it into computing a minimum s-t cut in a derived arc-weighted directed graph. The proposed algorithm has a low-order polynomial time complexity and is computationally efficient. It has been extensively validated on more than 300 computer-synthetic volumetric images, 72 CT-scanned data sets of different-sized plexiglas tubes, and tens of medical images spanning various imaging modalities. In all cases, the approach yielded highly accurate results. Our approach can be readily extended to higher-dimensional image segmentation.     

基于级联随机森林与活动轮廓的3D MR图像分割

针对医学磁共振（Magnetic resonance，MR）图像三维分割中随机森林（Random forest，RF）方法难以获得具有几何约束的结果以及活动轮廓模型（Active contour model，ACM）不能自动分割发生信号混叠的组织结构的问题，提出了一种整合了级联随机森林与活动轮廓模型的磁共振图像三维分割方法.该方法首先从多模态磁共振体数据中提取图像多尺度局部鲁棒统计信息，以此驱动级联随机森林对磁共振图像进行迭代的体素分类，从而获得对组织结构的初步分割结果，进一步将此结果作为初始轮廓与形状先验，整合进一个尺度可调的活动轮廓模型中，将独立的体素分类转化为轮廓曲线演化，最终得到具有几何约束的精确分割结果.在公开数据集上的实验结果表明，本文的自动化分割方法在分割精度和鲁棒性等方面，相比其他同类方法具有较大的性能提升.     

An improved image analogy method based on adaptive CUDA-accelerated neighborhood matching framework

The image analogy framework is especially useful to synthesize appealing images for non-homogeneous input and gives users creative control over the synthesized results. However, the traditional framework did not adaptively employ the searching strategy based on neighborhood’s different textural contents. Besides, the synthesis speed is slow due to intensive computation involved in neighborhood matching. In this paper we present a CUDA-based neighborhood matching algorithm for image analogy. Our algorithm adaptively applies the global search of the exact L ₂ nearest neighbor and k-coherence search strategies during synthesis according to different textural features of images, which is especially usefully for non-homogeneous textures. To consistently implement the above two search strategies on GPU, we adopt the fast k nearest neighbor searching algorithm based on CUDA. Such an acceleration greatly reduces the time of the pre-process of k-coherence search and the synthesis procedure of the global search, which makes possible the adjustment of important synthesis parameters. We further adopt synthesis magnification to get the final high-resolution synthesis image for running efficiency. Experimental results show that our algorithm is suitable for various applications of the image analogy framework and takes full advantage of GPU’s parallel processing capability to improve synthesis speed and get satisfactory synthesis results.     

Sketch‐Based Editing Tools for Tumour Segmentation in 3D Medical Images

In the past years sophisticated automatic segmentation algorithms for various medical image segmentation problems have been developed. However, there are always cases where automatic algorithms fail to provide an acceptable segmentation. In these cases the user needs efficient segmentation editing tools, a problem which has not received much attention in research. We give a comprehensive overview on segmentation editing for three‐dimensional (3D) medical images. For segmentation editing in two‐dimensional (2D) images, we discuss a sketch‐based approach where the user modifies the segmentation in the contour domain. Based on this 2D interface, we present an image‐based as well as an image‐independent method for intuitive and efficient segmentation editing in 3D in the context of tumour segmentation in computed tomography (CT). Our editing tools have been evaluated on a database containing 1226 representative liver metastases, lung nodules and lymph nodes of different shape, size and image quality. In addition, we have performed a qualitative evaluation with radiologists and technical experts, proving the efficiency of our tools.     

基于模糊聚类的脑磁共振图像分割算法综述

磁共振成像（Magnetic resonance imaging, MRI） 技术以其非介入、无损伤以及不受目标运动影响等特点,已成为临床诊断的重要辅助手段。精确的脑MR图像分割对生物医学研究和临床应用具有重要的指导意义。在实际应用中,脑MR图像中存在的噪声、灰度不均匀性、部分容积效应和低对比度等缺陷,都给脑MR图像的 精确分割带来了巨大困难和挑战。本文基于模糊聚类模型的脑MR图像分割问题,从聚类类别数的确定、模型初始化、克服噪声、估计偏移场、克服部分容积效应、数据不确定性描述以及模型扩展7个方面深入阐述了国内外发展现状、应对技巧及改进策略,并分析存在的不足 ,指出进一步的研究方向。     

并行多尺度特征融合的热层析图像分割算法

热层析技术应用于医学乳腺肿瘤检测具有重要的应用前景,但是医生在临床应用过程中,通过热层析图像诊断容易出现主观差异性误诊现象,为此,提出了一种智能化分割算法用于辅助诊断。然而,医学热层析图像由于目前数据量匮乏,且病灶区域占比小,依靠经典的分割模型,如FCN、U-Net容易出现分割不连续,边界细节分割不精细等问题。设计了一种基于并行多尺度特征融合的语义分割模型,模型通过并行的多分辨率特征子网之间反复的信息交换,在保证分割结果语义信息准确之外,还能有效地抓取病灶区域的细节特征。该方法在热层析医学图像数据集上取得了0.635?7的均交并比,相较于经典的U-Net分割网络,取得了5.14个百分点的提升,在肿块和血管等小目标区域的细节分割上有着更出色的表现。实验结果表明,该算法对热层析临床用于乳腺癌的辅助诊断具有现实意义。     

基于GPU的四维医学图像动态快速体绘制

传统的三维医学图像重建技术无法满足四维医学图像动态重建的需求,而四维医学图像庞大的数据量使传统重建技术很难实现高性能实时绘制.基于以上需求,提出了一种四维医学图像动态快速体绘制方法.首先采用GPU强大的并行计算能力,提出一种基于GPU、利用CUDA技术实现的光线投射算法;然后分析了算法框架、体数据及计算结果的存储策略、...     

基于GPU的快速Level Set图像分割

水平集(1evel set)图像分割方法是图像分割中的一个重要方法，但是该算法的计算量大，往往不能达到实时处理的要求。给出了利用新一代的可编程图形处理器(GPU)实现level set的加速算法。首先介绍了如何在GPU上利用片元渲染程序进行网格化的线性运算和有限差分PDE计算，把level set方法的离散化算子映射到GPU上。由于以数据流处理方式的GPU的存储访问快，具有并行运算能力，同时level set算法演化的显示不再需要把数据从CPU传到GPU，因此较大地提高了算法速度与交互显示。文中实现并测试了一个与初始化状态独立的二维level set的算子用于图像分割，并对其运算结果和性能进行了比较，结果表明该方法具有更快的速度。     

基于Snake模型的图像分割新算法

针对目前基于Snake模型的图像分割算法普遍存在噪声鲁棒性差、适用范围受限、易发生弱边缘泄露以及轮廓曲线难以收敛到细小深凹边界的缺陷,提出了一种基于Snake模型的图像分割新算法。首先,选取新的扩散项代替具有各向同性光滑作用的拉普拉斯算子;其次,引入p-拉普拉斯泛函到平滑能量项中强化法线方向外力;最后,利用边缘保护项使外力场方向与边缘方向一致,以防止弱边缘泄漏并促使轮廓线收敛到细小深凹边界。实验结果表明,所提模型不仅克服了现有基于Snake模型的图像分割算法的缺陷,具有更好的分割效果,明显提高了抗噪性能和角点定位精度,而且耗时更少,适用于噪声图像、医学图像以及含有很多弱边缘的自然图像分割。