基于灰度对比和自适应小波变换的X射线图像增强

背景:X射线检查作为常规的检查方式得到了广泛的应用,然而由于现有技术的局限性,使得X射线图像往往具有灰度对比度低和噪声影响等缺点,因此,现有的X射线图像往往达不到医生的要求。目的:增强和去噪处理对比度较低且含有噪声的X射线图像,以达到易于医生理解和识别的目的。方法:针对空间域处理和变换域处理增强X射线图像的不足,提出了基于灰度对比和自适应小波变换的X射线图像增强算法。首先,选择需要增强和减弱的灰度范围,并根据八邻域灰度对比增强算法对X射线图像进行灰度变换,并用中值滤波算法对图像进行平滑;然后,对X射线图像进行小波分解,并运用相邻分解层之间相关系数的大小来确定细节信号和噪声。结果与结论:应用了灰度对比和自适应小波变换相结合的X射线图像增强算法,把基于空间域增强的方法和基于变换域的方法有机地结合起来,比传统的单一增强方法更为优越。实验结果证明它能自适应地增强X射线图像的灰度对比,使得图像细节的显示更加清晰,同时在一定程度上去除了噪声的干扰,对于灰度对比度较低的图像效果更加明显。     

基于灰度共生矩阵的直肠肿瘤超声造影不均匀程度的分级方法

经直肠超声造影是直肠肿瘤常规检查方法,不同肿瘤内的造影剂分布的不均匀程度是重要的影像特征,依赖人工方法可以对该特征进行分级。但是针对大量数据时,人工分级繁琐缓慢,且结果容易受到影响。本文提出了一种基于灰度共生矩阵(GLCM)的提取直肠肿瘤超声造影图像内造影剂分布特征的计算机分级方法。具体流程包括压缩图片的灰度、计算灰度共生矩阵的纹理统计量、结合特征选择和主成分分析(PCA)进行降维以及训练和验证二次判别分析模型(QDA)。经过十次交叉验证,机器分级的总体准确率为87.01%;各级的准确率分别为:Ⅰ级52.94%;Ⅱ级96.48%;Ⅲ级92.35%。本文方法对Ⅱ级及Ⅲ级图像的判定准确率较高,可以帮助识别直肠肿瘤超声造影图像内的造影剂分布特征,有望用于辅助判定直肠肿瘤超声造影的不均匀程度。     

灰度与形状同步匹配的非刚性配准研究

基于灰度的非刚性配准算法一般假设参考图像和浮动图像对应结构之间的灰度保持一致,然而在基于图谱的图像配准应用中,这种假设往往不符合实际。本文在给出一种可以同时校正灰度和形状差异的弹性配准算法的同时,针对该算法不能校正局部微小形变的弱点,提出采用自由项变换的方法进行校正以提高配准精度。配准实验基于20个IBSR真实脑部MRI图像,结果表明配准后图像与参考图像间的互相关系数得到明显提高。实验证明,本文提出的方法不仅能够同时校正形状差异和灰度变化,而且具有较高的配准质量。     

基于纹理统计特征的医学图像颜色映射方法

为提高灰度医学图像颜色增强的有效性和视觉合理性,提出了一种基于纹理统计特征的颜色增强处理方法。此方法的颜色映射机理不是传统的在灰度级和颜色模型间经验性构筑一对一或多对一的映射关系函数,而是借助彩色可视化人体（VHP）解剖断层源图像数据,利用共生矩阵纹理统计特征信息,实现颜色在图像间的传输。实验结果证明了此方法的可行性,高维度、高阶数统计量的运用提高了颜色映射的准确性和有效性。     

基于生成对抗网络的乳腺癌组织病理图像样本均衡化

针对乳腺癌组织病理图像中各类样本的不均衡性,本研究构建了基于条件控制和深度卷积的两种乳腺癌组织病理图像样本生成对抗网络并生成人造样本,以实现样本均衡化。实验验证了两种网络用于数据均衡化的可靠性,发现在处理不均衡数据时基于深度卷积的生成对抗网络效果更好,基于条件控制的生成对抗网络鲁棒性更强;分析了增加人造样本对深度学习算法的影响。结果表明,本研究提出的数据均衡化方法将训练所得网络的分类准确率平均提升了近5%,生成对抗网络可以缓解深度学习在医学领域的应用中数据分布不平衡的问题。     

基于多尺度非线性扩散的超声图像斑点噪声去除算法

针对现有去噪算法可能造成超声图像细节模糊甚至丢失的问题,本文提出基于多尺度非线性扩散（multiscale nonlinear diffusion,MSND）的超声图像去噪模型.该模型结合冗余拉普拉斯塔形数据分解和非线性扩散的优点,利用冗余拉普拉斯塔形数据分解将图像分解为等大小的空间-频率子带,综合各子带的特征得到图像边缘和细节的精细表示,然后根据所得的综合特征指导各子带图像的非线性扩散.实验结果表明本文算法在去除噪声的同时能有效地保留和增强边界与细节.     

基于模糊均值聚类算法的灰度不均匀脑MR图像的分割

磁共振图像经常被含有缓慢变化的灰度不均匀场所破坏,不均匀场会造成同一组织的灰度发生变化,从而影响计算机辅助诊断的准确性.传统的基于灰度信息的分割方法对具有不均匀场的磁共振图像分割效果往往并不理想.文章改进了基于灰度信息的模糊C均值(FCM)算法,将偏移场模型、代表图像空间信息的邻域控制信息和最小二乘曲面拟合方法有机结合,能同时实现图像的校正和聚类,适用于灰度不均匀脑部磁共振图像的分割,分割精度明显优于已有的基于FCM的分割方法.     

基于Local Jet变换空间纹理特征的肺结节分类方法

为了在纹理特征下改善肺结节良、恶性的模式识别,提出一种基于local jet变换空间的纹理特征提取方法。首先利用二维高斯函数的前三阶偏微分函数将结节原图像变换到local jet纹理图像空间,然后利用纹理描述子在该空间提取特征参数。以灰度值的前四阶矩和基于灰度共生矩阵的特征参数作为纹理描述子,分别提取结节原图像和变换后纹理图像的特征参数,以BP神经网络作为分类器,对同一纹理描述子下的2个不同图像空间的经核主成分分析优化后的特征参数集进行结节良、恶性分类。以157个肺结节(51个良性,106个恶性)作为实验数据进行对比实验,结果显示:两种纹理描述子基于local jet变换空间提取的特征参数分别获得82.69%和86.54%的分类正确率,较原图像空间提高6%～8%,同时AUC值提高约10%。实验结果表明,基于local jet变换空间提取的纹理特征可以有效地改善肺结节良、恶性的模式识别。     

基于调幅-调频与熵图多模态医学图像的配准

背景：基于传统互信息量的多模态医学图像配准方法配准时需要利用二维直方图或者Parzen窗函数的方法估计概率密度分布,进而计算互信息量,这种方式计算速度慢,而且只考虑了图像的灰度信息,容易出现误配。 目的：针对目前主流的配准方法鲁棒性差、耗时的缺点,提出了一种新的基于调幅-调频(AM-FM)特征互信息量的快速配准方法。 方法：该方法考虑了图像的空间和结构信息;首先通过AM-FM模型对图像进行分解,得到图像的AM-FM特征,与图像的灰度特征一起组成高维特征;然后利用熵图和最小生成树加快AM-FM特征互信息量的计算,从而实现了医学图像的快速配准。 结果与结论：对20组磁共振T1-T2加权图像、CT/正电子发射计算机断层成像图像进行了实验,结果表明该方法在图像空间分辨率较低,有噪声影响等情况下均可以达到较好的结果,且配准精度优于国际上的主流方法,具有计算速度快,精度高,鲁棒性强的特点,适于临床应用。     

无线胶囊内窥镜图像小肠息肉的自动识别

息肉是小肠常见疾病之一。无线胶囊内窥镜(WCE)是检查小肠疾病的常规手段,但每次检查都会产生大量图像,却仅可能包含少数病变图像。目前WCE病变的筛查高度依赖于医生的临床经验,耗时费力,且可能发生漏检或误检,因此实现WCE图像小肠息肉的自动识别意义重大。基于深度学习框架,结合数据增强技术和迁移学习策略,提出实现小肠息肉识别的新方法。基于原始数据集(包含4 300张正常图像和429张息肉图像)和拓展数据集(包含6 920张正常图像和6 864张息肉图像),对比分析不同的深度卷积神经网络模型(AlexNet、VGGNet和GoogLeNet)对息肉的识别效果。实验结果表明,在随机初始化的卷积神经网络中,GoogLeNet模型对息肉的识别效果最好,其敏感性、特异性和准确性分别达到97.18%、98.78%和97.99%,说明增加网络深度可以有效提高识别率。但网络深度增加需要更高的硬件配置和训练时间,因此结合迁移学习策略,AlexNet模型的敏感性、特异性和准确性分别达到了96.57%、98.89%和97.74%,AUC为0.996,表明该方法能有效提高模型整体性能,同时降低对训练时间和实验配置的要求。与传统手工提取图像特征或仅基于深层卷积神经网络进行分类的方法相比,所提出的方法可以在有限的训练数据和实验环境下为小肠息肉的自动识别提供有效的解决方案,有望帮助医生高效完成基于WCE检查的消化道疾病的精准诊断。     

A method for pharmacokinetic modelling of dynamic contrast enhanced MRI studies of rapidly enhancing lesions acquired in a clinical setting

Abnormal microcirculation is a feature of many neoplastic and non-neoplastic diseases. Physiological variables that characterize tissue microcirculation (capillary permeability and the volume of the extravascular extracellular fluid) are altered in pathological states. Pharmacokinetic analysis of dynamic contrast enhanced MRI (DCE-MRI) has found a widespread use in the assessment of abnormal microcirculation due to the direct link between the contrast agent kinetics and underlying microcirculatory properties. A representation of temporal variation of contrast agent concentration in blood plasma (C(p)(t)) is central to this analysis. In clinical applications of DCE-MRI, signal intensity curves derived from rapidly enhancing lesions often display a sigmoid shape during the initial phase of contrast uptake and rapid arrival at the equilibrium phase. In this work, the features of two principal methods for pharmacokinetic analysis of DCE-MRI which allow for theoretical representation of C(p)(t) are examined and combined to improve analysis of this particular class of DCE-MRI curves. The proposed method allows the representation of the initial sigmoid part of the enhancement profiles whilst retaining a realistic representation of C(p)(t) based on previously published measurements obtained in healthy volunteers. The results of the computer simulations indicate that in rapidly enhancing lesions, with the transfer constant K(trans) greater than 0.1 min(-1), the DCE-MRI acquisition can be restricted to 5 min post-injection and a mono-exponential representation of C(p)(t) decay is sufficient. Furthermore, non-ideal bolus delivery can be represented as a short constant rate infusion when the tissue under investigation exhibits a sigmoid pattern of contrast uptake.     

Quantitative effects of using compressed sensing in dynamic contrast enhanced MRI

Dynamic contrast enhanced magnetic resonance imaging (DCE-MRI) involves the acquisition of images before, during and after the injection of a contrast agent. In order to perform quantitative modeling on the resulting signal intensity time course, data must be acquired rapidly, which compromises spatial resolution, signal to noise and/or field of view. One approach that may allow for gains in temporal or spatial resolution or signal to noise of an individual image is to use compressed sensing (CS) MRI. In this study, we demonstrate the accuracy of extracted pharmacokinetic parameters from DCE-MRI data obtained as part of pre-clinical and clinical studies in which fully sampled acquisitions have been retrospectively undersampled by factors of 2, 3 and 4 in Fourier space and then reconstructed with CS. The mean voxel-level concordance correlation coefficient for K(trans) (i.e. the volume transfer constant) obtained from the 2× accelerated and the fully sampled data is 0.92 and 0.90 for mouse and human data, respectively; for 3×, the results are 0.79 and 0.79, respectively; for 4×, the results are 0.64 and 0.70, respectively. The mean error in the tumor mean K(trans) for the mouse and human data at 2× acceleration is 1.8% and -4.2%, respectively; at 3×, 3.6% and -10%, respectively; at 4×, 7.8% and -12%, respectively. These results suggest that CS combined with appropriate reduced acquisitions may be an effective approach to improving image quality in DCE-MRI.     

Intensity based image registration by minimizing exponential function weighted residual complexity

In this paper, we propose a novel intensity-based similarity measure for medical image registration. Traditional intensity-based methods are sensitive to intensity distortions, contrast agent and noise. Although residual complexity can solve this problem in certain situations, relative modification of the parameter can generate dramatically different results. By introducing a specifically designed exponential weighting function to the residual term in residual complexity, the proposed similarity measure performed well due to automatically weighting the residual image between the reference image and the warped floating image. We utilized local variance of the reference image to model the exponential weighting function. The proposed technique was applied to brain magnetic resonance images, dynamic contrast enhanced magnetic resonance images (DCE-MRI) of breasts and contrast enhanced 3D CT liver images. The experimental results clearly indicated that the proposed approach has achieved more accurate and robust performance than mutual information, residual complexity and Jensen–Tsallis.     

Registration of dynamic contrast-enhanced MRI using a progressive principal component registration (PPCR)

Registration of dynamic contrast-enhanced magnetic resonance images (DCE-MRI) of soft tissue is difficult. Conventional registration cost functions that depend on information content are compromised by the changing intensity profile, leading to misregistration. We present a new data-driven model of uptake patterns formed from a principal components analysis (PCA) of time-series data, avoiding the need for a physiological model. We term this process progressive principal component registration (PPCR). Registration is performed repeatedly to an artificial time series of target images generated using the principal components of the current best-registered time-series data. The aim is to produce a dataset that has had random motion artefacts removed but long-term contrast enhancement implicitly preserved. The procedure is tested on 22 DCE-MRI datasets of the liver. Preliminary assessment of the images is by expert observer comparison with registration to the first image in the sequence. The PPCR is preferred in all cases where a preference exists. The method requires neither segmentation nor a pharmacokinetic uptake model and can allow successful registration in the presence of contrast enhancement.     

基于EMD与IMF分量统计特性的ECG去噪

经验模式分解（EMD）域内心电（ECG）信号的去噪,通常为基于QRS特征波经验性识别固有模态函数（IMF）分量并重建ECG信号。由于该方法引入个人误差,因此识别不准确。针对此问题,本文提出利用EMD与IMF分量统计特性对ECG信号进行去噪。本方法首先对含噪ECG信号进行EMD分解得到一系列IMF分量,然后利用IMF分量的统计特性识别IMF分量属性,并采用被识别为ECG信号的IMF分量重建ECG信号。该识别方法基于统计学方法,具有统计学和现实物理意义。将本方法应用于真实ECG信号去噪处理中,结果表明,本方法可有效去除ECG信号基线漂移噪声与肌电干扰噪声,去噪效果优于经验法。     

Quantitative comparison of post‐processing methods for reduction of frequency modulation sidebands in non‐water suppression 1H MRS

Non‐water suppression MRS (NWS MRS) has several advantages. First, the unsuppressed water signal can be used as internal calibration for metabolite quantification and as a reliable frequency/phase reference for retrospective motion correction. Second, it avoids the potential artifacts caused by incomplete water suppression (WS) and extra radiofrequency deposition from WS pulses. However, the frequency modulation (FM) sidebands originating from a large water signal will distort the spectrum. Among the methods proposed to solve the problems caused by FM sidebands, post‐acquisition processing methods are superior in flexibility for general use compared with experimental methods. In this study, we propose two algorithms based on advanced matrix decomposition to remove the FM sidebands. These methods, the simultaneous diagonalization (QZ) algorithm and its subsequent variant, the simultaneously generalized Schur decomposition (SGSD) algorithm, were numerically evaluated using computer simulations. In addition, we quantitatively compared the performance of these methods and the modulus method in an in vitro experiment and in vivo NWS MRS against conventional WS data. Our results show that the proposed SGSD algorithm can reduce the FM sidebands to achieve superior estimation of concentration on three major metabolites. This method can be applied directly to spectra pre‐acquired under various experimental conditions without modifying the acquisition sequences. Copyright © 2012 John Wiley & Sons, Ltd.     

肾脏射频消融中超声图像特征参数与温度关系的研究

为探索肾脏射频消融中超声图像特征参数与温度的相关性，设计并进行了新鲜离体猪肾脏射频消融实验。记录热 消融过程中的温度（侵入式热电偶测量）和B超影像数据，采用将温度探针视为圆形的方法和阈值分割法去除感兴趣区域 中的探针，提取灰度均值、灰度标准差和灰度梯度值等特征参数，使用MATLAB软件对得到的灰度均值、灰度标准差和温 度作回归分析，采用连续分段函数模型进行数据拟合。证明了阈值分割法可用于探针去除，肾脏射频消融中的超声图像 特征参数与温度具有相关性，得到拟合良好的灰度均值-温度、灰度标准差-温度模型。但所得模型中的参数会随图像增 益、消融组织差异变化，在后续研究中应排除此类干扰，得到更具有临床价值的温度测量模型。     

Temporal Analysis of Tumor Heterogeneity and Volume for Cervical Cancer Treatment Outcome Prediction: Preliminary Evaluation

In this paper, we present a method of quantifying the heterogeneity of cervical cancer tumors for use in radiation treatment outcome prediction. Features based on the distribution of masked wavelet decomposition coefficients in the tumor region of interest (ROI) of temporal dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) studies were used along with the imaged tumor volume to assess the response of the tumors to treatment. The wavelet decomposition combined with ROI masking was used to extract local intensity variations in the tumor. The developed method was tested on a data set consisting of 23 patients with advanced cervical cancer who underwent radiation therapy; 18 of these patients had local control of the tumor, and five had local recurrence. Each patient participated in two DCE-MRI studies: one prior to treatment and another early into treatment (2–4 weeks). An outcome of local control or local recurrence of the tumor was assigned to each patient based on a posttherapy follow-up at least 2 years after the end of treatment. Three different supervised classifiers were trained on combinational subsets of the full wavelet and volume feature set. The best-performing linear discriminant analysis (LDA) and support vector machine (SVM) classifiers each had mean prediction accuracies of 95.7%, with the LDA classifier being more sensitive (100% vs. 80%) and the SVM classifier being more specific (100% vs. 94.4%) in those cases. The K-nearest neighbor classifier performed the best out of all three classifiers, having multiple feature sets that were used to achieve 100% prediction accuracy. The use of distribution measures of the masked wavelet coefficients as features resulted in much better predictive performance than those of previous approaches based on tumor intensity values and their distributions or tumor volume alone.     

Estimation of the noisy component of anatomical backgrounds.

The knowledge of the relationship that links radiation dose and image quality is a prerequisite to any optimization of medical diagnostic radiology. Image quality depends, on the one hand, on the physical parameters such as contrast, resolution, and noise, and on the other hand, on characteristics of the observer that assesses the image. While the role of contrast and resolution is precisely defined and recognized, the influence of image noise is not yet fully understood. Its measurement is often based on imaging uniform test objects, even though real images contain anatomical backgrounds whose statistical nature is much different from test objects used to assess system noise. The goal of this study was to demonstrate the importance of variations in background anatomy by quantifying its effect on a series of detection tasks. Several types of mammographic backgrounds and signals were examined by psychophysical experiments in a two-alternative forced-choice detection task. According to hypotheses concerning the strategy used by the human observers, their signal to noise ratio was determined. This variable was also computed for a mathematical model based on the statistical decision theory. By comparing theoretical model and experimental results, the way that anatomical structure is perceived has been analyzed. Experiments showed that the observer's behavior was highly dependent upon both system noise and the anatomical background. The anatomy partly acts as a signal recognizable as such and partly as a pure noise that disturbs the detection process. This dual nature of the anatomy is quantified. It is shown that its effect varies according to its amplitude and the profile of the object being detected. The importance of the noisy part of the anatomy is, in some situations, much greater than the system noise. Hence, reducing the system noise by increasing the dose will not improve task performance. This observation indicates that the tradeoff between dose and image quality might be optimized by accepting a higher system noise. This could lead to a better resolution, more contrast, or less dose.     

Computer-Aided Diagnosis of Breast DCE-MRI Images Using Bilateral Asymmetry of Contrast Enhancement Between Two Breasts

Dynamic contrast material-enhanced magnetic resonance imaging (DCE-MRI) of breasts is an important imaging modality in breast cancer diagnosis with higher sensitivity but relatively lower specificity. The objective of this study is to investigate a new approach to help improve diagnostic performance of DCE-MRI examinations based on the automated detection and analysis of bilateral asymmetry of characteristic kinetic features between the left and right breast. An image dataset involving 130 DCE-MRI examinations was assembled and used in which 80 were biopsy-proved malignant and 50 were benign. A computer-aided diagnosis (CAD) scheme was developed to segment breast areas depicted on each MR image, register images acquired from the sequential MR image scan series, compute average contrast enhancement of all pixels in one breast, and a set of kinetic features related to the difference of contrast enhancement between the left and right breast, and then use a multi-feature based Bayesian belief network to classify between malignant and benign cases. A leave-one-case-out validation method was applied to test CAD performance. The computed area under a receiver operating characteristic (ROC) curve is 0.78 ± 0.04. The positive and negative predictive values are 0.77 and 0.64, respectively. The study indicates that bilateral asymmetry of kinetic features between the left and right breasts is a potentially useful image biomarker to enhance the detection of angiogenesis associated with malignancy. It also demonstrates the feasibility of applying a simple CAD approach to classify between malignant and benign DCE-MRI examinations based on this new image biomarker.