Semiautomatic three-dimensional segmentation of the prostate using two-dimensional ultrasound images

In this paper, we report on two methods for semiautomatic three-dimensional (3-D) prostate boundary segmentation using 2-D ultrasound images. For each method, a 3-D ultrasound prostate image was sliced into the series of contiguous 2-D images, either in a parallel manner, with a uniform slice spacing of 1 mm, or in a rotational manner, about an axis approximately through the center of the prostate, with a uniform angular spacing of 5 degrees. The segmentation process was initiated by manually placing four points on the boundary of a selected slice, from which an initial prostate boundary was determined. This initial boundary was refined using the Discrete Dynamic Contour until it fit the actual prostate boundary. The remaining slices were then segmented by iteratively propagating this result to an adjacent slice and repeating the refinement, pausing the process when necessary to manually edit the boundary. The two methods were tested with six 3-D prostate images. The results showed that the parallel and rotational methods had mean editing rates of 20% and 14%, and mean (mean absolute) volume errors of -5.4% (6.5%) and -1.7% (3.1%), respectively. Based on these results, as well as the relative difficulty in editing, we conclude that the rotational segmentation method is superior.     

Comparative evaluation of image segmentation methods for volume quantitation in SPECT.

A wide variety of image segmentation techniques have been proposed for the measurement of organ or lesion volumes in SPECT images. Evaluation of the relative performance of the various methods is difficult due to wide variations in system response characteristics, size, shape, and contrast of the imaged objects, and image acquisition and processing techniques. Selected image segmentation methods for volume quantitation in SPECT were applied to a set of simulated SPECT images containing objects ranging in volume from 1.8 to 113.1 cc. The specific segmentation methods included: (1) operator drawn regions of interest, (2) count-based methods, (3) three levels of fixed thresholds, (4) an adaptive threshold (GLH method), (5) a two-dimensional (2-D) edge detection method, and (6) a three-dimensional (3-D) edge detection method. In general, the 3-D edge detection method required minimal operator intervention while providing the most accurate and consistent estimates of object volume across changes in object contrast and size.     

A region-based segmentation of tumour from brain CT images using nonlinear support vector machine classifier

The proposed system provides new textural information for segmenting tumours, efficiently and accurately and with less computational time, from benign and malignant tumour images, especially in smaller dimensions of tumour regions of computed tomography (CT) images. Region-based segmentation of tumour from brain CT image data is an important but time-consuming task performed manually by medical experts. The objective of this work is to segment brain tumour from CT images using combined grey and texture features with new edge features and nonlinear support vector machine (SVM) classifier. The selected optimal features are used to model and train the nonlinear SVM classifier to segment the tumour from computed tomography images and the segmentation accuracies are evaluated for each slice of the tumour image. The method is applied on real data of 80 benign, malignant tumour images. The results are compared with the radiologist labelled ground truth. Quantitative analysis between ground truth and the segmented tumour is presented in terms of segmentation accuracy and the overlap similarity measure dice metric. From the analysis and performance measures such as segmentation accuracy and dice metric, it is inferred that better segmentation accuracy and higher dice metric are achieved with the normalized cut segmentation method than with the fuzzy c-means clustering method.     

A region-based segmentation of tumour from brain CT images using nonlinear support vector machine classifier

The proposed system provides new textural information for segmenting tumours, efficiently and accurately and with less computational time, from benign and malignant tumour images, especially in smaller dimensions of tumour regions of computed tomography (CT) images. Region-based segmentation of tumour from brain CT image data is an important but time-consuming task performed manually by medical experts. The objective of this work is to segment brain tumour from CT images using combined grey and texture features with new edge features and nonlinear support vector machine (SVM) classifier. The selected optimal features are used to model and train the nonlinear SVM classifier to segment the tumour from computed tomography images and the segmentation accuracies are evaluated for each slice of the tumour image. The method is applied on real data of 80 benign, malignant tumour images. The results are compared with the radiologist labelled ground truth. Quantitative analysis between ground truth and the segmented tumour is presented in terms of segmentation accuracy and the overlap similarity measure dice metric. From the analysis and performance measures such as segmentation accuracy and dice metric, it is inferred that better segmentation accuracy and higher dice metric are achieved with the normalized cut segmentation method than with the fuzzy c-means clustering method.     

A Fast Region-Based Active Contour Model for Boundary Detection of Echocardiographic Images

This paper presents the boundary detection of atrium and ventricle in echocardiographic images. In case of mitral regurgitation, atrium and ventricle may get dilated. To examine this, doctors draw the boundary manually. Here the aim of this paper is to evolve the automatic boundary detection for carrying out segmentation of echocardiography images. Active contour method is selected for this purpose. There is an enhancement of Chan–Vese paper on active contours without edges. Our algorithm is based on Chan–Vese paper active contours without edges, but it is much faster than Chan–Vese model. Here we have developed a method by which it is possible to detect much faster the echocardiographic boundaries. The method is based on the region information of an image. The region-based force provides a global segmentation with variational flow robust to noise. Implementation is based on level set theory so it easy to deal with topological changes. In this paper, Newton–Raphson method is used which makes possible the fast boundary detection.     

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.     

启发式牙颌CT影像自动分割

准确快速地分割CT切片特征轮廓是医学图像三维重建的重要环节。现有的轮廓分割方法必须通过手动层层交互操作,不仅耗时而且分割精度不高。针对这种局限性,提出一种基于启发式牙颌CT影像自动分割方法。首先用拉普拉斯算子对CT图像序列进行边缘增强,其次用轮廓匹配映射技术实现轮廓启发式传递,最后基于收缩包围算法自动分割牙颌序列。以14例完整牙（每例28～32颗牙数据样本）锥束CT断层扫描图像序列进行实验,在相同条件下分别用所提出的轮廓自动提取方法和其他提取方法,对实验样本进行轮廓提取,得到单颗牙轮廓提取的平均用时和提取轮廓与真实轮廓之间的距离差平均值。实验结果显示,轮廓自动分割算法提取单颗牙轮廓的用时约为其他手工分割法提取单颗牙轮廓用时的23%,同时提取的轮廓质量和用传统方法提取的轮廓质量相当。该方法为CT数据特征区自动化分割提供一种可行且高效的方法,为进一步改进现有的CT影像分割和三维重建算法提供了新的思路。     

Adaptive Segmentation of Vertebral Bodies from Sagittal MR Images Based on Local Spatial Information and Gaussian Weighted Chi-Square Distance

We present a novel method for the automatic segmentation of the vertebral bodies from 2D sagittal magnetic resonance (MR) images of the spine. First, a new affinity matrix is constructed by incorporating neighboring information, which local intensity is considered to depict the image and overcome the noise effectively. Second, the Gaussian kernel function is to weight chi-square distance based on the neighboring information, which the vital spatial structure of the image is introduced to improve the accuracy of the segmentation task. Third, an adaptive local scaling parameter is utilized to facilitate the image segmentation and avoid the optimal configuration of controlling parameter manually. The encouraging results on the spinal MR images demonstrate the advantage of the proposed method over other methods in terms of both efficiency and robustness.     

Metastatic liver tumour segmentation with a neural network-guided 3D deformable model

The segmentation of liver tumours in CT images is useful for the diagnosis and treatment of liver cancer. Furthermore, an accurate assessment of tumour volume aids in the diagnosis and evaluation of treatment response. Currently, segmentation is performed manually by an expert, and because of the time required, a rough estimate of tumour volume is often done instead. We propose a semi-automatic segmentation method that makes use of machine learning within a deformable surface model. Specifically, we propose a deformable model that uses a voxel classifier based on a multilayer perceptron (MLP) to interpret the CT image. The new deformable model considers vertex displacement towards apparent tumour boundaries and regularization that promotes surface smoothness. During operation, a user identifies the target tumour and the mesh then automatically delineates the tumour from the MLP processed image. The method was tested on a dataset of 40 abdominal CT scans with a total of 95 colorectal metastases collected from a variety of scanners with variable spatial resolution. The segmentation results are encouraging with a Dice similarity metric of \(0.80 \pm 0.11\) and demonstrates that the proposed method can deal with highly variable data. This work motivates further research into tumour segmentation using machine learning with more data and deeper neural networks.     

超声图像血管分割的研究进展

主要阐述超声图像血管分割算法及其评价指标。基于特征提取的经典图像处理算法不能摆脱对人工的依赖,削弱了分割算法的泛化能力;但对于缺乏大样本超声血管图像的研究场景下,充分利用传统且成熟的技术方法却是一种可行的研究办法。基于机器学习的算法提高了分割算法的泛化能力,改善了传统方法的短板;但深度学习技术对数据的依赖性强、可解释性差,其算法的有效性、稳定性还需深入研究。血管分割评价算法的研究极其重要,研究适合超声图像血管分割的客观评价方法也是重要课题之一。总之,传统方法仍然是解决超声图像血管分割的有效方法,传统方法与深度学习技术的紧密结合是未来的发展趋势。     

2D to 3D fusion of echocardiography and cardiac CT for TAVR and TAVI image guidance

This study proposed a registration framework to fuse 2D echocardiography images of the aortic valve with preoperative cardiac CT volume. The registration facilitates the fusion of CT and echocardiography to aid the diagnosis of aortic valve diseases and provide surgical guidance during transcatheter aortic valve replacement and implantation. The image registration framework consists of two major steps: temporal synchronization and spatial registration. Temporal synchronization allows time stamping of echocardiography time series data to identify frames that are at similar cardiac phase as the CT volume. Spatial registration is an intensity-based normalized mutual information method applied with pattern search optimization algorithm to produce an interpolated cardiac CT image that matches the echocardiography image. Our proposed registration method has been applied on the short-axis “Mercedes Benz” sign view of the aortic valve and long-axis parasternal view of echocardiography images from ten patients. The accuracy of our fully automated registration method was 0.81 ± 0.08 and 1.30 ± 0.13 mm in terms of Dice coefficient and Hausdorff distance for short-axis aortic valve view registration, whereas for long-axis parasternal view registration it was 0.79 ± 0.02 and 1.19 ± 0.11 mm, respectively. This accuracy is comparable to gold standard manual registration by expert. There was no significant difference in aortic annulus diameter measurement between the automatically and manually registered CT images. Without the use of optical tracking, we have shown the applicability of this technique for effective fusion of echocardiography with preoperative CT volume to potentially facilitate catheter-based surgery.     

Simulating Developmental Cardiac Morphology in Virtual Reality Using a Deformable Image Registration Approach

While virtual reality (VR) has potential in enhancing cardiovascular diagnosis and treatment, prerequisite labor-intensive image segmentation remains an obstacle for seamlessly simulating 4-dimensional (4-D, 3-D?+?time) imaging data in an immersive, physiological VR environment. We applied deformable image registration (DIR) in conjunction with 3-D reconstruction and VR implementation to recapitulate developmental cardiac contractile function from light-sheet fluorescence microscopy (LSFM). This method addressed inconsistencies that would arise from independent segmentations of time-dependent data, thereby enabling the creation of a VR environment that fluently simulates cardiac morphological changes. By analyzing myocardial deformation at high spatiotemporal resolution, we interfaced quantitative computations with 4-D VR. We demonstrated that our LSFM-captured images, followed by DIR, yielded average dice similarity coefficients of 0.92?±?0.05 (n?=?510) and 0.93?±?0.06 (n?=?240) when compared to ground truth images obtained from Otsu thresholding and manual segmentation, respectively. The resulting VR environment simulates a wide-angle zoomed-in view of motion in live embryonic zebrafish hearts, in which the cardiac chambers are undergoing structural deformation throughout the cardiac cycle. Thus, this technique allows for an interactive micro-scale VR visualization of developmental cardiac morphology to enable high resolution simulation for both basic and clinical science.     

Three-dimensional echocardiography: assessment of inter- and intra-operator variability and accuracy in the measurement of left ventricular cavity volume and myocardial mass

Accurate left ventricular (LV) volume and mass estimation is a strong predictor of cardiovascular morbidity and mortality. We propose that our technique of 3D echocardiography provides an accurate quantification of LV volume and mass by the reconstruction of 2D images into 3D volumes, thus avoiding the need for geometric assumptions. We compared the accuracy and variability in LV volume and mass measurement using 3D echocardiography with 2D echocardiography, using in vitro studies. Six operators measured the LV volume and mass of seven porcine hearts, using both 3D and 2D techniques. Regression analysis was used to test the accuracy of results and an ANOVA test was used to compute variability in measurement. LV volume measurement accuracy was 9.8% (3D) and 18.4% (2D); LV mass measurement accuracy was 5% (3D) and 9.2% (2D). Variability in LV volume quantification with 3D echocardiography was %SEMinter = 13.5%, %SEMintra = 11.4%, and for 2D echocardiography was %SEMinter = 21.5%, %SEMintra = 19.1%. We derived an equation to predict uncertainty in measurement of LV volume and mass using 3D echocardiography, the results of which agreed with our experimental results to within 13%. 3D echocardiography provided twice the accuracy for LV volume and mass measurement and half the variability for LV volume measurement as compared with 2D echocardiography.     

Left-ventricle boundary detection from nuclear medicine images

We present here a new algorithm for segmentation of nuclear medicine images to detect the left-ventricle (LV) boundary. In this article, other image segmentation techniques, such as edge detection and region growing, are also compared and evaluated. In the edge detection approach, we explored the relationship between the LV boundary characteristics in nuclear medicine images and their radial orientations: we observed that no single brightness function (eg, maximum of first or second derivative) is sufficient to identify the boundary in every direction. In the region growing approach, several criteria, including intensity change, gradient magnitude change, gradient direction change, and running mean differences, were tested. We found that none of these criteria alone was sufficient to successfully detect the LV boundary. Then we proposed a simple but successful region growing method—Contour-Modified Region Growing (CMRG). CMRG is an easy-to-use, robust, and rapid image segmentation procedure. Based on our experiments, this method seems to perform quite well in comparison to other automated methods that we have tested because of its ability to handle the problems of both low signal-to-noise ratios (SNR) as well as low image contrast without any assumptions about the shape of the left ventricle.     

Automatic lung nodule matching on sequential CT images

We propose an automatic segmentation and registration method that provides more efficient and robust matching of lung nodules in sequential chest computed tomography (CT) images. Our method consists of four steps. First, the lungs are extracted from chest CT images by the automatic segmentation method. Second, gross translational mismatch is corrected by optimal cube registration. This initial alignment does not require extracting any anatomical landmarks. Third, the initial alignment is step-by-step refined by hierarchical surface registration. To evaluate the distance measures between lung boundary points, a three-dimensional distance map is generated by narrow-band distance propagation, which drives fast and robust convergence to the optimal value. Finally, correspondences of manually detected nodules are established from the pairs with the smallest Euclidean distances. Experimental results show that our segmentation method accurately extracts lung boundaries and the registration method effectively finds the nodule correspondences.     

基于CT数据的股骨轴线的获取

目的　提出一种利用CT影像数据自动获取股骨轴线的方法,利用该方法可以在计算机上获取精准的股骨三维解剖轴线与机械轴线。方法　对人体下肢进行CT扫描,然后对CT图像进行二维阈值分割、三维数据体重建、骨骼分组、数据平滑填充及三维数据体旋转等预处理,获得三维股骨表面模型;通过对股骨头与股骨远端形态特征的分析,根据股骨头近似球形的特点,对判断断层扫描数据梯度变化来计算股骨头中心位置,另外,逐层搜索膝关节断层图像上闭环区域的方法自动求得股骨远端中心的坐标,从而获得股骨长轴。结果　建立了一种基于CT图像简便快捷的自动获取股骨头中心与膝关节骨中心三维空间坐标的方法。结论　通过此方法可较为精确获得人体下肢的三维股骨机械轴线和股骨解剖轴线。     

基于改进图割的超声瞳孔图像分割与直径测量

传统的瞳孔直径测量是通过医生手工标定,对于眼外伤和丧失意识的患者测量不方便。针对瞳孔直径测量的人工交互量大且测量鲁棒性不强的问题,采用图割算法分割瞳孔超声图像并测量瞳孔直径。对传统图割算法进行两个方面的改进,采用自适应阈值的区域生长代替人为种子点选取,在保证分割效果的基础上减少了图割的交互量;在能量函数的数据项部分增加图像的梯度信息,减少了原始算法分割结果中出现的小区域,增强了对弱边缘的分割。最后,对采集到的超声瞳孔图像进行自动分割、自动测量瞳孔直径,可以得到患者瞳孔的直径动态变化,给临床诊断提供依据。为了验证算法的有效性,对10位患者的动态瞳孔超声图像进行基于改进图割的瞳孔直径测量,并与医生的手动测量结果对比。结果表明,本方法的结果与医生手动测量结果的绝对误差小于0.2 mm,相关系数不小于0.83。通过改进图割算法,改善了分割效果,实现了超声瞳孔动态图像的自动直径测量,并可有效代替瞳孔直径的人工测量,减少人工交互量。     

U-Net改进及其在新冠肺炎图像分割的应用

CT成像已成为检测新型冠状病毒肺炎（COVID-19）最重要的步骤之一。针对手动分割患者胸部CT图像中毛玻璃混浊区域繁琐的问题提出了一种自注意力循环残差U型网络模型来实现COVID-19患者肺部CT图像的自动分割,辅助医生诊断。在U-Net模型的基础上引入了循环残差模块和自注意力机制来加强对特征信息的抓取从而提升分割精度。在公开数据集上的分割实验结果显示,该算法的Dice系数、敏感度和特异度分别达到了85.36%、76.64%和76.25%,与其他算法相比具有良好的分割效果。     

Ventricular shape visualization using selective volume rendering of cardiac datasets

In this paper, we present a novel technique of improving volume rendering quality and speed by integrating original volume data and global model information attained by segmentation. The segmentation information prevents object occlusions that may appear when volume rendering is based on local image features only. Thus the presented visualization technique provides meaningful visual results that enable a clear understanding of complex anatomical structures. In the first part, we describe a segmentation technique for extracting the region of interest based on an active contour model. In the second part, we propose a volume rendering method for visualizing the selected portions of fuzzy surfaces extracted by local image processing methods. We show the results of selective volume rendering of left and right ventricle based on cardiac datasets from clinical routines. Our method offers an accelerated technique to accurately visualize the surfaces of segmented objects.     

Automatic segmentation of left ventricle cavity from short-axis cardiac magnetic resonance images

In this paper, a computational framework is proposed to perform a fully automatic segmentation of the left ventricle (LV) cavity from short-axis cardiac magnetic resonance (CMR) images. In the initial phase, the region of interest (ROI) is automatically identified on the first image frame of the CMR slices. This is done by partitioning the image into different regions using a standard fuzzy c-means (FCM) clustering algorithm where the LV region is identified according to its intensity, size and circularity in the image. Next, LV segmentation is performed within the identified ROI by using a novel clustering method that utilizes an objective functional with a dissimilarity measure that incorporates a circular shape function. This circular shape-constrained FCM algorithm is able to differentiate pixels with similar intensity but are located in different regions (e.g. LV cavity and non-LV cavity), thus improving the accuracy of the segmentation even in the presence of papillary muscles. In the final step, the segmented LV cavity is propagated to the adjacent image frame to act as the ROI. The segmentation and ROI propagation are then iteratively executed until the segmentation has been performed for the whole cardiac sequence. Experiment results using the LV Segmentation Challenge validation datasets show that our proposed framework can achieve an average perpendicular distance (APD) shift of 2.23 ± 0.50 mm and the Dice metric (DM) index of 0.89 ± 0.03, which is comparable to the existing cutting edge methods. The added advantage over state of the art is that our approach is fully automatic, does not need manual initialization and does not require a prior trained model.