对角线剖面分析引导的全自动肺CT图像分割

目的 提出一种基于对角线剖面分析的全自动肺CT图像分割方法。方法 首先构造待分割图像的对角线剖面图, 然后自动分析该剖面, 得到各组织结构的位置信息和像素值信息, 引导区域增长算法分离患者身体和背景, 再利用灰度阈值算法分离胸壁与肺区, 再用数学形态学算法修正肺边缘, 得到肺区掩模图像, 最后利用肺区掩模图像与原图像运算提取肺区。结果 利用从不同数据库选取的51幅CT图像检验提出的方法, 所得结果与诊断医师手工分割结果进行比较, 计算重叠率指标(OR), 最低OR为95.86%, 最高OR为99.25%, 平均OR为97.85%。结论 对角线剖面分析方法能高效地实现全自动肺CT图像分割。     

基于自动分割技术联合基于体素的形态学观察帕金森病脑灰质结构

目的 探讨基于自动分割技术联合基于体素的形态学(VBM)观察帕金森病(PD)患者全脑灰质异常区域及分布特征的应用价值。方法 基于自动分割技术,应用FIRST工具对29例PD患者(PD组)及30名健康人(对照组)的T1图像皮层下灰质结构精确分割,对比两组各灰质结构体积。并应用VBM方法对两组脑灰质图像进行比较。结果 两组右侧壳核皮层下灰质体积差异有统计学意义(t=10.201,P<0.05)。与对照组比较,PD组脑灰质体积(右侧初级运动皮层,双侧额叶、边缘叶、部分左侧小脑后叶、右侧小脑前叶、右侧小脑后叶、右侧颞叶、顶叶、壳核及左侧枕叶)广泛减少,部分左侧小脑后叶体积增加,两侧半球脑体积缺失不对称(右侧大于左侧)。结论 通过FIRST工具可精确分割并直接计算皮层下灰质结构体积,应用VBM技术可定量分析脑结构形态学异常;二者结合可较全面地表现PD脑灰质体积广泛减少的形态学特点。     

双源CT心脏图像中二尖瓣的分割及三维重建

目的 对双源CT(DSCT)图像中心脏二尖瓣进行分割和三维重建,为二尖瓣结构和功能异常分析提供参考。 方法 采用两步分割法对DSCT图像中二尖瓣分割:首先利用基于区域竞争主动轮廓模型的快速水平集算法(RCAC-FLSA)对经过双边滤波处理后图像进行初步分割,得到心脏对比剂增强区域;然后在灰度拉伸处理的基础上,结合ROI,再次利用RCAC-FLSA对上一步分割结果进行分割,得到心脏二尖瓣区域;最后对二尖瓣进行恢复。在Visual C++ 2005平台上结合OpenGL开发三维重建与显示平台,利用基于三维纹理映射的体绘制方法进行三维重建,并且加入伪彩色处理和透明度处理,以增强三维重建的立体效果。 结果 成功分割出一系列DSCT心脏图像中的二尖瓣,结合伪彩色处理和透明度处理的三维重建与显示平台,可获得二尖瓣的逼真重建。 结论 两步分割算法能有效分割DSCT心脏图像中的二尖瓣;结合伪彩色处理和透明度处理的三维重建与显示平台,能提供逼真的三维重建效果。     

区域生长法结合多竞争最小二乘拟合算法去除乳腺X线摄影图像中胸大肌影

目的 评价区域生长法结合多竞争最小二乘拟合算法去除数字乳腺X线摄影（MG）图像中胸大肌影的价值。方法 分层抽样法随机抽取244例MG数据,对图像进行轮廓选择、增强数据特征、胸大肌边界轮廓粗定位和去噪处理;结合最小二乘法改进区域生长法,拟合胸大肌的边界轮廓函数,使用最优轮廓函数制作胸大肌掩膜图,计算预测图与人工勾画图交并比（IOU）及像素精度（PA）,评价其去除MG图像中的胸大肌影的价值。结果 基于上述方法所获胸大肌轮廓较为平滑,较少漏分割或过度分割,结果误差较小;还原胸大肌边界轮廓与手动分割结果非常接近,平均IOU为（89.76±4.28）%,平均PA为（89.98±3.91）%。结论 结合区域生长法与多竞争最小二乘拟合算法可用于去除MG图像中的胸大肌影。     

基于MeanShift方法的肝脏CT图像的自动分割

目的 探讨基于Mean Shift方法的肝脏CT图像的自动分割算法,以实现肝脏的自动分割。方法 首先对原始图像进行单次Mean Shift平滑 ,滤除噪声的影响以增强算法的鲁棒性,然后通过Mean Shift迭代自动选取初始种子点,最后采用基于区域生长的方法实现肝脏CT图像的自动分割。结果 实验证明此方法是一个准确、快速和有效的肝脏自动分割方法。结论 采用本文中提出的方法,可有效地实现肝脏的自动分割。     

基于超声图像处理的HIFU所致组织损伤自动检测方法:实验研究

目的 探讨基于超声图像处理的HIFU所致组织损伤的自动检测方法。方法 针对HIFU辐照后新鲜离体猪肉声像图中的ROI,通过搜索灰度极大区域自动定位图像中的所有亮斑,结合数学形态学、连通域标记和Canny边缘检测算法提取测试对象的边缘轮廓;根据亮斑中心至边缘轮廓的欧式距离去除边缘附近的亮斑噪声,获取HIFU损伤候选区;而后提取候选区特征参数,并结合支持向量机（SVM）识别HIFU损伤。结果 最大灰度值和矩形度两个特征参数的识别率分别为86.25%和93.33%。选用识别率更高的矩形度,可正确识别单处、多处HIFU损伤或无HIFU损伤的图像。结论 采用此法可直接分析HIFU辐照后超声声像图而自动检测HIFU损伤,无需依靠图像配准技术,可减少手动定位带来的误差。     

直线加速器机载锥形束CT图像散射的修正方法

目的 对直线加速器机载锥形束CT(CBCT)散射修正方法进行研究.方法 在CBCT射线源前放置一个"指交叉"形的阻挡光栅,对Catphan 504模体进行扫描,分别获得CBCT图像和扇形束CT图像.利用基于阈值的图像分割算法跟踪机架旋转过程中阻挡光栅在CBCT图像中的位置,提取散射样本后利用插值法估计散射信号分布,采用改进的半扇扫描重建算法重建散射修正后的图像.结果 散射修正后的Catphan 504模体图像与扇形束CT重建的图像接近.与散射修正前比较,散射修正后CT值误差从100.86 HU下降到15.74 HU,散射修正后低对比度分辨力平均提高1.37倍.结论 基于阈值的图像分割算法准确跟踪阻挡光栅的位置,在铅片区域可采集散射信号,其余区域可通过改进的半扇扫描算法完成单次扫描的图像重建.     

改进型骨骼细化算法提取冠状动脉中心线

目的 运用全自动骨骼细化算法从CT图像中精确提取冠状动脉的中心线。方法 分割CT图像中的冠状动脉区域，经三维重建得到完整的冠状动脉三维数据；利用骨骼细化算法提取该冠状动脉的中心线，引入Dijkstra最短路径算法提升提取精度。结果 相比未移除分支的骨骼细化算法，重叠率提升2%，平均距离减少38.2%，平均运行时间0.48 s。结论 改进型骨骼细化算法可有效提取冠状动脉中心线。     

基于金字塔模型和Mean Shift算法的门静脉和主动脉分割方法

目的 基于目前临床在绘制肝门静脉和主动脉的时间-密度曲线方面存在的问题,提出一种准确分割肝脏CT灌注成像(CTPI)图中肝脏门静脉和主动脉的方法。方法 采用金字塔模型,结合Mean Shift分割算法对肝脏CTPI图像中的门静脉和主动脉进行分割,并在此基础上计算时间-密度曲线。结果 此方法能实现对肝脏CTPI图像中门静脉和主动脉的有效分割,绘制出准确、平滑而无毛刺的门静脉和主动脉的时间-密度曲线。结论 此方法有助于临床客观、准确地评估肝功能和诊断病变。     

基于小波的磁共振图像聚类分割

目的 利用直方图自适应确定人体不同部位MRI的聚类类别的数目和相应的初始聚类中心,实现模糊-c均值聚类算法(FCM)分割的自适应。方法 首先采用小波变换拟合直方图的平滑包络线,降低噪声对寻找包络线极值的影响;其次根据微积分的知识求出包络线极大值的个数,按照文中给出的法则对包络线的极大值进行筛选,确定直方图中峰值的个数;最后以直方图中峰值的个数为聚类类别数,以相应的峰值为初始聚类中心,对MRI进行FCM分割。结果 采用该方法对多幅腹部和脑部MR图像进行分割,均能有效地自适应确定聚类的个数。结论 本文方法能够有效、准确地确定不同MR图像的聚类类别的个数,实现FCM的自适应。     

Application of a semiautomatic boundary detection algorithm for the assessment of amniotic fluid quantity from ultrasound images.

The aim of this study was to develop a computer-assisted method to evaluate amniotic fluid volume (AFV). This was done by automatically detecting the boundaries of the amniotic fluid portion in 2-D ultrasonographic images. The study population consisted of 36 low-risk patients that were selected at random from a healthy population undergoing routine pregnancy follow-up. For each patient, images of the four quadrants of the uterus were digitized into a PC. The amniotic fluid portion in each ultrasonographic image was automatically detected, and its area was calculated. Its area was also manually determined by an expert physician (R. T.). The areas automatically detected by the algorithm were highly correlated with the areas manually delimited by the expert: r2 = 0.9722 (p < 0.01). The areas calculated by the program provide a good measure for the areas determined by the expert and may, therefore, be used for calculating the actual amniotic fluid volume.     

超声图像中基于经验模态分解自动提取内-中膜厚度

目的为改善传统人工标记测量血管内-中膜厚度(IMT)的准确性和稳定性,提出基于图像分割技术的经验模态分解(EMD)改进算法。方法采用EMD改进算法去噪,根据血管壁的特点,在其中的极值点插值步骤使用非均匀的二维B样条函数,在水平和垂直方向上控制网格的密度不同,分别满足不同的分辨精度和平滑程度要求,改进了原始的二维EMD算法;然后通过K均值方法从图像中分离出血管腔、血管壁和其他组织,使用数学形态学算法逐步得到最终的内-中膜组织分割结果。结果改进EMD算法取得了较好的重建和滤波效果,有效克服了超声图像的强噪声和低分辨力对图像分割的限制,整个算法分割比较准确,算法复杂度相对较小。结论改进EMD算法是在超声图像中自动提取内-中膜的较有潜力的方法,能有效去除超声噪声,同时保留条纹结构的细节和边缘信息,有望于其他强噪声环境下提取条纹结构。     

一种数字人脑部切片图像分割新方法

目的 提出一种人脑切片图像自动分割算法,以克服现有的方法对大量人工参与的依赖.方法 针对人脑切片图像的特征,提出一种基于区域生长的灰度直方图阈值化分割算法.首先通过区域生长过程对图像进行初始的粗分割,再用直方图阈值化方法进行二次细分割提取目标区域.结果 采用此方法准确有效地分割出了大脑白质和大脑皮质.结论 此算法结合切片图像的全局信息和局部信息应用于分割,是一种比较好的分割方法.     

Utility of amniotic fluid chitotriosidase in the prenatal diagnosis of lysosomal storage disorders

ObjectivePlasma chitotriosidase is a documented biomarker for certain lysosomal storage disorders. However, its clinical utility for prenatal samples is not elucidated yet.MethodsWe have established Reference intervals for amniotic fluid chitotriosidase using control amniotic fluids (n = 47) and compared the activity with amniotic fluids affected by lysosomal storage disorders (n = 25).ResultsThe reference interval established was 0–6.76 nmol/h/ml. The amniotic fluids affected with LSDs exhibited elevation of chitotriosidase. The area under the curve (AUC) of receiver operating characteristic curve for affected vs. healthy was 0.987 indicating 98.6% accuracy of chitotriosidase in identifying pregnancies affected with LSDs. Among the different LSDs, Gaucher (202.00 ± 35.27 nmol/h/ml) and Niemann-pick A/B (60.33 ± 21.59 nmol/h/ml) showed very high levels of chitotriosidase.ConclusionAmniotic fluid chitotriosidase has the potential to serve as a diagnostic marker for lysosomal storage disorders, more specifically for Gaucher and Niemann-Pick A/B.     

Automated segmentation of the left ventricle in cardiac MRI

We present a fully automated deformable model technique for myocardium segmentation in 3D MRI. Loss of signal due to blood flow, partial volume effects and significant variation of surface grey value appearance make this a difficult problem. We integrate various sources of prior knowledge learned from annotated image data into a deformable model. Inter-individual shape variation is represented by a statistical point distribution model, and the spatial relationship of the epi- and endocardium is modeled by adapting two coupled triangular surface meshes. To robustly accommodate variation of grey value appearance around the myocardiac surface, a prior parametric spatially varying feature model is established by classification of grey value surface profiles. Quantitative validation of 121 3D MRI datasets in end-diastolic (end-systolic) phase demonstrates accuracy and robustness, with 2.45 mm (2.84 mm) mean deviation from manual segmentation.     

The predictive value of segmentation metrics on dosimetry in organs at risk of the brain

BackgroundFully automatic medical image segmentation has been a long pursuit in radiotherapy (RT). Recent developments involving deep learning show promising results yielding consistent and time efficient contours. In order to train and validate these systems, several geometric based metrics, such as Dice Similarity Coefficient (DSC), Hausdorff, and other related metrics are currently the standard in automated medical image segmentation challenges. However, the relevance of these metrics in RT is questionable. The quality of automated segmentation results needs to reflect clinical relevant treatment outcomes, such as dosimetry and related tumor control and toxicity. In this study, we present results investigating the correlation between popular geometric segmentation metrics and dose parameters for Organs-At-Risk (OAR) in brain tumor patients, and investigate properties that might be predictive for dose changes in brain radiotherapy.MethodsA retrospective database of glioblastoma multiforme patients was stratified for planning difficulty, from which 12 cases were selected and reference sets of OARs and radiation targets were defined. In order to assess the relation between segmentation quality -as measured by standard segmentation assessment metrics- and quality of RT plans, clinically realistic, yet alternative contours for each OAR of the selected cases were obtained through three methods: (i) Manual contours by two additional human raters. (ii) Realistic manual manipulations of reference contours. (iii) Through deep learning based segmentation results. On the reference structure set a reference plan was generated that was re-optimized for each corresponding alternative contour set. The correlation between segmentation metrics, and dosimetric changes was obtained and analyzed for each OAR, by means of the mean dose and maximum dose to 1% of the volume (Dmax 1%). Furthermore, we conducted specific experiments to investigate the dosimetric effect of alternative OAR contours with respect to the proximity to the target, size, particular shape and relative location to the target.ResultsWe found a low correlation between the DSC, reflecting the alternative OAR contours, and dosimetric changes. The Pearson correlation coefficient between the mean OAR dose effect and the Dice was -0.11. For Dmax 1%, we found a correlation of -0.13. Similar low correlations were found for 22 other segmentation metrics. The organ based analysis showed that there is a better correlation for the larger OARs (i.e. brainstem and eyes) as for the smaller OARs (i.e. optic nerves and chiasm). Furthermore, we found that proximity to the target does not make contour variations more susceptible to the dose effect. However, the direction of the contour variation with respect to the relative location of the target seems to have a strong correlation with the dose effect.ConclusionsThis study shows a low correlation between segmentation metrics and dosimetric changes for OARs in brain tumor patients. Results suggest that the current metrics for image segmentation in RT, as well as deep learning systems employing such metrics, need to be revisited towards clinically oriented metrics that better reflect how segmentation quality affects dose distribution and related tumor control and toxicity.     

Learning layer-specific edges for segmenting retinal layers with large deformations

We present an algorithm for layer-specific edge detection in retinal optical coherence tomography images through a structured learning algorithm to reinforce traditional graph-based retinal layer segmentation. The proposed algorithm simultaneously identifies individual layers and their corresponding edges, resulting in the computation of layer-specific edges in 1 second. These edges augment classical dynamic programming based segmentation under layer deformation, shadow artifacts noise, and without heuristics or prior knowledge. We considered Duke’s online data set containing 110 B-scans of 10 diabetic macular edema subjects with 8 retinal layers annotated by two experts for experimentation, and achieved a mean distance error of 1.38 pixels whereas that of the state-of-the-art was 1.68 pixels.OCIS codes: (170.4500) Optical coherence tomography, (100.6950) Tomographic image processing, (170.6935) Tissue characterization, (170.1610) Clinical applications     

对比QBrain与FreeSurfer软件自动测量海马体积

目的对比基于深度学习的脑影像量化分析软件QBrain与作为传统算法代表的FreeSurfer自动分割软件测量海马体积的效果。方法自健康中国成人头颅高分辨MRI数据库(Chinese 1000)中随机提取100名志愿者数据,以手动测量结果为标准,对比FreeSurfer、QBrain软件测量海马体积的差异。采用Pearson相关分析和组内相关系数(ICC)进行相关性分析,以Bland-Altman分析法行一致性分析;以戴斯系数(DSC)评估2种自动测量方法与手动测量值相似度。结果手动测量及FreeSurfer、QBrain软件测量结果均显示右侧海马体积测值大于左侧(P均<0.05)。FreeSurfer右侧海马测值明显小于手动测值(P<0.05);左侧测值大于手动测值,但差异无统计学意义(P>0.05)。QBrain右侧海马值明显小于手动测值(P<0.05);左侧测值小于手动测值,但差异无统计学意义(P>0.05)。2种自动方法海马体积测值均与手动测值显著相关(ICC>0.75,r>0.75,P<0.05)。Bland-Altman散点图显示2种自动测量方法与手动测量结果的一致性均较好。FreeSurfer及QBrain海马体积测值与手动测值的DSC分别为0.73和0.05(P均<0.05)。结论FreeSurfer与QBrain均可准确自动测量海马体积;QBrain所测海马体积与手动测值的相关性更佳,且耗时较少。     

A comparison of methods for the automated calculation of volumes and atrophy rates in the hippocampus

Hippocampal atrophy rates have been used in a number of studies in Alzheimer's disease (AD) to assess disease progression and are being increasingly utilized as an outcome measure in clinical trials of new pharmaceutical agents. Owing to the labor-intensive nature of hippocampal segmentation, more automated approaches are required for such analysis. In this study we compared methods of automatically segmenting the hippocampus (single-person template and template library) on the baseline image in a group of probable AD (n=36) and control (n=19) subjects with serial images. Using the method that gave most similar results to manual, three automated methods of calculating change within the hippocampal region were compared: fluid change calculated using (1) Jacobian change or (2) region propagation and (3) boundary shift. Rates were compared with manual measures. We found that segmentation of baseline hippocampus was most accurate using a template library combined with morphological operations (intensity thresholding plus one conditional dilation). This gave a voxel similarity of 0.69 (0.05) and 0.72 (0.06) in controls and probable AD subjects respectively compared with manual measures. Atrophy rates within these regions were most similar to the manual rates using the boundary shift integral (mean difference from manual rate 0.03% (1.29) in controls and 0.48% (2.44) in AD). A template library segmentation approach, together with morphological operations, provides a segmentation accurate enough to quantify relative change over time. The change over time can then be calculated automatically using boundary shift or fluid measures, with boundary shift giving most similar results to manual.