Characterization of mammographic masses using a gradient-based segmentation algorithm and a neural classifier

Computerized methods have recently shown a great potential in providing radiologists with a second opinion about the visual diagnosis of the malignancy of mammographic masses. The computer-aided diagnosis (CAD) system we developed for the mass characterization is mainly based on a segmentation algorithm and on the neural classification of several features computed on the segmented mass. Mass-segmentation plays a key role in most computerized systems. Our technique is a gradient-based one, showing the main characteristic that no free parameters have been evaluated on the data set used in this analysis, thus it can directly be applied to data sets acquired in different conditions without any ad hoc modification. A data set of 226 masses (109 malignant and 117 benign) has been used in this study. The segmentation algorithm works with a comparable efficiency both on malignant and benign masses. Sixteen features based on shape, size and intensity of the segmented masses are extracted and analyzed by a multi-layered perceptron neural network trained with the error back-propagation algorithm. The capability of the system in discriminating malignant from benign masses has been evaluated in terms of the receiver-operating characteristic (ROC) analysis. A feature selection procedure has been carried out on the basis of the feature discriminating power and of the linear correlations interplaying among them. The comparison of the areas under the ROC curves obtained by varying the number of features to be classified has shown that 12 selected features out of the 16 computed ones are powerful enough to achieve the best classifier performances. The radiologist assigned the segmented masses to three different categories: correctly-, acceptably- and non-acceptably-segmented masses. We initially estimated the area under ROC curve only on the first category of segmented masses (the 88.5% of the data set), then extending the classification to the second subclass (reaching the 97.8% of the data set) and finally to the whole data set, obtaining A(z)=0.805+/-0.030, 0.787+/-0.024 and 0.780+/-0.023, respectively.     

Live level set: a hybrid method of livewire and level set for medical image segmentation

Livewire and level set are popular methods for medical image segmentation. In this article, the authors propose a hybrid method of livewire and level set, termed the live level set (LLS). The LLS replaces the one graph update iteration in the classic livewire with two iterations of graph updates. The first iteration generates an initial contour for a level set computation. The level set distance is then factored back into the cost function in the second iteration of graph update. The authors validated LLS using synthetic images. The results show that the performance of the LLS is superior to both the classic live wire and traditional level set methods in terms of accuracy, reproducibility, smoothness and running time. They also qualitatively evaluated the LLS using real clinical data.     

基于信息量的脉冲耦合神经网络改进分割算法

目的解决区域生长简化脉冲耦合神经网络（PCNN）算法中由于阈值参数选取不当导致的分割不足与过分割问题。方法在区域生长简化PCNN算法中引入熵来刻画图像的信息量。结果避免了对阈值参数选取。结论基于信息量的PCNN改进算法在分割精度、算法的稳定性等方面均优于简化区域生长PCNN算法。     

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.     

Integrating spatial fuzzy clustering with level set methods for automated medical image segmentation

The performance of the level set segmentation is subject to appropriate initialization and optimal configuration of controlling parameters, which require substantial manual intervention. A new fuzzy level set algorithm is proposed in this paper to facilitate medical image segmentation. It is able to directly evolve from the initial segmentation by spatial fuzzy clustering. The controlling parameters of level set evolution are also estimated from the results of fuzzy clustering. Moreover the fuzzy level set algorithm is enhanced with locally regularized evolution. Such improvements facilitate level set manipulation and lead to more robust segmentation. Performance evaluation of the proposed algorithm was carried on medical images from different modalities. The results confirm its effectiveness for medical image segmentation.     

Computer-assisted detection of mammographic masses: a template matching scheme based on mutual information

The purpose of this study was to develop a knowledge-based scheme for the detection of masses on digitized screening mammograms. The computer-assisted detection (CAD) scheme utilizes a knowledge databank of mammographic regions of interest (ROIs) with known ground truth. Each ROI in the databank serves as a template. The CAD system follows a template matching approach with mutual information as the similarity metric to determine if a query mammographic ROI depicts a true mass. Based on their information content, all similar ROIs in the databank are retrieved and rank-ordered. Then, a decision index is calculated based on the query's best matches. The decision index effectively combines the similarity indices and ground truth of the best-matched templates into a prediction regarding the presence of a mass in the query mammographic ROI. The system was developed and evaluated using a database of 1465 ROIs extracted from the Digital Database for Screening Mammography. There were 809 ROIs with confirmed masses (455 malignant and 354 benign) and 656 normal ROIs. CAD performance was assessed using a leave-one-out sampling scheme and Receiver Operating Characteristics analysis. Depending on the formulation of the decision index, CAD performance as high as A(zeta) = 0.87 +/- 0.01 was achieved. The CAD detection rate was consistent for both malignant and benign masses. In addition, the impact of certain implementation parameters on the detection accuracy and speed of the proposed CAD scheme was studied in more detail.     

An abdominal aortic aneurysm segmentation method: level set with region and statistical information

We present a system for segmenting the human aortic aneurysm in CT angiograms (CTA), which, in turn, allows measurements of volume and morphological aspects useful for treatment planning. The system estimates a rough "initial surface," and then refines it using a level set segmentation scheme augmented with two external analyzers: The global region analyzer, which incorporates a priori knowledge of the intensity, volume, and shape of the aorta and other structures, and the local feature analyzer, which uses voxel location, intensity, and texture features to train and drive a support vector machine classifier. Each analyzer outputs a value that corresponds to the likelihood that a given voxel is part of the aneurysm, which is used during level set iteration to control the evolution of the surface. We tested our system using a database of 20 CTA scans of patients with aortic aneurysms. The mean and worst case values of volume overlap, volume error, mean distance error, and maximum distance error relative to human tracing were 95.3% +/- 1.4% (s.d.); worst case = 92.9%, 3.5% +/- 2.5% (s.d.); worst case = 7.0%, 0.6 +/- 0.2 mm (s.d.); worst case = 1.0 mm, and 5.2 +/- 2.3 mm (s.d.); worst case = 9.6 mm, respectively. When implemented on a 2.8 GHz Pentium IV personal computer, the mean time required for segmentation was 7.4 +/- 3.6 min (s.d.). We also performed experiments that suggest that our method is insensitive to parameter changes within 10% of their experimentally determined values. This preliminary study proves feasibility for an accurate, precise, and robust system for segmentation of the abdominal aneurysm from CTA data, and may be of benefit to patients with aortic aneurysms.     

基于水平集稳健特征统计算法的脑肿瘤自动分割研究

目的:研究基于水平集的稳健特征统计算法在脑部CT图像上自动勾画肿瘤轮廓的方法。方法:选取种子点,通过稳健统计量描述种子点及其周围点对象的特征,基于水平集算法进行轮廓演化,确定肿瘤的边界。运用C++语言编程处理图像,得到肿瘤的分割结果。选用正确率、体素相对差异率、对称位置表面距离的均方根、对称位置的平均表面距离等指标评价肿瘤分割结果与医生勾画结果的一致性。结果:19例脑瘤患者的CT图像进行肿瘤勾画,均能自动准确勾画肿瘤轮廓。平均正确率为0.92,体素相对差异率为0.12,对称位置表面距离的均方根为0.25 mm,对称位置的平均表面距离为0.49 mm,各评价指标均优于区域增长算法。结论:基于水平集稳健特征统计的分割算法,可以实现肿瘤轮廓的自动勾画,结果准确可靠。     

Use of border information in the classification of mammographic masses

We are developing a new method to characterize the margin of a mammographic mass lesion to improve the classification of benign and malignant masses. Towards this goal, we designed features that measure the degree of sharpness and microlobulation of mass margins. We calculated these features in a border region of the mass defined as a thin band along the mass contour. The importance of these features in the classification of benign and malignant masses was studied in relation to existing features used for mammographic mass detection. Features were divided into three groups, each representing a different mass segment: the interior region of a mass, the border and the outer area. The interior and the outer area of a mass were characterized using contrast and spiculation measures. Classification was done in two steps. First, features representing each of the three mass segments were merged into a neural network classifier resulting in a single regional classification score for each segment. Secondly, a classifier combined the three single scores into a final output to discriminate between benign and malignant lesions. We compared the classification performance of each regional classifier and the combined classifier on a data set of 1076 biopsy proved masses (590 malignant and 486 benign) from 481 women included in the Digital Database for Screening Mammography. Receiver operating characteristic (ROC) analysis was used to evaluate the accuracy of the classifiers. The area under the ROC curve (A(z)) was 0.69 for the interior mass segment, 0.76 for the border segment and 0.75 for the outer mass segment. The performance of the combined classifier was 0.81 for image-based and 0.83 for case-based evaluation. These results show that the combination of information from different mass segments is an effective approach for computer-aided characterization of mammographic masses. An advantage of this approach is that it allows the assessment of the contribution of regions rather than individual features. Results suggest that the border and the outer areas contained the most valuable information for discrimination between benign and malignant masses.     

A novel region-based level set method initialized with mean shift clustering for automated medical image segmentation

Appropriate initialization and stable evolution are desirable criteria to satisfy in level set methods. In this study, a novel region-based level set method utilizing both global and local image information complementarily is proposed. The global image information is extracted from mean shift clustering without any prior knowledge. Appropriate initial contours are obtained by regulating the clustering results. The local image information, as extracted by a data fitting energy, is employed to maintain a stable evolution of the zero level set curves. The advantages of the proposed method are as follows. First, the controlling parameters of the evolution can be easily estimated by the clustering results. Second, the automaticity of the model increases because of a reduction in computational cost and manual intervention. Experimental results confirm the efficiency and accuracy of the proposed method for medical image segmentation.     

Skin image segmentation based on energy transformation

In this paper, a new method on extraction of human skin grid centerlines is proposed. The method introduces the physics concepts of kinetic and potential energy into image processing. Regional energy is calculated. Energy transformation is performed to map the pixels from the grayscale space into energy space. Then, the energy image undergoes a morphological filter to remove noises and spurious minima. The amount of filtering can be manually tuned to get a different result. Subsequently, normal curvature of the energy surface is utilized to identify the principal direction and principal curvatures. The ridge centerlines can be detected at the image locations where the principal direction is perpendicular to the normal vector. The experiment shows that this method is an effective one for the purpose of extracting human skin grid.     

PET image reconstruction with anatomical edge guided level set prior

Acquiring both anatomical and functional images during one scan, PET/CT systems improve the ability to detect and localize abnormal uptakes. In addition, CT images provide anatomical boundary information that can be used to regularize positron emission tomography (PET) images. Here we propose a new approach to maximum a posteriori reconstruction of PET images with a level set prior guided by anatomical edges. The image prior models both the smoothness of PET images and the similarity between functional boundaries in PET and anatomical boundaries in CT. Level set functions (LSFs) are used to represent smooth and closed functional boundaries. The proposed method does not assume an exact match between PET and CT boundaries. Instead, it encourages similarity between the two boundaries, while allowing different region definition in PET images to accommodate possible signal and position mismatch between functional and anatomical images. While the functional boundaries are guaranteed to be closed by the LSFs, the proposed method does not require closed anatomical boundaries and can utilize incomplete edges obtained from an automatic edge detection algorithm. We conducted computer simulations to evaluate the performance of the proposed method. Two digital phantoms were constructed based on the Digimouse data and a human CT image, respectively. Anatomical edges were extracted automatically from the CT images. Tumors were simulated in the PET phantoms with different mismatched anatomical boundaries. Compared with existing methods, the new method achieved better bias-variance performance. The proposed method was also applied to real mouse data and achieved higher contrast than other methods.     

Analysis of temporal changes of mammographic features: computer-aided classification of malignant and benign breast masses

A new classification scheme was developed to classify mammographic masses as malignant and benign by using interval change information. The masses on both the current and the prior mammograms were automatically segmented using an active contour method. From each mass, 20 run length statistics (RLS) texture features, 3 speculation features, and 12 morphological features were extracted. Additionally, 20 difference RLS features were obtained by subtracting the prior RLS features from the corresponding current RLS features. The feature space consisted of the current RLS features, the difference RLS features, the current and prior speculation features, and the current and prior mass sizes. Stepwise feature selection and linear discriminant analysis classification were used to select and merge the most useful features. A leave-one-case-out resampling scheme was used to train and test the classifier using 140 temporal image pairs (85 malignant, 55 benign) obtained from 57 biopsy-proven masses (33 malignant, 24 benign) in 56 patients. An average of 10 features were selected from the 56 training subsets: 4 difference RLS features, 4 RLS features, and 1 speculation feature from the current image, and 1 speculation feature from the prior, were most often chosen. The classifier achieved an average training Az of 0.92 and a test Az of 0.88. For comparison, a classifier was trained and tested using features extracted from the 120 current single images. This classifier achieved an average training Az of 0.90 and a test Az of 0.82. The information on the prior image significantly (p = 0.015) improved the accuracy for classification of the masses.     

An ellipse-fitting based method for efficient registration of breast masses on two mammographic views

When reading mammograms, radiologists routinely search for and compare suspicious breast lesions identified on two corresponding craniocaudal (CC) and mediolateral oblique (MLO) views. Automatically identifying and matching the same true-positive breast lesions depicted on two views is an important step for developing successful multiview based computer-aided detection (CAD) schemes. The authors developed a method to automatically register breast areas and detect matching strips of interest used to identify the matched mass regions depicted on CC and MLO views. The method uses an ellipse based model to fit the breast boundary contour (skin line) and set a local Cartesian coordinate system for each view. One intersection point between the major/minor axis and the fitted ellipse perimeter passed through breast boundary is selected as the origin and the majoraxis and the minoraxis of the ellipse are used as the two axis of the Cartesian coordinate system. When a mass is identified on one view, the scheme computes its position in the local coordinate system. Then, the distance is mapped onto the local coordinate of the other view. At the end of the mapped distance a registered centerline of the matching strip is created. The authors established an image database that includes 200 test examinations each depicting one verified mass visible on the two views. They tested whether the registered centerline identified on another view can be used to locate the matched mass region. The experiments show that the average distance between the mass region centers and the registered centerlines was +/- 8.3 mm and in 91% of testing cases the registered centerline actually passes through the matched mass regions. A matching strip width of 47 mm was required to achieve 100% sensitivity for the test database. The results demonstrate the feasibility of the proposed method to automatically identify masses depicted on CC and MLO views, which may improve future development of multiview based CAD schemes.     

基于卷积神经网络和图像显著性的心脏CT图像分割

目的心脏医学影像中,感兴趣部分的提取与分割是诊断心脏病变部位的关键。由于心脏舒张、收缩以及血液的流动,心脏CT图像易出现弱边界、伪影,传统分割算法易产生过度分割的情况。为此,提出一种基于卷积神经网络和图像显著性的心脏CT图像分割方法。方法采用卷积神经网络对目标区域进行定位,滤除肋骨、肌肉等造影对比不明显部分,截取出感兴趣区域,结合感兴趣区域的对比度计算并提高感兴趣区域的心脏组织的显著值。通过获得的显著值图像截取心脏图像,并与区域生长算法的分割结果进行对比。最后使用泰州人民医院11例患者的影像数据对算法模型进行训练和测试,随机选择9例用于训练,剩余2例用于测试。结果所提算法模型在心底、心中、心尖3个心脏分段的分割正确率分别达到了92.79%、92.79%、94.11%,均优于基于区域生长的分割方法。结论基于卷积神经网络和图像显著性的分割方法能够准确获取心脏的外围轮廓,轮廓边缘更加平滑,完全能够满足CT图像序列的心脏全自动分割任务需求,分割后的图像更有利于医生对患者心脏健康状况和病变部位的观察。     

基于卷积神经网络和Transformer的肝脏CT图像分割方法

针对现有的卷积神经网络在肝脏图像分割上精度较低的问题,提出了一种以U-Net网络模型为基础的分割算法。将多头自注意力机制引入到U-Net网络的跳跃连接中,在编码器部分使用空洞卷积,采用混合损失函数从而提高分割精度。在LITS数据集上通过实验结果表明,利用本文方法进行肝脏分割与传统U-Net方法相比Dice系数提升3.3%,平均交并比提升了2.4%,平均像素准确率提升了3.66%。     

基于深度学习的轴突三维图像分割与重构

目的:设计适用于神经轴突荧光显微图像三维分割任务的深度神经网络(DNN),提高神经轴突自动重构的准确性。方法:将三维图像分割任务转化为在3个正交投影方向上的二维分割任务,在开源网络DeepMACT的基础上,利用多通道输入降低压缩维度上的信息损失,利用神经轴突骨架加权的损失函数训练以强调神经骨架连贯性,提出SWCUnet。采用转盘共聚焦荧光显微成像采集的小鼠大脑稀疏标记神经元神经轴突部分49个图块作为数据集,以人工标注的形态重构结果作为金标准训练网络。对网络模型输出的二维分割图像进行三维复原,并以三维分割结果输入MOST算法进行自动重构。结果:SWCUnet (32通道,骨架权重5)三维分割F1-score达到0.662,较DeepMACT提升0.132。基于三维分割结果的自动重构F1-score达到0.80,比基于原图的自动重构提升0.24。结论:SWCUnet可以较好地提取高分辨荧光显微图像中的神经轴突特征,输出的三维分割结果实现了大幅提升神经轴突骨架形态的自动重构准确率的目标,为小鼠大脑稀疏标记神经元全脑成像数据的大规模自动化重构提供了一种新工具。     

基于生成对抗网络的肝脏CT图像分割

目的 从腹部计算机断层扫描(computed tomography,CT)图像中分割出肝脏区域,对于肝脏疾病早期诊断、肝脏大小估计以及3D重建十分重要,精准快速地分割出肝脏边缘成为研究要点.方法 采用公开发表的肝脏肿瘤数据集为研究对象,融合生成对抗网络和Unet网络对CT图像实现肝脏的自动分割.首先将腹部CT图像输入到Unet网络进行分割预测,然后通过生成对抗网络(generative adversarial networks,GAN)进行对抗训练,使得预测结果更加接近于真实结果,同时在进行对抗训练的过程中探索了不同的距离约束函数对于分割结果的影响;预测的分割结果通过Dice分数(dice similarity coefficient,Dice)、IoU分数(intersection over union,IoU)、像素精确度(pixel accuracy,PA)、相对体积误差(relative volume difference,RVD)以及相对表面积误差(relative surface area error,RSSD)在CT-核磁健康腹部器官分割挑战数据集[combined(CT-MR)healthy abdominal organ segmentation challenge data,CHAOS]数据集上进行评价.结果 L2距离约束的Gan-Unet网络可以很好地对肝脏进行分割,其Dice、IoU和PA分别达到了94.9％、91.3％、99.4％,相比于Unet的Dice、IoU和PA为92.3％、86.7％、95.8％有明确的提升.在三维指标中,本文的方法在RVD、RSSD为0.026、0.079,相比于Unet的0.042、0.191有明显下降.结论 通过对Unet网络进行生产对抗训练以及在训练过程中引入距离约束函数可以提高肝脏分割的性能,肝脏分割结果可以应用于计算机辅助诊断系统中.     

基于纹理分析的带标记线心脏MR图像分割

背景：左心室边界的准确分割是对左心室运动及形变进行分析的前提。由于受带标记线心脏核磁共振图像中标记线强梯度的影响,对左心室内膜的提取变得非常困难。 目的：为了抑制标记线对图像分割的影响,提出了一种基于最小值-方差能量图的纹理分析方法。 方法：首先对局部最小值和方差进行加权求和,得到能量图;然后利用中值滤波滤除能量图中的伪影并保持边界;最后,应用GVF-snake模型提取左心室内膜。 结果与结论：针对标记线在心脏MR图像中的分布特征,提出了一种基于最小值-方差的纹理分析方法,该方法有效地去除了标记线。结果提示,对使用该纹理分析方法生成的能量图应用GVF-snake模型可以较好地提取左心室内膜。