An energy minimization method for MS lesion segmentation from T1-w and FLAIR images

In this paper, we extend the multiplicative intrinsic component optimization (MICO) algorithm to multichannel MR image segmentation, with focus on segmentation of multiple sclerosis (MS) lesions. The MICO algorithm was originally proposed by Li et al. in Ref. [1] for normal brain tissue segmentation and intensity inhomogeneity correction of a single channel MR image, which exhibits desirable advantages over other methods for MR image segmentation and intensity inhomogeneity correction in terms of segmentation accuracy and robustness. In this paper, we extend the MICO algorithm to multi-channel MR image segmentation and enable the segmentation of MS lesions. We assign different weights for different channels to control the impact of each channel. The weighted channels allow the enhancement of the impact of the FLAIR image on the segmentation of MS lesions by assigning a larger weight to the FLAIR image channel than the other channels. With the inherent mechanism of estimation of the bias field, our method is able to deal with the intensity inhomogeneity in the input multi-channel MR images. In the application of our method, we only use T1-w and FLAIR images as the input two channel MR images. Experimental results show promising result of our method.     

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.     

Automatic white matter lesion segmentation using an adaptive outlier detection method

White matter (WM) lesions are diffuse WM abnormalities that appear as hyperintense (bright) regions in cranial magnetic resonance imaging (MRI). WM lesions are often observed in older populations and are important indicators of stroke, multiple sclerosis, dementia and other brain-related disorders. In this paper, a new automated method for WM lesions segmentation is presented. In the proposed method, the presence of WM lesions is detected as outliers in the intensity distribution of the fluid-attenuated inversion recovery (FLAIR) MR images using an adaptive outlier detection approach. Outliers are detected using a novel adaptive trimmed mean algorithm and box-whisker plot. In addition, pre- and postprocessing steps are implemented to reduce false positives attributed to MRI artifacts commonly observed in FLAIR sequences. The approach is validated using the cranial MRI sequences of 38 subjects. A significant correlation (R=0.9641, P value=3.12×10(-3)) is observed between the automated approach and manual segmentation by radiologist. The accuracy of the proposed approach was further validated by comparing the lesion volumes computed using the automated approach and lesions manually segmented by an expert radiologist. Finally, the proposed approach is compared against leading lesion segmentation algorithms using a benchmark dataset.     

A fully automatic three-step liver segmentation method on LDA-based probability maps for multiple contrast MR images

Automatic 3D liver segmentation in magnetic resonance (MR) data sets has proven to be a very challenging task in the domain of medical image analysis. There exist numerous approaches for automatic 3D liver segmentation on computer tomography data sets that have influenced the segmentation of MR images. In contrast to previous approaches to liver segmentation in MR data sets, we use all available MR channel information of different weightings and formulate liver tissue and position probabilities in a probabilistic framework. We apply multiclass linear discriminant analysis as a fast and efficient dimensionality reduction technique and generate probability maps then used for segmentation. We develop a fully automatic three-step 3D segmentation approach based upon a modified region growing approach and a further threshold technique. Finally, we incorporate characteristic prior knowledge to improve the segmentation results. This novel 3D segmentation approach is modularized and can be applied for normal and fat accumulated liver tissue properties.     

Are multi-contrast magnetic resonance images necessary for segmenting multiple sclerosis brains? A large cohort study based on deep learning

BackgroundMagnetic resonance images with multiple contrasts or sequences are commonly used for segmenting brain tissues, including lesions, in multiple sclerosis (MS). However, acquisition of images with multiple contrasts increases the scan time and complexity of the analysis, possibly introducing factors that could compromise segmentation quality.ObjectiveTo investigate the effect of various combinations of multi-contrast images as input on the segmented volumes of gray (GM) and white matter (WM), cerebrospinal fluid (CSF), and lesions using a deep neural network.MethodsU-net, a fully convolutional neural network was used to automatically segment GM, WM, CSF, and lesions in 1000 MS patients. The input to the network consisted of 15 combinations of FLAIR, T1-, T2-, and proton density-weighted images. The Dice similarity coefficient (DSC) was evaluated to assess the segmentation performance. For lesions, true positive rate (TPR) and false positive rate (FPR) were also evaluated. In addition, the effect of lesion size on lesion segmentation was investigated.ResultsHighest DSC was observed for all the tissue volumes, including lesions, when the input was combination of all four image contrasts. All other input combinations that included FLAIR also provided high DSC for all tissue classes. However, the quality of lesion segmentation showed strong dependence on the input images. The DSC and TPR values for inputs with the four contrast combination and FLAIR alone were very similar, but FLAIR showed a moderately higher FPR for lesion size <100 μl. For lesions smaller than 20 μl all image combinations resulted in poor performance. The segmentation quality improved with lesion size.ConclusionsBest performance for segmented tissue volumes was obtained with all four image contrasts as the input, and comparable performance was attainable with FLAIR only as the input, albeit with a moderate increase in FPR for small lesions. This implies that acquisition of only FLAIR images provides satisfactory tissue segmentation. Lesion segmentation was poor for very small lesions and improved rapidly with lesion size.     

Image-guided regularization level set evolution for MR image segmentation and bias field correction

Magnetic resonance (MR) image segmentation is a crucial step in surgical and treatment planning. In this paper, we propose a level-set-based segmentation method for MR images with intensity inhomogeneous problem. To tackle the initialization sensitivity problem, we propose a new image-guided regularization to restrict the level set function. The maximum a posteriori inference is adopted to unify segmentation and bias field correction within a single framework. Under this framework, both the contour prior and the bias field prior are fully used. As a result, the image intensity inhomogeneity can be well solved. Extensive experiments are provided to evaluate the proposed method, showing significant improvements in both segmentation and bias field correction accuracies as compared with other state-of-the-art approaches.     

Automatic segmentation of white matter lesions on magnetic resonance images of the brain by using an outlier detection strategy

White matter lesions (WMLs) are commonly observed on the magnetic resonance (MR) images of normal elderly in association with vascular risk factors, such as hypertension or stroke. An accurate WML detection provides significant information for disease tracking, therapy evaluation, and normal aging research. In this article, we present an unsupervised WML segmentation method that uses Gaussian mixture model to describe the intensity distribution of the normal brain tissues and detects the WMLs as outliers to the normal brain tissue model based on extreme value theory. The detection of WMLs is performed by comparing the probability distribution function of a one-sided normal distribution and a Gumbel distribution, which is a specific extreme value distribution. The performance of the automatic segmentation is validated on synthetic and clinical MR images with regard to different imaging sequences and lesion loads. Results indicate that the segmentation method has a favorable accuracy competitive with other state-of-the-art WML segmentation methods.     

Removal of partial volume averaging with free water in MR diffusion tensor imaging using inversion recovery for b0 image

Purpose

To remove the partial volume averaging effect of free water in MR diffusion imaging of neural tissues by use of the fluid attenuated inversion recovery (FLAIR) without the penalty of an extended scan time.

Materials and methods

The magnetic resonance images were obtained from a normal volunteer in a coronal slice orientation at 3 T with the 20-channel rf coil. In diffusion imaging only the b0 images were obtained with the FLAIR contrast while the diffusion weighted images were obtained without the FLAIR contrast. A composition of FLAIR b0 and non-FLAIR diffusion weighted images was used in calculating the diffusion tensor and fractional anisotropy after compensating the reduced signal amplitude due to the inversion recovery in the FLAIR b0 images. The fractional anisotropy of the non-FLAIR, FLAIR, and the composite methods were analyzed for the mean and histogram in the corpus callosum, cervical spine, and the fornix tracts.

Results

The partial volume averaging effect was observed in the corpus callosum, the cervical spine, and the fornix tracts in the non-FLAIR b0 and diffusion images. The partial volume averaging effect was removed in the FLAIR diffusion images which took more than twice the scan time than the non-FLAIR diffusion imaging. The proposed composite FLAIR diffusion imaging removed the partial volume averaging effect as in the FLAIR diffusion imaging. The distribution of the FA histogram was very different between the non-FLAIR and FLAIR diffusion images, while it was very similar between the FLAIR and the composite FLAIR after correcting the white matter signal in the FLAIR b0 images.

Conclusions

The proposed composite FLAIR diffusion imaging method was equally effective in removing the partial volume averaging effect as the FLAIR diffusion imaging at a limited increase of the scan time since only a small number of b0 images needed to be obtained with the FLAIR contrast.     

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.     

结合小波融合和深度学习的脑胶质瘤自动分割

针对水肿区域边界模糊和瘤内结构复杂多变导致的脑胶质瘤分割不精确问题，本文提出了一种基于小波融合和3D-UNet网络的脑胶质瘤磁共振图像自动分割算法.首先，对脑胶质瘤磁共振图像的T1、T1ce、T2、Flair四种模态进行小波融合以及偏置场校正；然后，提取待分类的图像块；再利用提取的图像块训练3D-UNet网络以对图像块中的像素进行分类；最后加载损失率较小的网络模型进行分割，并采用基于连通区域的轮廓提取方法，以降低假阳性率.对57组Brats2018（Brain Tumor Segmentation 2018）磁共振图像测试集进行分割的结果显示，肿瘤的整体、核心和水肿部分的平均分割准确率（DSC）分别达到90.64%、80.74%和86.37%，这表明该算法分割脑胶质瘤准确率较高，与金标准相近.相比多模态图像融合前，该算法在减少输入网络数据量和图像冗余信息的同时，还一定程度上解决了胶质瘤边界模糊、分割不精确的问题，提高了分割的准确度和鲁棒性.     

Hepatic vessel segmentation using variational level set combined with non-local robust statistics

Hepatic vessel segmentation is a challenging step in therapy guided by magnetic resonance imaging (MRI). This paper presents an improved variational level set method, which uses non-local robust statistics to suppress the influence of noise in MR images. The non-local robust statistics, which represent vascular features, are learned adaptively from seeds provided by users. K-means clustering in neighborhoods of seeds is utilized to exclude inappropriate seeds, which are obviously corrupted by noise. The neighborhoods of appropriate seeds are placed in an array to calculate the non-local robust statistics, and the variational level set formulation can be constructed. Bias correction is utilized in the level set formulation to reduce the influence of intensity inhomogeneity of MRI. Experiments were conducted over real MR images, and showed that the proposed method performed better on small hepatic vessel segmentation compared with other segmentation methods.     

Dynamic pixel-wise weighting-based fully convolutional neural networks for left ventricle segmentation in short-axis MRI

Left ventricle (LV) segmentation in cardiac MRI is an essential procedure for quantitative diagnosis of various cardiovascular diseases. In this paper, we present a novel fully automatic left ventricle segmentation approach based on convolutional neural networks. The proposed network fully takes advantages of the hierarchical architecture and integrate the multi-scale feature together for segmenting the myocardial region of LV. Moreover, we put forward a dynamic pixel-wise weighting strategy, which can dynamically adjust the weight of each pixel according to the segmentation accuracy of upper layer and force the pixel classifier to take more attention on the misclassified ones. By this way, the LV segmentation performance of our method can be improved a lot especially for the apical and basal slices in cine MR images. The experiments on the CAP database demonstrate that our method achieves a substantial improvement compared with other well-know deep learning methods. Beside these, we discussed two major limitations in convolutional neural networks-based semantic segmentation methods for LV segmentation.     

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.     

Methods for quantitative image quality evaluation of MRI parallel reconstructions: detection and perceptual difference model

Many reconstruction algorithms are being proposed for parallel magnetic resonance imaging (MRI), which uses multiple coils and subsampled k-space data, and a quantitative method for comparison of algorithms is sorely needed. On such images, we compared three methods for quantitative image quality evaluation: human detection, computer detection model and a computer perceptual difference model (PDM). One-quarter sampling and three different reconstruction methods were investigated: a regularization method developed by Ying et al., a simplified regularization method and an iterative method proposed by Pruessmann et al. Images obtained from a full complement of k-space data were also included as reference images. Detection studies were performed using a simulated dark tumor added on MR images of fresh bovine liver. Human detection depended strongly on reconstruction methods used, with the two regularization methods achieving better performance than the iterative method. Images were also evaluated using detection by a channelized Hotelling observer model and by PDM scores. Both predicted the same trends as observed from human detection. We are encouraged that PDM gives trends similar to that for human detection studies. Its ease of use and applicability to a variety of MRI situations make it attractive for evaluating image quality in a variety of MR studies.     

Multicontext wavelet-based thresholding segmentation of brain tissues in magnetic resonance images

A novel segmentation method based on wavelet transform is presented for gray matter, white matter and cerebrospinal fluid in thin-sliced single-channel brain magnetic resonance (MR) scans. On the basis of the local image model, multicontext wavelet-based thresholding segmentation (MCWT) is proposed to classify 2D MR data into tissues automatically. In MCWT, the wavelet multiscale transform of local image gray histogram is done, and the gray threshold is gradually revealed from large-scale to small-scale coefficients. Image segmentation is independently performed in each local image to calculate the degree of membership of a pixel to each tissue class. Finally, a strategy is adopted to integrate the intersected outcomes from different local images. The result of the experiment indicates that MCWT outperforms other traditional segmentation methods in classifying brain MR images.     

Magnetic-resonance image segmentation based on improved variable weight multi-resolution Markov random field in undecimated complex wavelet domain

To solve the problem that the magnetic resonance (MR) image has weak boundaries, large amount of information, and low signal-to-noise ratio, we propose an image segmentation method based on the multi-resolution Markov random field (MRMRF) model. The algorithm uses undecimated dual-tree complex wavelet transformation to transform the image into multiple scales. The transformed low-frequency scale histogram is used to improve the initial clustering center of the K-means algorithm, and then other cluster centers are selected according to the maximum distance rule to obtain the coarse-scale segmentation. The results are then segmented by the improved MRMRF model. In order to solve the problem of fuzzy edge segmentation caused by the gray level inhomogeneity of MR image segmentation under the MRMRF model, it is proposed to introduce variable weight parameters in the segmentation process of each scale. Furthermore, the final segmentation results are optimized. We name this algorithm the variable-weight multi-resolution Markov random field (VWMRMRF). The simulation and clinical MR image segmentation verification show that the VWMRMRF algorithm has high segmentation accuracy and robustness, and can accurately and stably achieve low signal-to-noise ratio, weak boundary MR image segmentation.     

A novel content-based active contour model for brain tumor segmentation

Brain tumor segmentation is a crucial step in surgical and treatment planning. Intensity-based active contour models such as gradient vector flow (GVF), magneto static active contour (MAC) and fluid vector flow (FVF) have been proposed to segment homogeneous objects/tumors in medical images. In this study, extensive experiments are done to analyze the performance of intensity-based techniques for homogeneous tumors on brain magnetic resonance (MR) images. The analysis shows that the state-of-art methods fail to segment homogeneous tumors against similar background or when these tumors show partial diversity toward the background. They also have preconvergence problem in case of false edges/saddle points. However, the presence of weak edges and diffused edges (due to edema around the tumor) leads to oversegmentation by intensity-based techniques. Therefore, the proposed method content-based active contour (CBAC) uses both intensity and texture information present within the active contour to overcome above-stated problems capturing large range in an image. It also proposes a novel use of Gray-Level Co-occurrence Matrix to define texture space for tumor segmentation. The effectiveness of this method is tested on two different real data sets (55 patients - more than 600 images) containing five different types of homogeneous, heterogeneous, diffused tumors and synthetic images (non-MR benchmark images). Remarkable results are obtained in segmenting homogeneous tumors of uniform intensity, complex content heterogeneous, diffused tumors on MR images (T1-weighted, postcontrast T1-weighted and T2-weighted) and synthetic images (non-MR benchmark images of varying intensity, texture, noise content and false edges). Further, tumor volume is efficiently extracted from 2-dimensional slices and is named as 2.5-dimensional segmentation.     

Automated Detection and Characterization of Multiple Sclerosis Lesions in Brain MR Images

In the present study an automatic algorithm for detection and contouring of multiple sclerosis (MS) lesions in brain magnetic resonance (MR) images is introduced. This algorithm automatically detects MS lesions in axial proton density, T₂-weighted, gadolinium enhanced, and fast fluid attenuated inversion recovery (FLAIR) brain MR images. Automated detection consists of three main stages: (1) detection and contouring of all hyperintense signal regions within the image; (2) partial elimination of false positive segments (defined herein as artifacts) by size, shape index, and anatomical location; (3) the use of an artificial neural paradigm (Back-Propagation) for final removal of artifacts by differentiating them from true MS lesions. The algorithm was applied to 45 images acquired from 14 MS patients. The algorithm’s sensitivity was 0.87 and the specificity 0.96. In 34 images, 100% of the lesions were detected. The algorithm potentially may serve as a useful preprocessing tool for quantitative MS monitoring via magnetic resonance imaging.     

Compressed Sensing MRI Using Sparsity Averaging and FISTA

Magnetic resonance imaging (MRI) is widely adopted for clinical diagnosis due to its non-invasively detection. However, acquisition of full k-space data limits its imaging speed. Compressed sensing (CS) provides a new technique to significantly reduce the measurements with high-quality MR image reconstruction. The sparsity of the MR images is one of the crucial bases of CS-MRI. In this paper, we present to use sparsity averaging prior for CS-MRI reconstruction in the basis of that MR images have average sparsity over multiple wavelet frames. The problem is solved using a Fast Iterative Shrinkage Thresholding Algorithm (FISTA), each iteration of which includes a shrinkage step. The performance of the proposed method is evaluated for several types of MR images. The experiment results illustrate that our approach exhibits a better performance than those methods that using redundant frame or a single orthonormal basis to promote sparsity.