Reduced field-of-view DTI segmentation of cervical spine tissue

The number of diffusion tensor imaging (DTI) studies regarding the human spine has considerably increased and it is challenging because of the spine’s small size and artifacts associated with the most commonly used clinical imaging method. A novel segmentation method based on the reduced field-of-view (rFOV) DTI dataset is presented in cervical spinal canal cerebrospinal fluid, spinal cord grey matter and white matter classification in both healthy volunteers and patients with neuromyelitis optica (NMO) and multiple sclerosis (MS). Due to each channel based on high resolution rFOV DTI images providing complementary information on spinal tissue segmentation, we want to choose a different contribution map from multiple channel images. Via principal component analysis (PCA) and a hybrid diffusion filter with a continuous switch applied on fourteen channel features, eigen maps can be obtained and used for tissue segmentation based on the Bayesian discrimination method. Relative to segmentation by a pair of expert readers, all of the automated segmentation results in the experiment fall in the good segmentation area and performed well, giving an average segmentation accuracy of about 0.852 for cervical spinal cord grey matter in terms of volume overlap. Furthermore, this has important applications in defining more accurate human spinal cord tissue maps when fusing structural data with diffusion data. rFOV DTI and the proposed automatic segmentation outperform traditional manual segmentation methods in classifying MR cervical spinal images and might be potentially helpful for detecting cervical spine diseases in NMO and MS.     

Magnetic Resonance Imaging Segmentation via Weighted Level Set Model Based on Local Kernel Metric and Spatial Constraint

Magnetic resonance imaging (MRI) segmentation is a fundamental and significant task since it can guide subsequent clinic diagnosis and treatment. However, images are often corrupted by defects such as low-contrast, noise, intensity inhomogeneity, and so on. Therefore, a weighted level set model (WLSM) is proposed in this study to segment inhomogeneous intensity MRI destroyed by noise and weak boundaries. First, in order to segment the intertwined regions of brain tissue accurately, a weighted neighborhood information measure scheme based on local multi information and kernel function is designed. Then, the membership function of fuzzy c-means clustering is used as the spatial constraint of level set model to overcome the sensitivity of level set to initialization, and the evolution of level set function can be adaptively changed according to different tissue information. Finally, the distance regularization term in level set function is replaced by a double potential function to ensure the stability of the energy function in the evolution process. Both real and synthetic MRI images can show the effectiveness and performance of WLSM. In addition, compared with several state-of-the-art models, segmentation accuracy and Jaccard similarity coefficient obtained by WLSM are increased by 0.0586, 0.0362 and 0.1087, 0.0703, respectively.     

Unbiased segmentation of diffusion-weighted magnetic resonance images of the brain using iterative clustering

Segmentation of diffusion-weighted echo-planar imaging (DW-EPI) is challenging because of concerns regarding spatial resolution and distortion. Methods commonly used require manual input and often need thresholding measures to segment white matter (WM), gray matter (GM) and cerebrospinal fluid (CSF). This may introduce operator bias and misclassification error. When comparing patients with a diffuse disease process-such as multiple sclerosis (MS)--with healthy controls, although information from all images may be biased due to disease effect, this is more so if the data set employed to perform segmentation is also used as a measured outcome for the study, for example, fractional anisotropy maps. Presented in this work is an unbiased method for segmenting DW-EPI data sets using the b=0 and single-shot inversion recovery EPI into WM, GM and CSF. The method employs an iterative clustering technique to account for partial volume effects and signal variation caused by radiofrequency inhomogeneity. The technique is evaluated with both real and synthetic brain data and results compared with statistical parametric mapping (SPM02). With synthetic brain data, where a gold standard of segmentation exists, the presented method showed less misclassification compared to SPM02. The unbiased method proposed may provide a more accurate methodology of segmentation in the analysis of DWI-EPI images in conditions such as MS.     

Segmentation techniques for tissue differentiation in MRI of ophthalmology using fuzzy clustering algorithms

This paper presents MRI segmentation techniques to differentiate abnormal and normal tissues in Ophthalmology using fuzzy clustering algorithms. Applying the best-known fuzzy c-means (FCM) clustering algorithm, a newly proposed algorithm, called an alternative fuzzy c-mean (AFCM), was used for MRI segmentation in Ophthalmology. These unsupervised segmentation algorithms can help Ophthalmologists to reduce the medical imaging noise effects originating from low resolution sensors and/or the structures that move during the data acquisition. They may be particularly helpful in the clinical oncological field as an aid to the diagnosis of Retinoblastoma, an inborn oncological disease in which symptoms usually show in early childhood. For the purpose of early treatment with radiotherapy and surgery, the newly proposed AFCM is preferred to provide more information for medical images used by Ophthalmologists. Comparisons between FCM and AFCM segmentations are made. Both fuzzy clustering segmentation techniques provide useful information and good results. However, the AFCM method has better detection of abnormal tissues than FCM according to a window selection. Overall, the newly proposed AFCM segmentation technique is recommended in MRI segmentation.     

An anisotropic images segmentation and bias correction method

Intensity inhomogeneities cause considerable difficulty in the quantitative analysis of magnetic resonance (MR) images. Thus, bias field correction is a necessary step before quantitative analysis of MR data can be undertaken. This paper presents an anisotropic approach to bias correction and segmentation for images with intensity inhomogeneities and noise. Intensity-based methods are usually applied to estimate the bias field; however, most of them only concern the intensity information. When the images have noise or slender topological objects, these methods cannot obtain accurate results or bias fields. We use structure information to construct an anisotropic Gibbs field and combine the anisotropic Gibbs field with the Bayesian framework to segment images while estimating the bias fields. Our method is able to capture bias of quite general profiles. Moreover, it is robust to noise and slender topological objects. The proposed method has been used for images of various modalities with promising results.     

A Texture Combined Multispectral Magnetic Resonance Imaging Segmentation for Nasopharyngeal Carcinoma

Tumor segmentation from magnetic resonance imaging (MRI) is important for volume estimation and visualization of nasopharyngeal carcinoma (NPC). In some cases, segmentation using the general multispectral (GM) method often obtained poor results due to the high false positives caused by complex anatomic structures and serious overlap in feature space. In this study, a texture combined multispectral fuzzy clustering (TCMFC) segmentation algorithm was proposed. A texture measure of T1-weighted (T1) MR image was introduced by calculating the two-order central statistical information of every pixel within a window after the window convolution operation. The texture measure and the intensities in T1 and contrast-enhanced T1 images formed the new 3-D feature vector for fuzzy clustering implemented by semi-supervised fuzzy c-means (SFCM). Testing showed that by reducing the false positives significantly, the TCMFC method achieved improved segmentation results, compared with the GM method.     

Keyhole and zero-padding approaches for reduced-encoding diffusion tensor imaging of the mouse brains

Keyhole diffusion tensor imaging (keyhole DTI) was previously proposed in cardiac imaging to reconstruct DTI maps from the reduced phase-encoding images. To evaluate the feasibility of keyhole DTI in brain imaging, keyhole and zero-padding DTI algorithms were employed on in vivo mouse brain. The reduced phase-encoding portion, also termed as the sharing rate, was varied from 50% to 90% of the full k-space. Our data showed that zero-padding DTI resulted in decreased fractional anisotropy (FA) and decreased mean apparent diffusion coefficient (mean ADC) in white matter (WM) regions. Keyhole DTI showed a better edge preservation on mean ADC maps but not on FA maps as compared to the zero-padding DTI. When increasing the sharing rate in keyhole approach, an underestimation of FA and an over- or underestimation of mean ADC were measured in WM depending on the selected reference image. The inconsistency of keyhole DTI may add a challenge for the wide use of this modality. However, with a carefully selected directive diffusion-weighted image to serve as the reference image in the keyhole approach, this study demonstrated that one may obtain DTI indices of reduced-encoding images with high consistency to those derived with full k-space DTI.     

通道注意网络和模糊划分熵图割的图像去雾

针对雾图成像时变化的场景光及去雾过程中不同雾相关信息在处理上的差异性,提出了通道注意网络和模糊划分熵图割的单幅图像去雾算法。以考虑变化场景光的大气散射物理成像模型为基础,首先使用通道注意的编码解码网络来估计透射率,并在编码器最后及解码器起始处添加通道注意模块,以便为编码器提取的不同雾相关特征图分配不同的权重,准确地计算透射率;然后利用所提出的模糊划分熵图割算法将透射率划分为不同场景光覆盖下的近景、中景、远景,此分割策略将考虑空间相关性的图割算法与模糊划分熵的阈值分割算法相结合,解决了单一阈值分割算法产生的区域误分问题;最后估计场景光和大气光,得到去雾图像。实验结果表明,算法在合成雾图及真实雾图上均有较好的去雾效果。与已有的去雾算法相比,本文算法在峰值信噪比及结构相似性上均有提升,单张图像的平均处理时间为3.9 s。     

Optimization of tissue segmentation of brain MR images based on multispectral 3D feature maps

The purpose of this work was to optimize and increase the accuracy of tissue segmentation of the brain magnetic resonance (MR) images based on multispectral 3D feature maps. We used three sets of MR images as input to the in-house developed semi-automated 3D tissue segmentation algorithm: proton density (PD) and T2-weighted fast spin echo and, T1-weighted spin echo. First, to eliminate the random noise, non-linear anisotropic diffusion type filtering was applied to all the images. Second, to reduce the nonuniformity of the images, we devised and applied a correction algorithm based on uniform phantoms. Following these steps, the qualified observer "seeded" (identified training points) the tissue of interest. To reduce the operator dependent errors, cluster optimization was also used; this clustering algorithm identifies the densest clusters pertaining to the tissues. Finally, the images were segmented using k-NN (k-Nearest Neighborhood) algorithm and a stack of color-coded segmented images were created along with the connectivity algorithm to generate the entire surface of the brain. The application of pre-processing optimization steps substantially improved the 3D tissue segmentation methodology.     

Automatic segmentation for brain MR images via a convex optimized segmentation and bias field correction coupled model

Accurate segmentation of magnetic resonance (MR) images remains challenging mainly due to the intensity inhomogeneity, which is also commonly known as bias field. Recently active contour models with geometric information constraint have been applied, however, most of them deal with the bias field by using a necessary pre-processing step before segmentation of MR data. This paper presents a novel automatic variational method, which can segment brain MR images meanwhile correcting the bias field when segmenting images with high intensity inhomogeneities. We first define a function for clustering the image pixels in a smaller neighborhood. The cluster centers in this objective function have a multiplicative factor that estimates the bias within the neighborhood. In order to reduce the effect of the noise, the local intensity variations are described by the Gaussian distributions with different means and variances. Then, the objective functions are integrated over the entire domain. In order to obtain the global optimal and make the results independent of the initialization of the algorithm, we reconstructed the energy function to be convex and calculated it by using the Split Bregman theory. A salient advantage of our method is that its result is independent of initialization, which allows robust and fully automated application. Our method is able to estimate the bias of quite general profiles, even in 7T MR images. Moreover, our model can also distinguish regions with similar intensity distribution with different variances. The proposed method has been rigorously validated with images acquired on variety of imaging modalities with promising results.     

A study of rotationally invariant and symmetric indices of diffusion anisotropy.

This study investigated the properties of a class of rotationally invariant and symmetric (relative to the principal diffusivities) indices of the anisotropy of water self-diffusion, namely fractional anisotropy (FA), relative anisotropy (RA), and volume ratio (VR), with particular emphasis to their measurement in brain tissues. A simplified theoretical analysis predicted significant differences in the sensitivities of the anisotropy indices (AI) over the distribution of the principal diffusivities. Computer simulations were used to investigate the effects on AI image quality of three magnetic resonance (MR) diffusion tensor imaging (DTI) acquisition schemes, one being novel: the schemes were simulated on cerebral model fibres varying in shape and spatial orientation. The theoretical predictions and the results of the simulations were corroborated by experimentally determined spatial maps of the AI in a normal feline brain in vivo. We found that FA mapped diffusion anisotropy with the greatest detail and SNR whereas VR provided the strongest contrast between low- and high-anisotropy areas at the expense of increased noise contamination and decreased resolution in anisotropic regions. RA proved intermediate in quality. By sampling the space of the effective diffusion ellipsoid more densely and uniformly and requiring the same total imaging time as the published schemes, the novel DTI scheme achieved greater rotational invariance than the published schemes, with improved noise characteristics, resulting in improved image quality of the AI examined. Our findings suggest that significant improvements in diffusion anisotropy mapping are possible and provide criteria for the selection of the most appropriate AI for a particular application.     

基于伪魏格纳分布分解的合成孔径雷达图像目标与阴影分割

在二维魏格纳分布的框架内,针对魏格纳变换的交叉项问题和计算量大的问题,提出了合成孔径雷达图像局部伪魏格纳变换的目标和目标阴影的分割方法.首先,将合成孔径雷达图像进行二维伪魏格纳变换,得到各像素点的二维能量谱图|然后提取各像素点的二维能量谱图对应位置值形成多个不同频段的与原图像同大小的能量谱图|最后,对不同频段的能量谱图采用不同的处理方法后,将各能量谱图相加处理后形成区域标识图像,最终得到原图像的目标和目标阴影分割图像.本文利用该方法对MSTAR切片图像进行了分割试验,并对分割图像与频谱最大值距离或方位分割算法和基于双参量CFAR与隐马尔科夫联合分割算法进行了分割图像对比度对比.实验结果表明,采用本文算法的合成孔径雷达分割图像,对比度明显提高,且保留了目标图像细节.     

Non-locally regularized segmentation of multiple sclerosis lesion from multi-channel MRI data

Segmentation of multiple sclerosis (MS) lesion is important for many neuroimaging studies. In this paper, we propose a novel algorithm for automatic segmentation of MS lesions from multi-channel MR images (T1W, T2W and FLAIR images). The proposed method is an extension of Li et al.'s algorithm in [1], which only segments the normal tissues from T1W images. The proposed method is aimed to segment MS lesions, while normal tissues are also segmented and bias field is estimated to handle intensity inhomogeneities in the images. Another contribution of this paper is the introduction of a nonlocal means technique to achieve spatially regularized segmentation, which overcomes the influence of noise. Experimental results have demonstrated the effectiveness and advantages of the proposed algorithm.     

A practical approach to in vivo high-resolution diffusion tensor imaging of rhesus monkeys on a 3-T human scanner

The nonhuman primate brain study provides important supplemental means for human brain exploration since the two species share close anatomical and functional similarities. MR diffusion tensor imaging (DTI) in human brain has revealed exquisite details of brain structures especially in the brain white matter. However, most previous monkey brain DTI results lack the spatial resolution in comparison to the conventional tracing and postmortem imaging methods, especially when it is acquired in commonly available human MRI scanners of field strength of 3 T or lower. To meet the increasing demands for nonhuman primate DTI studies, we proposed an in vivo high-resolution monkey DTI acquisition protocol that is practically feasible and combined it with an improved postprocessing procedure for a 3-T human scanner. The acquisition protocol, susceptibility distortion correction method with phase reversal acquisition, and postprocessing steps were proved to be effective in our study of rhesus monkeys. Results from diffusion tensor estimations and fiber tractography at 1 x 1 x 1 mm(3) resolution were found to be comparable to previous ex vivo DTI studies with much longer acquisition times. Effects of image resolution were evaluated and it was confirmed that the partial volume effect due to the larger voxel size in low-resolution data biased the diffusion tensor estimation and produced erroneous fiber tractography. Our results suggest that in vivo high-resolution monkey brain DTI can be achieved within practical time, which allows accurate diffusion tensor estimation and fiber tractography in monkey brains, so that the complex anatomical structures within many small but important anatomic structures can be delineated.     

Quantitative ultrasound brain imaging with multiscale deconvolutional waveform inversion

High-resolution images of human brain are critical for monitoring the neurological conditions in a portable and safe manner. Sound speed mapping of brain tissues provides unique information for such a purpose. In addition, it is particularly important for building digital human acoustic models, which form a reference for future ultrasound research. Conventional ultrasound modalities can hardly image the human brain at high spatial resolution inside the skull due to the strong impedance contrast between hard tissue and soft tissue. We carry out numerical experiments to demonstrate that the time-domain waveform inversion technique, originating from the geophysics community, is promising to deliver quantitative images of human brains within the skull at a sub-millimeter level by using ultra-sound signals. The successful implementation of such an approach to brain imaging requires the following items: signals of sub-megahertz frequencies transmitting across the inside of skull, an accurate numerical wave equation solver simulating the wave propagation, and well-designed inversion schemes to reconstruct the physical parameters of targeted model based on the optimization theory. Here we propose an innovative modality of multiscale deconvolutional waveform inversion that improves ultrasound imaging resolution, by evaluating the similarity between synthetic data and observed data through using limited length Wiener filter. We implement the proposed approach to iteratively update the parametric models of the human brain. The quantitative imaging method paves the way for building the accurate acoustic brain model to diagnose associated diseases, in a potentially more portable, more dynamic and safer way than magnetic resonance imaging and x-ray computed tomography.     

Correction of B0 susceptibility induced distortion in diffusion-weighted images using large-deformation diffeomorphic metric mapping

Geometric distortion caused by B0 inhomogeneity is one of the most important problems for diffusion-weighted images (DWI) using single-shot, echo planar imaging (SS-EPI). In this study, large-deformation, diffeomorphic metric mapping (LDDMM) algorithm has been tested for the correction of geometric distortion in diffusion tensor images (DTI). Based on data from nine normal subjects, the amount of distortion caused by B0 susceptibility in the 3-T magnet was characterized. The distortion quality was validated by manually placing landmarks in the target and DTI images before and after distortion correction. The distortion was found to be up to 15 mm in the population-averaged map and could be more than 20 mm in individual images. Both qualitative demonstration and quantitative statistical results suggest that the highly elastic geometric distortion caused by spatial inhomogeneity of the B0 field in DTI using SS-EPI can be effectively corrected by LDDMM. This postprocessing method is especially useful for correcting existent DTI data without phase maps.     

An image-processing toolset for diffusion tensor tractography

Diffusion tensor imaging (DTI)-based fiber tractography holds great promise in delineating neuronal fiber tracts and, hence, providing connectivity maps of the neural networks in the human brain. An array of image-processing techniques has to be developed to turn DTI tractography into a practically useful tool. To this end, we have developed a suite of image-processing tools for fiber tractography with improved reliability. This article summarizes the main technical developments we have made to date, which include anisotropic smoothing, anisotropic interpolation, Bayesian fiber tracking and automatic fiber bundling. A primary focus of these techniques is the robustness to noise and partial volume averaging, the two major hurdles to reliable fiber tractography. Performance of these techniques has been comprehensively examined with simulated and in vivo DTI data, demonstrating improvements in the robustness and reliability of DTI tractography.     

Deep unregistered multi-contrast MRI reconstruction

Multiple magnetic resonance images of different contrasts are normally acquired for clinical diagnosis. Recently, research has shown that the previously acquired multi-contrast (MC) images of the same patient can be used as anatomical prior to accelerating magnetic resonance imaging (MRI). However, current MC-MRI networks are based on the assumption that the images are perfectly registered, which is rarely the case in real-world applications. In this paper, we propose an end-to-end deep neural network to reconstruct highly accelerated images by exploiting the shareable information from potentially misaligned reference images of an arbitrary contrast. Specifically, a spatial transformation (ST) module is designed and integrated into the reconstruction network to align the pre-acquired reference images with the images to be reconstructed. The misalignment is further alleviated by maximizing the normalized cross-correlation (NCC) between the MC images. The visualization of feature maps demonstrates that the proposed method effectively reduces the misalignment between the images for shareable information extraction when applied to the publicly available brain datasets. Additionally, the experimental results on these datasets show the proposed network allows the robust exploitation of shareable information across the misaligned MC images, leading to improved reconstruction results.     

Segmentation of the brain using direction-averaged signal of DWI images

Segmentation of brain tissue in diffusion MRI image space has some unique advantages. A novel segmentation method using the direction-averaged diffusion weighted imaging (DWI) signal is proposed. Two images can be obtained from the fitting of the direction-averaged DWI signal as a function of b-value: one with superior contrast between the gray matter and white matter; one with prominent CSF contrast. A pseudo T1 weighted image can be constructed and standard segmentation tools can be applied. The method was tested on the HCP dataset using SPM12, and showed good agreement with segmentation using the T1 weighted image with the same resolution. The Dice score was all greater than 0.88 for GM or WM with full DWI data and very stable against subsampling of the DWI data in number of diffusion directions, number of shells, and spatial resolution.     

Voxel-based morphometry with templates and validation in a mouse model of Huntington’s disease

Despite widespread application to human imaging, voxel-based morphometry (VBM), where images are compared following grey matter (GM) segmentation, is seldom used in mice. Here VBM is performed for the R6/2 model of Huntington’s disease, a progressive neurological disorder. This article discusses issues in translating the methods to mice and shows that its statistical basis is sound in mice as it is in human studies. Whole brain images from live transgenic and control mice are segmented into GM maps after processing and compared to produce statistical parametric maps of likely differences. To assess whether false positives were likely to occur, a large cohort of ex vivo magnetic resonance brain images were sampled with permutation testing. Differences were seen particularly in the striatum and cortex, in line with studies performed ex vivo and as seen in human patients. In validation, the rate of false positives is as expected and these have no discernible distribution through the brain. The study shows that VBM successfully detects differences in the Huntington’s disease mouse brain. The method is rapid compared to manual delineation and reliable. The templates created here for the mouse brain are freely released for other users in addition to an open-source software toolbox for performing mouse VBM.