基于层间先验知识从脑MRI图像中自动提取脑组织

目的从脑MRI图像中提取脑组织,解决边缘模糊时脑和非脑组织难以分离的问题。方法首先利用各向异性扩散滤波的方法对脑MRI图像进行去噪处理;然后利用形态学的方法对初始脑MRI图像进行脑组织提取,在此分割结果的基础上,利用相邻层脑形态差异较小的特点,实现结构元素的自适应选取,完成从脑MRI图像中逐层准确、自动提取脑组织。结果采用不同来源的数据对算法性能进行了测试,结果优于经典背散射电子成像(BSE)方法的分割结果。结论利用层间先验知识有利于实现边缘模糊的脑组织自动准确提取,且适用性较强。     

一种磁共振脑组织及肿瘤区域的提取方法

脑成像的脑组织准确提取有助于提高研究脑部感兴趣区域的精度,脑部肿瘤图像分割的研究可用于组织三维重建、肿瘤体积计算等.本文使用磁共振图像,首先采用脑提取（brain extraction tool,BET）算法提取出脑组织区域,再利用一种信息熵自动阈值与形态学结合的方法;当提取出脑组织后,利用模糊C均值（fuzzy C-means,FCM）聚类算法对肿瘤区域进行提取,经过中值滤波等步骤,提取出脑肿瘤区域.与专家手工勾画对比,本文较好地提取出了脑肿瘤组织,从而实现了脑组织的自动分割,提高了工作效率.     

改进的Brain Extraction Tool算法及其在脑实质分割中的应用

BET(Brain Extraction Tool)算法是一种常用的从磁共振(MRI)脑图像中分割脑实质的工具,在实际应用中发现,BET算法对正常脑实质的分割精度较高,但对有病灶的脑实质分割精度较差。根据BET算法存在的问题,改进原BET算法中不合理的u_3,简化了计算繁琐的u_2,并将其应用于分割MRI图像中的脑实质。首先:选择序列图像中间层,对其应用两次改进后的BET算法获得精确分割结果;然后:将获得的边界向其中心缩小一定比例后作为与其相邻层的初始边界再次应用修改后的算法获得该层精确边界;最后,不断重复上述步骤直至所有层分割结束。改进后的算法对脑部图像分割结果与人工分割结果的重叠率达到92.92%,而使用FSL中提供的BET工具的分割结果与人工分割结果的重叠率为88.94%。改进后的算法相比原BET算法能够更加准确地分割MRI图像中的脑实质。     

基于深度监督全卷积神经网络的MRI脑图像语义分割算法

目的 依据临床诊断对MRI脑图像自动分割算法的需求,基于卷积神经网络(convolutional neural networks,CNN)设计了一种端到端的深度监督全卷积网络(deeply supervised fully convolutional network,DS-FCN)以解决脑图像中脑组织的自动分割问题。方法 针对三维MRI脑图像,先将体数据切割成二维图像切片,在FCN网络结构的基础上,加入了深度监督机制,即在特征提取的多层级结构中提前得到损失值反馈。结果 以三维MRI脑图像公开数据集LPBA-40为实验数据,56类脑组织的准确率(precision rate)、召回率(recall rate)、F1评估值分别为74. 40%、74. 82%、73. 75%,测试速率为152 ms。结论 通过引入深度监督结构,改进后的DS-FCN在MRI脑组织分割任务中得到了更精准的分割效果。     

结合水平集和区域生长的脑MR图像分割

本文提出了结合改进的水平集和区域生长方法实现脑MR图像分割,并根据不同组织成像特征和组织结构特点采用不同算法分割进行了探索.主要步骤:首先用改进的水平集算法实现图像中骨组织和脑脊液(CSF)的提取;然后,依据直方图确定脑灰质(GM)、脑白质(WM)的近似灰度值,自动定位种子点后进行区域生长,实现脑灰质和脑白质的分离.实验结果表明,该方法充分利用了脑MR图像中的区域信息和边界信息,与传统单一算法分割脑MR图像相比,具有更强的鲁棒性和准确性.     

MR脑图像组织分割的方法

图像分割是一个经典难题,至今没有一个通用的有效分割方法,也不存在一个分割的评价标准。应用MRI图像进行脑组织自动和有效的分割对诊断、病理研究、放疗和外科手术计划的制定、手术导航、计算机辅助诊断等各方面均有着极其重要的意义。磁共振脑图像比普通图像要复杂,组织边界不清晰,用通用方法无法实现良好的分割。对目前应用于脑组织分割并取得良好效果的分割方法给予综合论述,并分析了脑组织分割的发展。     

基于FCM聚类算法的MRI脑组织图像分割方法比较研究

目的磁共振成像(magnetic resonance imaging,MRI)对脑组织有较好的成像效果,但噪声、偏移场和部分容积效应(partial volume effect,PVE)的存在,使得全自动分割MRI图像面临一定的困难。模糊C均值(fuzzy C-means,FCM)聚类算法在脑组织分割中得到较广泛研究。本文以存在噪声和偏移场影响的脑MRI图像分割为应用背景,研究了大量相关方法,探讨FCM算法分割脑部图像的改进思想。方法本文主要研究了9种FCM算法的理论基础,并通过脑组织分割实验对各种算法进行了分析。结果比较了不同算法的优劣,给出各类算法直观及定量评价结果。结论偏移场和噪声对脑磁共振图像组织分类质量有明显影响。其中几种方法可以减弱这些不利影响,但由于难以选择合适的参数,其分类效果并不理想。如何合理利用空间信息在未来仍有较大研究价值。     

MR脑图像组织分割的方法

图像分割是一个经典难题,至今没有一个通用的有效分割方法,也不存在一个分割的评价标准.应用MRI图像进行脑组织自动和有效的分割对诊断、病理研究、放疗和外科手术计划的制定、手术导航、计算机辅助诊断等各方面均有着极其重要的意义.磁共振脑图像比普通图像要复杂,组织边界不清晰,用通用方法无法实现良好的分割.对目前应用于脑组织分割并取得良好效果的分割方法给予综合论述,并分析了脑组织分割的发展.     

脑梗塞患者MR图像分割的研究

目的研究一种可实现脑梗塞患者MR图像脑组织分割的算法.方法根据脑梗塞患者MR图像中脑组织的区域和边缘的特性,对传统水平集算法进行改进,实现了对特定目标体分割的能力,降低了边界泄漏发生的可能性.结果通过体膜和大量脑梗塞患者MR图像实验和SPM5对比,实验证实了改进算法对MR图像分割的准确性和鲁棒性. 结论该算法为脑梗塞患者的脑图像分析和脑组织测量提供了一种有效的分割方法.     

图论在脑肿瘤分割及提取中的应用研究

目的 基于Matlab和VC++混合编程,实现了图论在脑肿瘤分割及提取中的应用,为之后脑肿瘤三维重建提供准确的分割结果.方法 在Matlab和VC++开发平台下,首先读取含脑肿瘤的MRI图像,经过一定的预处理后,调用C++编写的图论分割函数,实现MRI图像的全局分割,然后通过肿瘤区域的颜色信息进行区域二值化和轮廓提取等后处理,很好地完成了脑肿瘤的分割提取.结果 通过与专家手动分割的脑肿瘤区域进行比较以及对算法各模块运行时间的监测,显示脑肿瘤分割准确度高,且算法运行稳定.结论 基于图论的分割算法能够反映图像全局特性,且运行稳定,是一种值得推广的脑肿瘤分割方法.     

阿尔茨海默病患者MR图像偏差场修正和脑组织分割的研究

目的探索适用于阿尔茨海默病（Alzheimer’s disease,AD）患者MR图像脑组织的分割的方法。方法结合阿尔茨海默病患者MR图像中组织区域和边缘的特性对传统水平集进行改进,利用同态滤波对图像进行偏差场修正,增加了UNSHARP MASK处理方法,有效避免了水平集边界泄漏问题。结果标准体膜和真实数据实验证实,该改进算法分割结果优于SPM5。结论利用修正偏差场和添加UNSHARP MASK方法有可能提高AD患者MR图像脑组织分割的准确性和鲁棒性,本研究为MR图像脑组织的精确分割和进一步准确测量作了有益探索。     

三维医学图像序列的自动连续分割

我们针对医学辅助诊断系统中从M R图像分割脑肿瘤的问题,改进了区域竞争算法,并利用它实现了医学图像序列间的连续自动分割,特别是脑肿瘤的分割和脑膜瘤的自动识别。模糊化区域竞争算法是为了更好的适应医学图像的模糊与不均匀的特点,而用区域增长做初始化可以给区域竞争提供用来竞争和合并的过分割区域。为了实现医学图像序列的自动连续分割,每一副切片的分割结果都会被用作初始化下一张切片;并且我们根据脑膜瘤的特点实现了它的自动识别。实验表明,我们的自动分割算法对仿真脑图像和真实脑图像均有较好的分割精度,并能满足系统对分割快速性的需要。     

Endocardial Border Detection in Cardiac Magnetic Resonance Images Using Level Set Method

Segmentation of the left ventricle in MRI images is a task with important diagnostic power. Currently, the evaluation of cardiac function involves the global measurement of volumes and ejection fraction. This evaluation requires the segmentation of the left ventricle contour. In this paper, we propose a new method for automatic detection of the endocardial border in cardiac magnetic resonance images, by using a level set segmentation-based approach. To initialize this level set segmentation algorithm, we propose to threshold the original image and to use the binary image obtained as initial mask for the level set segmentation method. For the localization of the left ventricular cavity, used to pose the initial binary mask, we propose an automatic approach to detect this spatial position by the evaluation of a metric indicating object’s roundness. The segmentation process starts by the initialization of the level set algorithm and ended up through a level set segmentation. The validation process is achieved by comparing the segmentation results, obtained by the automated proposed segmentation process, to manual contours traced by tow experts. The database used was containing one automated and two manual segmentations for each sequence of images. This comparison showed good results with an overall average similarity area of 97.89%.     

A Fast and Fully Automatic Method for Cerebrovascular Segmentation on Time-of-Flight (TOF) MRA Image

The precise three-dimensional (3-D) segmentation of cerebral vessels from magnetic resonance angiography (MRA) images is essential for the detection of cerebrovascular diseases (e.g., occlusion, aneurysm). The complex 3-D structure of cerebral vessels and the low contrast of thin vessels in MRA images make precise segmentation difficult. We present a fast, fully automatic segmentation algorithm based on statistical model analysis and improved curve evolution for extracting the 3-D cerebral vessels from a time-of-flight (TOF) MRA dataset. Cerebral vessels and other tissue (brain tissue, CSF, and bone) in TOF MRA dataset are modeled by Gaussian distribution and combination of Rayleigh with several Gaussian distributions separately. The region distribution combined with gradient information is used in edge-strength of curve evolution as one novel mode. This edge-strength function is able to determine the boundary of thin vessels with low contrast around brain tissue accurately and robustly. Moreover, a fast level set method is developed to implement the curve evolution to assure high efficiency of the cerebrovascular segmentation. Quantitative comparisons with 10 sets of manual segmentation results showed that the average volume sensitivity, the average branch sensitivity, and average mean absolute distance error are 93.6%, 95.98%, and 0.333 mm, respectively. By applying the algorithm to 200 clinical datasets from three hospitals, it is demonstrated that the proposed algorithm can provide good quality segmentation capable of extracting a vessel with a one-voxel diameter in less than 2 min. Its accuracy and speed make this novel algorithm more suitable for a clinical computer-aided diagnosis system.     

Technique for the computation of lower leg muscle bulk from magnetic resonance images

An unsupervised technique to estimate the relative size of a patient's lower leg musculature in vivo using magnetic resonance imaging (MRI) in the context of venous insufficiency is presented. This post-acquisition technique was designed to segment calf muscle bulk, which could be used to make inter- or intra-patient comparisons of calf muscle size in the context of unilateral leg ulcers and venous return. Pre-processing stages included partial volume reduction, intensity inhomogeneity correction and contrast equalization. The algorithm created a binary mask of voxels that fell within a computed threshold designated as representing muscle based on a 3-class fuzzy clustering approach. The segmentation was improved using a set of morphological operations to remove adipose tissue, spongy bone and cortical bone.The technique was evaluated for accuracy against a manual segmented ground truth. Results showed that the automatic technique performed sufficiently well in terms of accuracy and efficacy. The automatic method did not suffer from intra-observer variability.     

Automatic Articular Cartilage Segmentation Based on Pattern Recognition from Knee MRI Images

An automatic method for cartilage segmentation using knee MRI images is described. Three binary classifiers with integral and partial pixel features are built using the Bayesian theorem to segment the femoral cartilage, tibial cartilage and patellar cartilage separately. First, an iterative procedure based on the feedback of the number of strong edges is designed to obtain an appropriate threshold for the Canny operator and to extract the bone-cartilage interface from MRI images. Second, the different edges are identified based on certain features, which allow for different cartilage to be distinguished synchronously. The cartilage is segmented preliminarily with minimum error Bayesian classifiers that have been previously trained. According to the cartilage edge and its anatomic location, the speed of segmentation is improved. Finally, morphological operations are used to improve the primary segmentation results. The cartilage edge is smooth in the automatic segmentation results and shows good consistency with manual segmentation results. The mean Dice similarity coefficient is 0.761.     

眼底图像中硬性渗出物检测算法

目的利用眼底图像中硬性渗出物(hard exudates,HE)的亮度与边缘特征,提出一种基于Canny边缘检测算法与形态学重构相结合的HE自动检测方法,以解决目前算法灵敏度低、检测结果中视盘和血管的干扰等问题,对糖尿病视网膜病变(diabetic retinopathy,DR)的自动筛查具有重要意义。方法检测算法包括4个步骤。步骤一,图像预处理,主要包括RGB通道选取、基于形态学的图像对比度增强。步骤二,视网膜图像关键结构的消除,利用基于Gabor滤波的血管分割方法,消除血管边缘对HE检测的影响。将本文视杯分割算法应用在眼底图像红色通道上实现视盘自动分割,消除视盘及其边缘对HE检测的影响。步骤三,利用改进的Canny边缘检测算法和形态学重构方法对HE进行提取。步骤四,基于形态学的图像后处理,消除眼底图像边缘部分假阳性区域。最后利用该算法测试公开数据库中的40幅图像(35幅HE病变图像,5幅正常图像)。结果该算法对基于病变的灵敏性(sensitivity,SE)和阳性预测值(positive predictive value,PPV)分别为93.18%和79.26%,基于图像的灵敏性、特异性(specificity,SP)和准确率(accuracy,ACC)分别为97.14%、80.00%和95.00%。结论与其他方法对比,基于Canny边缘检测算法与形态学重构相结合的HE自动检测算法具有较好的可行性。     

改进的K-均值聚类算法及其在脑组织分割中的应用

目的：鉴于K-均值聚类算法易受初始聚类中心的影响,初始聚类中心不仅影响聚类速度。还可能使算法陷入局部极小值,得到错误的聚类结果,基于SOM神经网络,提出了一种改进的K．均值聚类算法并将其应用于脑实质分割。方法：首先,由SOM神经网络对图像进行初始聚类,得到＆个聚类中心值;然后,以SOM神经网络获得的k个聚类中心值作为K_均值聚类算法的初始聚类中心对图像进行％．均值聚类,最终获得图像的聚类分割结果。结果：基于SOM神经网络的K-means聚类算法的分割精度为O．9274,K-means聚类算法的分割精度为0．8649。结论：利用改进的K-均值聚类算法对磁共振脑部图像进行了分割实验,结果表明该算法有效改善了K-means聚类算法初始聚类中心选取的盲目性,使聚类结果更为准确、稳定,取得了比单一方法更好的分割结果。     

An Effective Method for Segmentation of MR Brain Images Using the Ant Colony Optimization Algorithm

Since segmentation of magnetic resonance images is one of the most important initial steps in brain magnetic resonance image processing, success in this part has a great influence on the quality of outcomes of subsequent steps. In the past few decades, numerous methods have been introduced for classification of such images, but typically they perform well only on a specific subset of images, do not generalize well to other image sets, and have poor computational performance. In this study, we provided a method for segmentation of magnetic resonance images of the brain that despite its simplicity has a high accuracy. We compare the performance of our proposed algorithm with similar evolutionary algorithms on a pixel-by-pixel basis. Our algorithm is tested across varying sets of magnetic resonance images and demonstrates high speed and accuracy. It should be noted that in initial steps, the algorithm is computationally intensive requiring a large number of calculations; however, in subsequent steps of the search process, the number is reduced with the segmentation focused only in the target area.