肺结节检测算法研究

探讨基于CT图像数据的肺结节自动检测算法。肺结节提取一般步骤为：CT图像预处理、肺实质分割、肺结节提取。     

基于改进的模糊C均值聚类的肺结节计算机辅助诊断算法研究

目的:研究基于改进的模糊C均值聚类计算机辅助诊断算法对肺结节的诊断价值,降低对肺结节的漏诊率,提高病人的生存率.方法:基于模糊C均值聚类的算法,利用直方图统计特性对数据进行优化,在此基础上利用像素的邻域特性,将数据样本对各聚类中心约束条件为1,改变为隶属度之和为样本总数.用改进的FCM对肺实质图像进行分割,将分割后的图像应用区域标记算法去除小面积区域.利用肺结节的关键特征,提取可疑区域.结果:运用改进算法后,区域分割效果更好.仿真结果证明算法很好的将"线"形或分枝状结构的血管去除.结论:改进的FCM有很好的实时性和对噪声的鲁棒性,分离血管后,将可疑区域在原图标记出来,使医生的工作更加明确.     

基于背包式激光雷达测量系统的城市绿地树木三维绿量估算方法

三维绿量能够客观、准确描述城市绿化水平,可为定量研究城市绿地生态功能的机理提供可靠的数据基础。针对单位附属绿地分布分散、规模较小等特点,本研究提出一种面向该类城市绿地的三维绿量估算方案,该方案包括数据获取、处理、实体分割、分类和单木冠层提取以及三维绿量计算的环节。首先,利用背包式激光雷达测量系统获取三维点云数据,利用变尺度地面点滤波算法剔除地面点云;然后,利用基于密度的聚类算法对非地面点云进行聚类,且基于密度特征的竞争算法对重叠区域进行二次分割,形成独立对象;接着,利用PointNet++模型提取植物点云,根据枝叶点云主方向差异性以及轴向分布密度提取冠层点云;最后,使用凸包法计算单木冠层三维绿量,累计每株木的三维绿量得到区域三维绿量。以某科技园区为例,估算其总三维绿量为21034.95 m³,其中,芒果树株数最多,三维绿量总量最大,为4868.64 m³,占23.2%;单株三维绿量最大的树种为小叶榄仁,平均每株为120.37 m³。本研究方案估算的树木三维绿量与传统方法的相对误差在10.7%～33.7%,平均相对误差为20.9%;与台积法的相对误差在2.7%～16.0%,平均相对误差为8.7%。本研究方案充分利用三维点云数据特性,所用凸多面体逼近树冠的原始形态,更符合树木的实际情况。该三维绿量测量和估算方案可为城市三维绿量快速、精确估算提供新思路。     

一种基于视网膜主血管方向的视盘定位及提取方法

为分割出眼底图像中的视盘,构建基于眼底图像的计算机辅助诊断系统,提出了一种基于视网膜主血管方向的视盘定位及提取方法。首先,利用Otsu阈值分割眼底图像R通道获取视盘候选区域;然后利用彩色眼底图像的HSV空间的H通道提取视网膜主血管并确定主血管方向;在此基础上,通过在方向图内寻找出对加权匹配滤波器响应值最高的点确定视盘中心位置;最后,利用该位置信息从视盘候选区域中"挑选"出真正的视盘。利用该方法对100幅不同颜色、不同亮度的眼底图像进行视盘分割,得到准确率98%,平均每幅图像处理时间1.3 s。结果表明:该方法稳定可靠,能快速、有效分割出眼底图像中的视盘。     

医学图像中的边缘分析

根据医学图像处理的要求,需要将图像划分若干区域,其划分过程要求迅速、精确。本文结合实际经验,介绍了图像分割的重要方法——边缘提取,并着重分析了其中边缘检测和边缘跟踪的过程和方法,同时还给出了用计算机模拟得到的边缘提取的结果。     

基于动态方向梯度矢量流模型的脑肿瘤图像分割

目的:针对GVF Snake模型算法收敛容易陷入局部极小值及对初始轮廓位置敏感等缺点,提出一种动态方向梯度矢量流模型(DDGVF),使其更适合医学图像的分割。方法:利用主动轮廓模型的提取和跟踪特定区域内目标轮廓的方法,将其应用于医学图像如CT、MRI和超声图像的处理,以获取特定器官及组织的轮廓。结果:动态方向梯度矢量流场(DDGVF)能够较好地提取出脑肿瘤图像。结论:利用该方法能够较好地分割提取出脑肿瘤图像的肿瘤病变区域,为进一步对其纹理和形状等特征进行描述和分析提供了可靠的依据。     

基于高光谱成像和主成分分析的水稻茎叶分割

在单株水稻表型测量研究中,为了实现绿叶面积和茎叶相关表型参数的准确计算提供技术保障,茎叶的分割是非常重要的一步。传统的人工测量方法费时费力,且主观性较强,而基于普通相机拍摄的彩色图像进行分割效果很差。本研究介绍了一种使用可见光-近红外高光谱成像系统自动区分单株盆栽水稻茎叶的方法。首先将各波长下的图像从原始二进制数据中提取出来,接着使用主成分分析所有波长下的图像,并提取出主要的主成分图像,再基于数字图像处理技术将茎叶区分开。实验结果表明,本系统以及文中所用方法对分蘖盛期的水稻茎叶有很好的分割效果,这为后续水稻茎叶表型性状高通量、数字化、无损准确提取提供了重要的技术保障,并进一步促进植物表型组学的发展。     

通过光学相干断层扫描图像进行自动视网膜分割评估黄斑水肿的投影面积（英文）

本文提出一种自动视网膜分割方法,以评估光学相干断层扫描(OCT)图像中黄斑水肿(ME)在视网膜特定层上的投影面积.首先使用基于权重矩阵的优化最短路径最快算法对10个视网膜层边界进行分割,这有效降低了算法对血管阴影的敏感性.然而,ME的存在将导致水肿区域的分割不准确.因此,使用强度阈值方法提取每个OCT图像中的水肿区域,并将该区域中的值设置为零,并确保获得的分割边界可以自动穿过而不是绕过水肿区域.同时使用最小值投影来计算ME在不同层的投影面积.为了测试该方法,使用了从Topcon OCT机器收集的数据.在轴向和B扫描方向上测得的黄斑区域分辨率分别为11.7μm和46.8μm.与手动分割相比,视网膜层边界分割的平均绝对误差和标准偏差为(4.5±3.2)μm.因此,所提出的方法为评估水肿提供了一种自动、无创和定量的工具.     

基于机载LiDAR数据的福建柏人工林林木参数提取

准确高效地提取人工林林木参数可为估算单木材积、林分蓄积量提供关键信息。本文提出基于机载LiDAR数据的高精度单木参数提取方法,其实现过程包括数据预处理、地面滤波、单木分割和参数提取。以福建省沙县官庄国有林场的福建柏大径材人工林为试验区,采集高密度机载点云数据,对点云进行去噪、重采样等预处理。使用布料滤波算法(CSF)分离出植被点云和地面点云,并采用Delaunay三角网法将植被点云数据插值生成数字表面模型(DSM),采用反距离加权插值法将地面点云数据插值生成数字高程模型(DEM),两者作差运算获得冠层高度模型(CHM)。利用分水岭分割算法分析不同分辨率的CHM对单木分割及参数提取精度的影响。采用点云距离聚类算法对归一化植被点云进行单木分割,分析不同的距离阈值对单木分割及参数提取精度的影响。结果表明：使用分水岭分割算法处理0.3 m分辨率CHM单木分割调和值最高,达到91.1%,提取的树高精度较优,决定系数(R²)达到0.967,均方根误差(RMSE)为0.890 m;使用间距阈值为平均冠幅的点云分割算法单木分割调和值最高,达到91.3%,提取的冠幅精度较优,R     

通过光学相干断层扫描图像进行自动视网膜分割评估黄斑水肿的投影面积

在本文中,我们提出了一种自动视网膜分割方法,以评估光学相干断层扫描（OCT）图像中黄斑水肿（ME）在视网膜特定层上的投影面积。首先使用基于权重矩阵的优化的最短路径最快算法对十个视网膜层边界进行分割,这有效降低了算法对血管阴影的敏感性。然而,ME的存在将导致水肿区域的分割不准确。因此,我们使用强度阈值方法提取每个OCT图像中的水肿区域,并将该区域中的值设置为零,并确保获得的分割边界可以自动穿过而不是绕过水肿区域。我们使用最小值投影来计算ME在不同层的投影面积。为了测试我们的方法,我们使用了从Topcon的OCT机器收集的数据。在轴向和B扫描方向上测得的黄斑区域分辨率分别为11.7微米和46.8微米。与手动分割相比,视网膜层边界分割的平均绝对误差和标准偏差为4.5±3.2微米。因此,所提出的方法为评估水肿提供了一种自动,无创和定量的工具。     

Automatic detection of pulmonary nodules in CT images by incorporating 3D tensor filtering with local image feature analysis

Computer-aided detection (CAD) technology has been developed and demonstrated its potential to assist radiologists in detecting pulmonary nodules especially at an early stage. In this paper, we present a novel scheme for automatic detection of pulmonary nodules in CT images based on a 3D tensor filtering algorithm and local image feature analysis. We first apply a series of preprocessing steps to segment the lung volume and generate the isotropic volumetric CT data. Next, a unique 3D tensor filtering approach and local image feature analysis are used to detect nodule candidates. A 3D level set segmentation method is used to correct and refine the boundaries of nodule candidates subsequently. Then, we extract the features of the detected candidates and select the optimal features by using a CFS (Correlation Feature Selection) subset evaluator attribute selection method. Finally, a random forest classifier is trained to classify the detected candidates. The performance of this CAD scheme is validated using two datasets namely, the LUNA16 (Lung Nodule Analysis 2016) database and the ANODE09 (Automatic Nodule Detection 2009) database. By applying a 10-fold cross-validation method, the CAD scheme yielded a sensitivity of 79.3% at an average of 4 false positive detections per scan (FP/Scan) for the former dataset, and a sensitivity of 84.62% and 2.8 FP/Scan for the latter dataset, respectively. Our detection results show that the use of 3D tensor filtering algorithm combined with local image feature analysis constitutes an effective approach to detect pulmonary nodules.     

Finite element 3D reconstruction of the pulmonary acinus imaged by synchrotron X-ray tomography

The alveolated structure of the pulmonary acinus plays a vital role in gas exchange function. Three-dimensional (3D) analysis of the parenchymal region is fundamental to understanding this structure-function relationship, but only a limited number of attempts have been conducted in the past because of technical limitations. In this study, we developed a new image processing methodology based on finite element (FE) analysis for accurate 3D structural reconstruction of the gas exchange regions of the lung. Stereologically well characterized rat lung samples (Pediatr Res 53: 72-80, 2003) were imaged using high-resolution synchrotron radiation-based X-ray tomographic microscopy. A stack of 1,024 images (each slice: 1024 x 1024 pixels) with resolution of 1.4 mum(3) per voxel were generated. For the development of FE algorithm, regions of interest (ROI), containing approximately 7.5 million voxels, were further extracted as a working subunit. 3D FEs were created overlaying the voxel map using a grid-based hexahedral algorithm. A proper threshold value for appropriate segmentation was iteratively determined to match the calculated volume density of tissue to the stereologically determined value (Pediatr Res 53: 72-80, 2003). The resulting 3D FEs are ready to be used for 3D structural analysis as well as for subsequent FE computational analyses like fluid dynamics and skeletonization.     

Automatic ROI Selection in Structural Brain MRI Using SOM 3D Projection

This paper presents a method for selecting Regions of Interest (ROI) in brain Magnetic Resonance Imaging (MRI) for diagnostic purposes, using statistical learning and vector quantization techniques. The proposed method models the distribution of GM and WM tissues grouping the voxels belonging to each tissue in ROIs associated to a specific neurological disorder. Tissue distribution of normal and abnormal images is modelled by a Self-Organizing map (SOM), generating a set of representative prototypes, and the receptive field (RF) of each SOM prototype defines a ROI. Moreover, the proposed method computes the relative importance of each ROI by means of its discriminative power. The devised method has been assessed using 818 images from the Alzheimer''s disease Neuroimaging Initiative (ADNI) which were previously segmented through Statistical Parametric Mapping (SPM). The proposed algorithm was used over these images to parcel ROIs associated to the Alzheimer''s Disease (AD). Additionally, this method can be used to extract a reduced set of discriminative features for classification, since it compresses discriminative information contained in the brain. Voxels marked by ROIs which were computed using the proposed method, yield classification results up to 90% of accuracy for controls (CN) and Alzheimer''s disease (AD) patients, and 84% of accuracy for Mild Cognitive Impairment (MCI) and AD patients.     

螺旋CT增强扫描对孤立性肺结节的诊断价值

目的:研究螺旋CT增强扫描时孤立性肺结节的诊断价值。方法:回顾分析经病理证实的恶性结节50例、炎性结节26例、结核瘤12例的螺旋CT增强扫描的表现。结果:恶性结节和炎性结节增强扫描的强化程度明显高于结核瘤(P＜0．05)。炎性结节强化峰值的时间较恶性结节延迟。恶性结节增强扫描出现点、条状及边缘强化。结论:螺旋CT增强扫描对孤立性肺结节的诊断具有重要临床应用价值。     

基于颜色直方图及双树复小波变换（DTCWT）的昆虫图像识别

为了给生产单位害虫管理的普通技术人员提供简便易操作的昆虫鉴别方法, 本文提出了一种新颖的基于图像颜色及纹理特征的昆虫图像识别方法。鳞翅目昆虫翅面图像经过预处理, 确定目标区域, 再进行特征提取。首先将彩色图像从三原色(red-green-blue, RGB)空间转换至色调饱和值（HSV）空间并提取有效区域内的色度、饱和度直方图特征, 然后经图像位置校准, 提取灰度图的双树复小波变换（DTCWT）特征; 匹配首先计算两颜色直方图特征向量之间的相关性, 将相关性大于阈值的样本再进一步用DTCWT特征匹配; DTCWT匹配通过计算Canberra距离实现, 从通过第一层颜色匹配的样本中取出最近邻作为最终匹配类别。算法在包含100类鳞翅目昆虫的图像库中进行试验验证, 取得了76%的识别率, 其中前翅识别率则达92%, 同时取得了理想的时间性能。试验结果证明了本文方法的有效性。     

Can Spectral CT Imaging Improve the Differentiation between Malignant and Benign Solitary Pulmonary Nodules?

Purpose

To quantitatively assess the value of dual-energy CT (DECT) in differentiating malignancy and benignity of solitary pulmonary nodules.

Materials and Methods

Sixty-three patients with solitary pulmonary nodules detected by CT plain scan underwent contrast enhanced CT scans in arterial phase (AP) and venous phase (VP) with spectral imaging mode for tumor type differentiation. The Gemstone Spectral Imaging (GSI) viewer was used for image display and data analysis. Region of interest was placed on the relatively homogeneous area of the nodule to measure iodine concentration (IC) on iodine-based material decomposition images and CT numbers on monochromatic image sets to generate spectral HU curve. Normalized IC (NIC), slope of the spectral HU curve (λ_HU) and net CT number enhancement on 70keV images were calculated. The two-sample t-test was used to compare quantitative parameters. Receiver operating characteristic curves were generated to calculate sensitivity and specificity.

Results

There were 63 nodules, with 37 malignant nodules (59%) and 26 benign nodules (41%). NIC, λ_HU and net CT number enhancement on 70keV images for malignant nodules were all greater than those of benign nodules. NIC and λ_HU had intermediate to high performances to differentiate malignant nodules from benign ones with the areas under curve of 0.89 and 0.86 respectively in AP, 0.96 and 0.89 respectively in VP. Using 0.30 as a threshold value for NIC in VP, one could obtain sensitivity of 93.8% and specificity of 85.7% for differentiating malignant from benign solitary pulmonary nodules. These values were statistically higher than the corresponding values of 74.2% and 53.8% obtained with the conventional CT number enhancement.

Conclusions

DECT imaging with GSI mode provides more promising value in quantitative way for distinguishing malignant nodules from benign ones than CT enhancement numbers.     

Lung tumors on multimodal radiographs derived from grating-based X-ray imaging – A feasibility study

PurposeThe purpose of this study was to assess whether grating-based X-ray imaging may have a role in imaging of pulmonary nodules on radiographs.Materials and methodsA mouse lung containing multiple lung tumors was imaged using a small-animal scanner with a conventional X-ray source and a grating interferometer for phase-contrast imaging. We qualitatively compared the signal characteristics of lung nodules on transmission, dark-field and phase-contrast images. Furthermore, we quantitatively compared signal characteristics of lung tumors and the adjacent lung tissue and calculated the corresponding contrast-to-noise ratios.ResultsOf the 5 tumors visualized on the transmission image, 3/5 tumors were clearly visualized and 1 tumor was faintly visualized in the dark-field image as areas of decreased small angle scattering. In the phase-contrast images, 3/5 tumors were clearly visualized, while the remaining 2 tumors were faintly visualized by the phase-shift occurring at their edges. No additional tumors were visualized in either the dark-field or phase-contrast images. Compared to the adjacent lung tissue, lung tumors were characterized by a significant decrease in transmission signal (median 0.86 vs. 0.91, p = 0.04) and increase in dark-field signal (median 0.71 vs. 0.65, p = 0.04). Median contrast-to-noise ratios for the visualization of lung nodules were 4.4 for transmission images and 1.7 for dark-field images (p = 0.04).ConclusionLung nodules can be visualized on all three radiograph modalities derived from grating-based X-ray imaging. However, our initial data suggest that grating-based multimodal X-ray imaging does not increase the sensitivity of chest radiographs for the detection of lung nodules.     

Utility of fast non-local means (FNLM) filter for detection of pulmonary nodules in chest CT for pediatric patient

PurposeThis study was aimed to evaluate the utility based on imaging quality of the fast non-local means (FNLM) filter in diagnosing lung nodules in pediatric chest computed tomography (CT).MethodsWe retrospectively reviewed the chest CT reconstructed with both filtered back projection (FBP) and iterative reconstruction (IR) in pediatric patients with metastatic lung nodules. After applying FNLM filter with six h values (0.0001, 0.001, 0.01, 0.1, 1, and 10) to the FBP images, eight sets of images including FBP, IR, and FNLM were analyzed. The image quality of the lung nodules was evaluated objectively for coefficient of variation (COV), contrast to noise ratio (CNR), and point spread function (PSF), and subjectively for noise, sharpness, artifacts, and diagnostic acceptability.ResultsThe COV was lowest in IR images and decreased according to increasing h values and highest with FBP images (P < 0.001). The CNR was highest with IR images, increased according to increasing h values and lowest with FBP images (P < 0.001). The PSF was lower only in FNLM filter with h value of 0.0001 or 0.001 than in IR images (P < 0.001). In subjective analysis, only images of FNLM filter with h value of 0.0001 or 0.001 rarely showed unacceptable quality and had comparable results with IR images. There were less artifacts in FNLM images with h value of 0.0001 compared with IR images (p < 0.001).ConclusionFNLM filter with h values of 0.0001 allows comparable image quality with less artifacts compared with IR in diagnosing metastatic lung nodules in pediatric chest CT.     

Pulmonary Nodule Detection in Patients with a Primary Malignancy Using Hybrid PET/MRI: Is There Value in Adding Contrast-Enhanced MR Imaging?

Purpose

To investigate the added value of post-contrast VIBE (volumetric-interpolated breath-hold examination) to PET/MR imaging for pulmonary nodule detection in patients with primary malignancies.

Materials and Methods

This retrospective institutional review board–approved study, with waiver of informed consent, included 51 consecutive patients who underwent ¹⁸F-fluorodeoxyglucose (FDG) PET/MR followed by PET/CT for cancer staging. In all patients, the thorax was examined with pre-and post-contrast VIBE MR with simultaneous PET acquisition. Two readers blinded to the patients’ data independently recorded their level of suspicion for pulmonary nodules based on PET, pre-contrast VIBE, and fused PET/MR images (first session), and reassessed them 4-weeks later after addition of post-contrast VIBE (second session). Jackknife alternative free-response receiver-operating-characteristic (JAFROC) analysis was performed, with PET/CT as the reference standard.

Results

A total of 151 pulmonary nodules (44 FDG-avid, 107 non-FDG-avid nodules) were detected on PET/CT, including 62 nodules≥5mm in diameter and 89 nodules<5mm. In the first session, the average nodule detection rate was 53.3% for all nodules, 97.7% for FDG-avid, 35.0% for non-FDG-avid nodules, 87.9% for nodules≥5mm and 29.2% for nodules<5mm. In the second session, the average detection rate was 53.3% for all nodules, 97.7% for FDG-avid, 35.0% for non-FDG-avid nodules, 85.5% for nodules≥5mm and 30.9% for nodules<5mm. The average JAFROC figure-of-merit was 0.837 in the first session and 0.848 in the second session. There were no significant differences in detection performance between sessions (P=0.48).

Conclusion

The addition of post-contrast VIBE to hybrid PET/MR imaging provided no additional value in the detection of pulmonary nodules.