Representing diffusion MRI in 5-D simplifies regularization and segmentation of white matter tracts

We present a new five-dimensional (5-D) space representation of diffusion magnetic resonance imaging (dMRI) of high angular resolution. This 5-D space is basically a non-Euclidean space of position and orientation in which crossing fiber tracts can be clearly disentangled, that cannot be separated in three-dimensional position space. This new representation provides many possibilities for processing and analysis since classical methods for scalar images can be extended to higher dimensions even if the spaces are not Euclidean. In this paper, we show examples of how regularization and segmentation of dMRI is simplified with this new representation. The regularization is used with the purpose of denoising and but also to facilitate the segmentation task by using several scales, each scale representing a different level of resolution. We implement in five dimensions the Chan-Vese method combined with active contours without edges for the segmentation and the total variation functional for the regularization. The purpose of this paper is to explore the possibility of segmenting white matter structures directly as entirely separated bundles in this 5-D space. We will present results from a synthetic model and results on real data of a human brain acquired with diffusion spectrum magnetic resonance imaging (MRI), one of the dMRI of high angular resolution available. These results will lead us to the conclusion that this new high-dimensional representation indeed simplifies the problem of segmentation and regularization.     

Automatic tractography segmentation using a high-dimensional white matter atlas

We propose a new white matter atlas creation method that learns a model of the common white matter structures present in a group of subjects. We demonstrate that our atlas creation method, which is based on group spectral clustering of tractography, discovers structures corresponding to expected white matter anatomy such as the corpus callosum, uncinate fasciculus, cingulum bundles, arcuate fasciculus, and corona radiata. The white matter clusters are augmented with expert anatomical labels and stored in a new type of atlas that we call a high-dimensional white matter atlas. We then show how to perform automatic segmentation of tractography from novel subjects by extending the spectral clustering solution, stored in the atlas, using the Nystrom method. We present results regarding the stability of our method and parameter choices. Finally we give results from an atlas creation and automatic segmentation experiment. We demonstrate that our automatic tractography segmentation identifies corresponding white matter regions across hemispheres and across subjects, enabling group comparison of white matter anatomy.     

A probabilistic model-based approach to consistent white matter tract segmentation

Since the invention of diffusion magnetic resonance imaging (dMRI), currently the only established method for studying white matter connectivity in a clinical environment, there has been a great deal of interest in the effects of various pathologies on the connectivity of the brain. As methods for in vivo tractography have been developed, it has become possible to track and segment specific white matter structures of interest for particular study. However, the consistency and reproducibility of tractography-based segmentation remain limited, and attempts to improve them have thus far typically involved the imposition of strong constraints on the tract reconstruction process itself. In this work we take a different approach, developing a formal probabilistic model for the relationships between comparable tracts in different scans, and then using it to choose a tract, a posteriori, which best matches a predefined reference tract for the structure of interest. We demonstrate that this method is able to significantly improve segmentation consistency without directly constraining the tractography algorithm.     

A new method to derive white matter conductivity from diffusion tensor MRI

We propose a new algorithm to derive the anisotropic conductivity of the cerebral white matter (WM) from the diffusion tensor MRI (DT-MRI) data. The transportation processes for both water molecules and electrical charges are described through a common multicompartment model that consists of axons, glia, or the cerebrospinal fluid (CSF). The volume fraction (VF) of each compartment varies from voxel to voxel and is estimated from the measured diffusion tensor. The conductivity tensor at each voxel is then computed from the estimated VF values and the decomposed eigenvectors of the diffusion tensor. The proposed VF algorithm was applied to the DT-MRI data acquired from two healthy human subjects. The extracted anisotropic conductivity distribution was compared with those obtained by using two existing algorithms, which were based upon a linear conductivity-to-diffusivity relationship and a volume constraint, respectively. The present results suggest that the VF algorithm is capable of incorporating the partial volume effects of the CSF and the intravoxel fiber crossing structure, both of which are not addressed altogether by existing algorithms. Therefore, it holds potential to provide a more accurate estimate of the WM anisotropic conductivity, and may have important applications to neuroscience research or clinical applications in neurology and neurophysiology.      

Texture anisotropy of the brain's white matter as revealed by anatomical MRI

The purpose of this work was to study specific texture properties of the brain's white matter (WM) based on conventional high-resolution T1-weighted magnetic resonance imaging (MRI) datasets. Quantitative parameters anisotropy and laminarity were derived from 3-D texture analysis. Differences in WM texture associated with gender were evaluated on an age-matched sample of 210 young healthy subjects (mean age 24.8, SD 3.97 years, 103 males and 107 females). Changes of WM texture with age were studied using 112 MRI-T1 datasets of healthy subjects aged 16 to 70 years (57 males and 55 females). Both texture measures indicated a "more regular" WM structure in females (p < 10(-6)). An age-related deterioration of WM structure manifests itself as a remarkable decline of both parameters (p < 10(-6)) that is more prominent in females (p < 10(-6)) than in males (p = 0.02). Texture analysis of anatomical MRI-T1 brain datasets provides quantitative information about macroscopic WM characteristics and helps discriminating between normal and pathological aging.     

基于局部Walsh变换和非负矩阵分解的脑白质图像分割

脑白质病变诊断是医学研究和病理分析的重要方面。颅脑核磁共振图像的白质分割在诊断中起着非常重要的作用,其分割的准确性直接影响后续的分析和诊断研究。本文提出了一种基于局部Walsh变换和非负矩阵分解的大脑核磁共振图像白质分割算法。算法首先对颅脑图像进行局部Walsh变换,选择鉴别性能好的特征得到特征矩阵,然后对其进行非负矩阵分解并得到白质的分割结果。实验表明,本方法计算简单,精度比较高,可以得到比较理想的分割结果。     

Effect of image standardization on FLAIR MRI for brain extraction

Fluid attenuation inversion recovery (FLAIR) magnetic resonance images (MRI) are being used by physicians to identify and analyze white matter lesions in the brain to determine whether patients are at risk of stroke. Pipelines used to analyze these images require a preprocessing step of brain extraction in order to be robust and to be applied to multicenter, large-scale studies. This paper proposes a novel brain extraction tool solely for the FLAIR modality, as well as a robust standardization pipeline that eliminates variability between datasets by reducing image noise, intensity inhomogeneity, patient movement, and the nonstandardness of tissue intensities, which are inherent in MRI. Feature extraction is performed on the standardized dataset, and a brain segmentation is produced by a random forest classifier. The effects of the standardization steps are evaluated using objective metrics, and the resultant segmentations produced by the unstandardized and standardized images are compared. By implementing a robust standardization pipeline, images acquired from different scanners at different centers can be processed automatically and accurately, allowing for the fast processing of large-scale, multicenter data.     

Adaptive segmentation of MRI data

Intensity-based classification of MR images has proven problematic, even when advanced techniques are used. Intrascan and interscan intensity inhomogeneities are a common source of difficulty. While reported methods have had some success in correcting intrascan inhomogeneities, such methods require supervision for the individual scan. This paper describes a new method called adaptive segmentation that uses knowledge of tissue intensity properties and intensity inhomogeneities to correct and segment MR images. Use of the expectation-maximization (EM) algorithm leads to a method that allows for more accurate segmentation of tissue types as well as better visualization of magnetic resonance imaging (MRI) data, that has proven to be effective in a study that includes more than 1000 brain scans. Implementation and results are described for segmenting the brain in the following types of images: axial (dual-echo spin-echo), coronal [three dimensional Fourier transform (3-DFT) gradient-echo T1-weighted] all using a conventional head coil, and a sagittal section acquired using a surface coil. The accuracy of adaptive segmentation was found to be comparable with manual segmentation, and closer to manual segmentation than supervised multivariant classification while segmenting gray and white matter.     

Automated left ventricular segmentation in cardiac MRI

We present an automated left ventricular (LV) myocardial boundary extraction method. Automatic localization of the LV is achieved using a motion map and an expectation maximization algorithm. The myocardial region is then segmented using an intensity-based fuzzy affinity map and the myocardial contours are extracted by cost minimization through a dynamic programming approach. The results from the automated algorithm compared against the experienced radiologists using Bland and Altman analysis were found to have consistent mean bias of 7% and limits of agreement comparable to the inter-observer variability inherent in the manual method.     

Automated seeded lesion segmentation on digital mammograms

Segmenting lesions is a vital step in many computerized mass-detection schemes for digital (or digitized) mammograms. The authors have developed two novel lesion segmentation techniques-one based on a single feature called the radial gradient index (RGI) and one based on simple probabilistic models to segment mass lesions, or other similar nodular structures, from surrounding background. In both methods a series of image partitions is created using gray-level information as well as prior knowledge of the shape of typical mass lesions. With the former method the partition that maximizes the RGI is selected. In the latter method, probability distributions for gray-levels inside and outside the partitions are estimated, and subsequently used to determine the probability that the image occurred for each given partition. The partition that maximizes this probability is selected as the final lesion partition (contour). The authors tested these methods against a conventional region growing algorithm using a database of biopsy-proven, malignant lesions and found that the new lesion segmentation algorithms more closely match radiologists' outlines of these lesions. At an overlap threshold of 0.30, gray level region growing correctly delineates 62% of the lesions in the authors' database while the RGI and probabilistic segmentation algorithms correctly segment 92% and 96% of the lesions, respectively     

Fully automatic segmentation of the brain in MRI

A robust fully automatic method for segmenting the brain from head magnetic resonance (MR) images has been developed, which works even in the presence of radio frequency (RF) inhomogeneities. It has been successful in segmenting the brain in every slice from head images acquired from several different MRI scanners, using different-resolution images and different echo sequences. The method uses an integrated approach which employs image processing techniques based on anisotropic filters and “snakes” contouring techniques, and a priori knowledge, which is used to remove the eyes, which are tricky to remove based on image intensity alone. It is a multistage process, involving first removal of the background noise leaving a head mask, then finding a rough outline of the brain, then refinement of the rough brain outline to a final mask. The paper describes the main features of the method, and gives results for some brain studies     

Robust shape regression for supervised vessel segmentation and its application to coronary segmentation in CTA

This paper presents a vessel segmentation method which learns the geometry and appearance of vessels in medical images from annotated data and uses this knowledge to segment vessels in unseen images. Vessels are segmented in a coarse-to-fine fashion. First, the vessel boundaries are estimated with multivariate linear regression using image intensities sampled in a region of interest around an initialization curve. Subsequently, the position of the vessel boundary is refined with a robust nonlinear regression technique using intensity profiles sampled across the boundary of the rough segmentation and using information about plausible cross-sectional vessel shapes. The method was evaluated by quantitatively comparing segmentation results to manual annotations of 229 coronary arteries. On average the difference between the automatically obtained segmentations and manual contours was smaller than the inter-observer variability, which is an indicator that the method outperforms manual annotation. The method was also evaluated by using it for centerline refinement on 24 publicly available datasets of the Rotterdam Coronary Artery Evaluation Framework. Centerlines are extracted with an existing method and refined with the proposed method. This combination is currently ranked second out of 10 evaluated interactive centerline extraction methods. An additional qualitative expert evaluation in which 250 automatic segmentations were compared to manual segmentations showed that the automatically obtained contours were rated on average better than manual contours.     

DB-TASNet for disease diagnosis and lesion segmentation in medical images

Deep learning algorithms have been successfully used in the field of medical image analysis and have greatly improved application of intelligent algorithms to medical diagnosis. However, existing deep-learning-based diagnostic methods still suffer from several drawbacks: (1) In most medical image multi-tasking methods, focus segmentation and disease classification are often performed linearly, resulting in excessive reliance on the final results of focus segmentation. (2) The computational cost of the traditional attention mechanism for performing the segmentation task is very high and the convolutional architecture cannot be used to model long-distance dependencies, which in turn affects the segmentation accuracy. To address these issues, we propose a disease diagnosis and lesion segmentation model, Dual-Branch with Transformer Axial-attention Segmentation Net (DB-TASNet). DB-TASNet is built by the DenseNet-121 classification network and U-Net segmentation network improved using an axial-attention transformer model. Moreover, DB-TASNet also includes a lesion integration module to integrate segmentation results with the classification network in order to increase its attention to lesions and improve the diagnosis results. Experimental results on the Pneumothorax dataset provided by the Society for Imaging Informatics in Medicine (SIIM) show that the average AUC of the DB-TASNet classification task reaches 0.939, and the DICE coefficient of the segmentation task reaches 0.886. Such performance suggests that the proposed model may provide an efficient and effective diagnosis tool for medical personnel.     

基于改进U-Net的SPECT骨显像病灶分割研究北大核心CSCD

在核医学中,单光子发射计算机断层(single-photon emission computed tomograpy,SPECT)骨显像是辅助医师诊断癌症的重要手段。针对骨显像图像信噪比低、边界模糊、病灶小难以提取和人工勾画病灶耗时等问题,提出一种基于改进U-Net网络的骨显像病灶自动分割算法。该算法在U-Net的原卷积块基础上,采用了多尺度密集连接(multi-scale dense connection,MDC)的方式来提高对小病灶特征的提取能力,同时解决了网络加深后出现的梯度消失问题。其次,为提取病灶的细节特征,在密集连接和跳跃连接处引入了注意力机制结构。最后,针对使用小样本数据集,模型难以收敛的问题,采用迁移学习的方法,优化了模型的初始参数,提升模型的泛化能力和分割效率。此外,为了降低计算量、进一步提高分割效果,对数据集进行了裁剪和去噪。同时,将处理后的图像采用旋转、镜像等方法进行了数据扩充。实验结果表明,改进的U-Net的识别精确率(precision)、平均交并比(mean intersection-over-union,mIoU)分别能达到0.7352、0.4673,效果优于目前主流的分割算法,具有一定实际应用价值。     

Normalized cuts in 3-D for spinal MRI segmentation

Segmentation of medical images has become an indispensable process to perform quantitative analysis of images of human organs and their functions. Normalized Cuts (NCut) is a spectral graph theoretic method that readily admits combinations of different features for image segmentation. The computational demand imposed by NCut has been successfully alleviated with the Nystr?m approximation method for applications different than medical imaging. In this paper we discuss the application of NCut with the Nystr?m approximation method to segment vertebral bodies from sagittal T1-weighted magnetic resonance images of the spine. The magnetic resonance images were preprocessed by the anisotropic diffusion algorithm, and three-dimensional local histograms of brightness was chosen as the segmentation feature. Results of the segmentation as well as limitations and challenges in this area are presented.     

基于自组织神经网络的多模态MRI图像分割

磁共振成像(MRI)是一项重要的医学成像技术,在人体组织器官的诊断治疗方面被广泛应用。在脑肿瘤的临床诊断应用中,如何实现脑肿瘤图像的有效自动分割是一个研究的难点和重点。利用多个自组织神经网络(SOM)构造一个并行自组织神经网络(CSOM),将肿瘤图像的分割问题转化为并行自组织神经网络的分类问题。实验表明,并行自组织神经网络的应用,有效提高了分割精确度,有利于自动分割的实现。     

基于WFCM算法在MRI图像分割中的应用

模糊C均值聚类(FCM)算法是一种基于非监督聚类算法。样本加权模糊C均值聚类(WFCM)算法是FCM算法的改进,该算法能够明显提高收敛速度和聚类的准确性。无论是FCM算法还是WFCM算法,对噪声都相对敏感,而且聚类数目仍然需要人工确定。在此提出一种改进算法,首先通过偏微分方程(PDE)降噪算法对原始脑MRI医学图像进行处理;其次利用聚类有效性确定最佳聚类数目,对WFCM算法进行改进;最后利用本文改进算法对图像进行聚类分割。实验表明,该方法是一种具有自动分类能力、抗噪性较好的模糊聚类图像分割算法。     

Robust global motion estimation oriented to video object segmentation.

Most global motion estimation (GME) methods are oriented to video coding while video object segmentation methods either assume no global motion (GM) or directly adopt a coding-oriented method to compensate for GM. This paper proposes a hierarchical differential GME method oriented to video object segmentation. A scheme which combines three-step search and motion parameters prediction is proposed for initial estimation to increase efficiency. A robust estimator that uses object information to reject outliers introduced by local motion is also proposed. For the first frame, when the object information is unavailable, a robust estimator is proposed which rejects outliers by examining their distribution in local neighborhoods of the error between the current and the motion-compensated previous frame. Subjective and objective results show that the proposed method is more robust, more oriented to video object segmentation, and faster than the referenced methods.     

Robust automatic breast and pectoral muscle segmentation from scanned mammograms

Breast skin–air interface and pectoral muscle segmentation are usually first steps in all CAD applications on scanned as well as digital mammograms. Breast skin–air interface segmentation is much more difficult task when performed on scanned mammograms than on digital mammograms. In case of pectoral muscle segmentation, segmentation difficulty of analog and digital mammograms is usually similar. In this paper we present adaptive contrast enhancement method for breast skin–air interface detection which combines usage of adaptive histogram equalization method on small region of interest which contains actual edge and edge detection operators. Pectoral muscle detection method uses combination of contrast enhancement using adaptive histogram equalization and polynomial curvature estimation on selected region of interest. This method makes segmentation of very low contrast pectoral muscle areas possible because of estimation used to segment areas which have lower contrast difference than detection threshold.     

A Bayesian approach for stochastic white matter tractography

White matter fiber bundles in the human brain can be located by tracing the local water diffusion in diffusion weighted magnetic resonance imaging (MRI) images. In this paper, a novel Bayesian modeling approach for white matter tractography is presented. The uncertainty associated with estimated white matter fiber paths is investigated, and a method for calculating the probability of a connection between two areas in the brain is introduced. The main merits of the presented methodology are its simple implementation and its ability to handle noise in a theoretically justified way. Theory for estimating global connectivity is also presented, as well as a theorem that facilitates the estimation of the parameters in a constrained tensor model of the local water diffusion profile.