颅颌面CT与MR图像的配准

目的 :实现颅颌面CT MR医学图像的配准。材料和方法 :基于轮廓特征的奇异值分解 迭代最近点法 (SingularValueDecomposition IterativeClosestPoint ,SVD ICP)。结果 :该配准操作简便、图像满意、可靠性好 ,尚可以用于任意维度向量集合的匹配。结论 :在临床实践中颅颌面CT MR医学图像的配准是可行的 ,为进一步实现图像的融合奠定了基础     

锥形束CT图像分割方法研究进展

图像引导放射治疗(IGRT)是一种可视化的影像引导放疗技术, 具有提高肿瘤靶区剂量, 降低正常器官受照剂量等诸多优点。锥形束CT(CBCT)是IGRT中最常用的医学图像之一, 对CBCT进行快速、准确的靶区及危及器官的分割对放疗具有重大意义。目前的研究方法主要有基于配准的分割方法和基于深度学习的分割方法。本研究针对CBCT图像分割方法、存在问题及发展方向进行综述。     

基于新过渡区提取法的医学图像交互式分割

目的：为了提高医学图像三维重组过程中二维图像交互分割的效率,我们试验了一种新过渡区提取方法,并验证了其分割效率和分割效果。方法：新过渡区提取法先依据原始图像,分散构造过渡片段,后将过渡片段按一定规则连接成过渡区,在过渡区的基础上实现交互分割。以512×512的CT图像序列为样本进行实验,结果与基于边缘提取的交互分割法及完全手工分割法比较。结果：基于新过渡区提取的交互分割法对目标区域的分割精确度高于边缘提取分割法,更接近完全手工分割,而人工操作时间较基于边缘提取的分割法及完全手工分割法分别节省39%和62%。结论：新过渡区提取法保留了过渡区分割法抗干扰能力强、对弱边界提取效果好的优点。应用于交互分割,能够减少人工劳动,提高分割效率,同时分割精确度高于边缘提取法,重组后能更准确反映目标特征。     

从CT图像中自动分割出肺部区域的算法研究

目的为用于肺部疾病的计算机辅助诊断，研究设计从CT图像中提取肺部区域的自动分割算法。方法在最优闽值分割的基础上，用自动区域生长去除气管／支气管区域，对边界跟踪法进行改进以快速去除背景干扰和获得肺部边界，最后进行肺部边界修补得到完整的肺部图像。算法采用迭代法寻找最优阈值解决了阈值选取的敏感性问题，提出了基于前层图像中气管／支气管位置的气管／支气管提取方法，避免了种子点的人工选取，基于前次搜索方向改进了八邻域搜索方法来提高边界跟踪的速度：结果用该算法对不同病人的4组胸部CT序列进行处理，能自动、快速地分割出肺部区域且精度较高：结论提出的算法能有效地从CT图像中自动提取肺部区域。     

基于Snake模型的海马结构MR图像分割方法的应用研究

目的：介绍一种海马结构的磁共振图像分割方法Snake模型,并利用该模型对海马结构的磁共振图像进行分割研究。材料和方法：首先在MR图像工作站上采集图像,并进行图像预处理;然后编程,利用Snake模型进行海马结构的边缘检测,从磁共振图像中分割出海马结构。结果：除通过人机交互,由操作者给出初始轮廓外,Snake模型能从磁共振图像中自动分割出海马结构。Snake分割与人工分割总的重叠率是84％,标准差SD＝8．30。结论：Snake模型是一种快速、有效的海马结构分割方法,具有很强的鲁棒性和稳定性。     

基于边缘流的改进梯度矢量流算法及其在淋巴结超声图像分割中的应用

目的 提出一种基于边缘流的梯度矢量流（gradient vector flow，GVF）形变模型的图像分割方法，并用于淋巴结超声图像的分割。方法 综合图像灰度和纹理特征构造边缘流，使每点的边缘流矢量指向最近的边缘，再由边缘流扩散得到GVF场作为形变模型的外部势力，引导模型形变实现图像分割。结果 在给定4个标记点的条件下，实现了对淋巴结超声图像的半自动分割。结论 将边缘流引入GVF将明显改善对低对比度超声图像的分割效果。     

Matlab在医学图像分割处理中的应用

目的:通过Matlab软件处理,将医学图像中病灶部分轮廓更清晰地标记出来.材料和方法:利用Matlab平台对脑部肿瘤图像进行分割和形态学处理.结果:在图像像素不太大的情况下,通过编程,实施图像分割和形态处理,可以在维持原来图像的基础上,使原图像的轮廓明显清晰.结论:利用Matlab平台,通过对图像的分割和形态学运算可以使病灶部分变得更清晰.     

基于ACP方法的平行医学图像智能分析及其应用

近年来,人工智能技术在自然图像分析领域取得了巨大的进展。这些技术也被广泛应用于医学图像领域,以便更好地诊断、治疗疾病和判断预后。然而,由于医学图像在数据标注和专家知识方面的复杂性,使得这些技术的实际应用具有较大的挑战。本文基于ACP方法提出了一个融合医生智慧与计算智能的医学图像分析新框架——平行医学图像。传统的医学图像分析直接从带标注图像中学习模型而不能很好地解释诊断决策,平行医学图像引入了描述智能、预测智能和引导智能来提高模型的泛化能力和诊断的可解释性。我们采用平行闭环优化模型来挖掘并融合医学知识,从而优化辅助诊疗系统。最后,本文以乳腺癌为例探讨了平行医学图像框架在医学图像分析中的实际应用。     

基于信号互相关函数与神经网络的全自动图像配准算法

目的对多模态非刚性变换序列图像进行配准。方法将一种新的信号处理的概念引入配准过程，以两组具有时延特性的随机信号分别描述待配准的两幅医学图像的边缘特性，继而提出一种以信号互相关函数为性能指标，通过利用神经网络的泛化能力对轮廓特征点样本进行训练以得到最优变换参数的头部断层扫描图像自动配准算法。结果仿真结果表明该算法配准误差可达到亚象素级以下，且比之其他基于形状信息的配准算法具有寻优参数少，配准时间短，自动化程度高的特点。最后该算法被成功地应用到了做过开颅手术病人的CT—MRI图像融合上。结论该方法为多模态医学图像配准提供了一种新的有效手段。     

基于深度学习的CT图像肋骨自动分割与三维重组研究

目的 探讨基于卷积神经网络的深度学习模型在胸部CT图像上对肋骨区域的自动分割与三维重组的价值.方法 搜集2020年11月至2021年1月在本院行胸部CT检查者共130例(共计33280张轴位图像),以其中的80例作为训练集,20例作为测试集,来自另外三台不同CT设备的被检者各10例作为独立验证集,评价基于四种3D分割网...     

Dual-modality brain PET-CT image segmentation based on adaptive use of functional and anatomical information

Dual medical imaging modalities, such as PET-CT, are now a routine component of clinical practice. Medical image segmentation methods, however, have generally only been applied to single modality images. In this paper, we propose the dual-modality image segmentation model to segment brain PET-CT images into gray matter, white matter and cerebrospinal fluid. This model converts PET-CT image segmentation into an optimization process controlled simultaneously by PET and CT voxel values and spatial constraints. It is innovative in the creation and application of the modality discriminatory power (MDP) coefficient as a weighting scheme to adaptively combine the functional (PET) and anatomical (CT) information on a voxel-by-voxel basis. Our approach relies upon allowing the modality with higher discriminatory power to play a more important role in the segmentation process. We compared the proposed approach to three other image segmentation strategies, including PET-only based segmentation, combination of the results of independent PET image segmentation and CT image segmentation, and simultaneous segmentation of joint PET and CT images without an adaptive weighting scheme. Our results in 21 clinical studies showed that our approach provides the most accurate and reliable segmentation for brain PET-CT images.     

An image processing strategy for the quantification and visualization of exercise-induced muscle MRI signal enhancement

Exercise increases the skeletal muscle water signal in T2-weighted images. Potential medical applications of MR studies of exercise-induced muscle signal intensity changes are the assessment of myopathies, sport training regimens, and physical therapy approaches following surgeries. We developed an automated image processing technique that provides volumetric analysis and visualization of exercise-related T2-weighted image intensity changes. The image processing was applied to the segmentation and quantification of activated muscle volumes. Qualitative assessment of muscle activation is demonstrated with three-dimensional surface rendering. Quantitative determination of active muscle volume, signal intensity, and change over time is demonstrated. Visualization of the activated muscles allows functional anatomical assessment of exercise, which in turn allows detection of muscle utilization.     

Real-time 3D interactive segmentation of echocardiographic data through user-based deformation of B-spline explicit active surfaces

Image segmentation is an ubiquitous task in medical image analysis, which is required to estimate morphological or functional properties of given anatomical targets. While automatic processing is highly desirable, image segmentation remains to date a supervised process in daily clinical practice. Indeed, challenging data often requires user interaction to capture the required level of anatomical detail. To optimize the analysis of 3D images, the user should be able to efficiently interact with the result of any segmentation algorithm to correct any possible disagreement. Building on a previously developed real-time 3D segmentation algorithm, we propose in the present work an extension towards an interactive application where user information can be used online to steer the segmentation result. This enables a synergistic collaboration between the operator and the underlying segmentation algorithm, thus contributing to higher segmentation accuracy, while keeping total analysis time competitive. To this end, we formalize the user interaction paradigm using a geometrical approach, where the user input is mapped to a non-cartesian space while this information is used to drive the boundary towards the position provided by the user. Additionally, we propose a shape regularization term which improves the interaction with the segmented surface, thereby making the interactive segmentation process less cumbersome. The resulting algorithm offers competitive performance both in terms of segmentation accuracy, as well as in terms of total analysis time. This contributes to a more efficient use of the existing segmentation tools in daily clinical practice. Furthermore, it compares favorably to state-of-the-art interactive segmentation software based on a 3D livewire-based algorithm.     

A combined region growing and deformable model method for extraction of closed surfaces in 3D CT and MRI scans

Image segmentation of 3D medical images is a challenging problem with several still not totally solved practical issues, such as noise interference, variable object structures and image artifacts. This paper describes a hybrid 3D image segmentation method which combines region growing and deformable models to obtain accurate and topologically preserving surface structures of anatomical objects of interest. The proposed strategy starts by determining a rough but robust approximation of the objects using a region-growing algorithm. Then, the closed surface mesh that encloses the region is constructed and used as the initial geometry of a deformable model for the final refinement. This integrated strategy provides an alternative solution to one of the flaws of traditional deformable models, achieving good refinements of internal surfaces in few steps. Experimental segmentation results of complex anatomical structures on both simulated and real data from MRI scans are presented, and the method is assessed by comparing with standard reference segmentations of head MRI. The evaluation was mainly based on the average overlap measure, which was tested on the segmentation of white matter, corresponding to a simulated brain data set, showing excellent performance exceeding 90% accuracy. In addition, the algorithm was applied to the detection of anatomical head structures on two real MRI and one CT data set. The final reconstructions resulting from the deformable models produce high quality meshes suitable for 3D visualization and further numerical analysis. The obtained results show that the approach achieves high quality segmentations with low computational complexity.     

Knowledge-based method for segmentation and analysis of lung boundaries in chest X-ray images

We present a knowledge-based approach to segmentation and analysis of the lung boundaries in chest X-rays. Image edges are matched to an anatomical model of the lung boundary using parametric features. A modular system architecture was developed which incorporates the model, image processing routines, an inference engine and a blackboard. Edges associated with the lung boundary are automatically identified and abnormal features are reported. In preliminary testing on 14 images for a set of 18 detectable abnormalities, the system showed a sensitivity of 88% and a specificity of 95% when compared with assessment by an experienced radiologist.     

Joint registration and segmentation of neuroanatomic structures from brain MRI

RATIONALE AND OBJECTIVES: Segmentation of anatomic structures from magnetic resonance brain scans can be a daunting task because of large inhomogeneities in image intensities across an image and possible lack of precisely defined shape boundaries for certain anatomical structures. One approach that has been quite popular in the recent past for these situations is the atlas-based segmentation. The atlas, once constructed, can be used as a template and can be registered nonrigidly to the image being segmented thereby achieving the desired segmentation. The goal of our study is to segment these structures with a registration assisted image segmentation technique. MATERIALS AND METHODS: We present a novel variational formulation of the registration assisted image segmentation problem which leads to solving a coupled set of nonlinear Partial Differential Equations (PDEs) that are solved using efficient numeric schemes. Our work is a departure from earlier methods in that we can simultaneously register and segment in three dimensions and easily cope with situations where the source (atlas) and target images have very distinct intensity distributions. RESULTS: We present several examples (20) on synthetic and (3) real data sets along with quantitative accuracy estimates of the registration in the synthetic data case. CONCLUSION: The proposed atlas-based segmentation technique is capable of simultaneously achieve the nonrigid registration and the segmentation; unlike previous methods of solution for this problem, our algorithm can accommodate for image pairs having very distinct intensity distributions.     

Medical workstations for applied imaging and graphics research

We present a medical workstation for the efficient implementation of research ideas related to image processing and computer graphics. Based on standard hardware platforms the software system encompasses two major components: A turnkey application system provides a functionality kernel for a broad community of clinical users working with digital imaging devices, including methods of noise suppression, interactive and automatic segmentation, 3D surface reconstruction and multi-modal registration. A development toolbox allows new algorithms and applications to be efficiently implemented and consistently integrated with the common framework of the turnkey system. The platform is based on an elaborate object class structure describing objects for image processing, computer graphics, study handling and user interface control. Thus expertise of computer scientists familiar with this application domain is brought into the hospital and can be readily used by clinical researchers.     

Multi-region labeling and segmentation using a graph topology prior and atlas information in brain images

Medical image segmentation and anatomical structure labeling according to the types of the tissues are important for accurate diagnosis and therapy. In this paper, we propose a novel approach for multi-region labeling and segmentation, which is based on a topological graph prior and the topological information of an atlas, using a modified multi-level set energy minimization method in brain images. We consider a topological graph prior and atlas information to evolve the contour based on a topological relationship presented via a graph relation. This novel method is capable of segmenting adjacent objects with very close gray level in low resolution brain image that would be difficult to segment correctly using standard methods. The topological information of an atlas are transformed to the topological graph of a low resolution (noisy) brain image to obtain region labeling. We explain our algorithm and show the topological graph prior and label transformation techniques to explain how it gives precise multi-region segmentation and labeling. The proposed algorithm is capable of segmenting and labeling different regions in noisy or low resolution MRI brain images of different modalities. We compare our approaches with other state-of-the-art approaches for multi-region labeling and segmentation.     

A unified set of analysis tools for uterine cervix image segmentation

Segmentation is a fundamental component of many medical image-processing applications, and it has long been recognized as a challenging problem. In this paper, we report our research and development efforts on analyzing and extracting clinically meaningful regions from uterine cervix images in a large database created for the study of cervical cancer. In addition to proposing new algorithms, we also focus on developing open source tools which are in synchrony with the research objectives. These efforts have resulted in three Web-accessible tools which address three important and interrelated sub-topics in medical image segmentation, respectively: the Boundary Marking Tool (BMT), Cervigram Segmentation Tool (CST), and Multi-Observer Segmentation Evaluation System (MOSES). The BMT is for manual segmentation, typically to collect “ground truth” image regions from medical experts. The CST is for automatic segmentation, and MOSES is for segmentation evaluation. These tools are designed to be a unified set in which data can be conveniently exchanged. They have value not only for improving the reliability and accuracy of algorithms of uterine cervix image segmentation, but also promoting collaboration between biomedical experts and engineers which are crucial to medical image-processing applications. Although the CST is designed for the unique characteristics of cervigrams, the BMT and MOSES are very general and extensible, and can be easily adapted to other biomedical image collections.