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.     

Increased differentiation of intracranial white matter lesions by multispectral 3D-tissue segmentation: preliminary results

MRI is a very sensitive imaging modality, however with relatively low specificity. The aim of this work was to determine the potential of image post-processing using 3D-tissue segmentation technique for identification and quantitative characterization of intracranial lesions primarily in the white matter. Forty subjects participated in this study: 28 patients with brain multiple sclerosis (MS), 6 patients with subcortical ischemic vascular dementia (SIVD), and 6 patients with lacunar white matter infarcts (LI). In routine MR imaging these pathologies may be almost indistinguishable. The 3D-tissue segmentation technique used in this study was based on three input MR images (T(1), T(2)-weighted, and proton density). A modified k-Nearest-Neighbor (k-NN) algorithm optimized for maximum computation speed and high quality segmentation was utilized. In MS lesions, two very distinct subsets were classified using this procedure. Based on the results of segmentation one subset probably represent gliosis, and the other edema and demyelination. In SIVD, the segmented images demonstrated homogeneity, which differentiates SIVD from the heterogeneity observed in MS. This homogeneity was in agreement with the general histological findings. The LI changes pathophysiologically from subacute to chronic. The segmented images closely correlated with these changes, showing a central area of necrosis with cyst formation surrounded by an area that appears like reactive gliosis. In the chronic state, the cyst intensity was similar to that of CSF, while in the subacute stage, the peripheral rim was more prominent. Regional brain lesion load were also obtained on one MS patient to demonstrate the potential use of this technique for lesion load measurements. The majority of lesions were identified in the parietal and occipital lobes. The follow-up study showed qualitatively and quantitatively that the calculated MS load increase was associated with brain atrophy represented by an increase in CSF volume as well as decrease in "normal" brain tissue volumes. Importantly, these results were consistent with the patient's clinical evolution of the disease after a six-month period. In conclusion, these results show there is a potential application for a 3D tissue segmentation technique to characterize white matter lesions with similar intensities on T(2)-weighted MR images. The proposed methodology warrants further clinical investigation and evaluation in a large patient population.     

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.     

Magnetic resonance imaging segmentation techniques using batch-type learning vector quantization algorithms

In this article, we propose batch-type learning vector quantization (LVQ) segmentation techniques for the magnetic resonance (MR) images. Magnetic resonance imaging (MRI) segmentation is an important technique to differentiate abnormal and normal tissues in MR image data. The proposed LVQ segmentation techniques are compared with the generalized Kohonen's competitive learning (GKCL) methods, which were proposed by Lin et al. [Magn Reson Imaging 21 (2003) 863-870]. Three MRI data sets of real cases are used in this article. The first case is from a 2-year-old girl who was diagnosed with retinoblastoma in her left eye. The second case is from a 55-year-old woman who developed complete left side oculomotor palsy immediately after a motor vehicle accident. The third case is from an 84-year-old man who was diagnosed with Alzheimer disease (AD). Our comparisons are based on sensitivity of algorithm parameters, the quality of MRI segmentation with the contrast-to-noise ratio and the accuracy of the region of interest tissue. Overall, the segmentation results from batch-type LVQ algorithms present good accuracy and quality of the segmentation images, and also flexibility of algorithm parameters in all the comparison consequences. The results support that the proposed batch-type LVQ algorithms are better than the previous GKCL algorithms. Specifically, the proposed fuzzy-soft LVQ algorithm works well in segmenting AD MRI data set to accurately measure the hippocampus volume in AD MR images.     

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.     

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.     

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.     

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.     

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.     

STrategically Acquired Gradient Echo (STAGE) imaging,part III: Technical advances and clinical applications of a rapid multi-contrast multi-parametric brain imaging method

One major thrust in radiology today is image standardization with a focus on rapidly acquired quantitative multi-contrast information. This is critical for multi-center trials, for the collection of big data and for the use of artificial intelligence in evaluating the data. Strategically acquired gradient echo (STAGE) imaging is one such method that can provide 8 qualitative and 7 quantitative pieces of information in 5 min or less at 3 T. STAGE provides qualitative images in the form of proton density weighted images, T1 weighted images, T2* weighted images and simulated double inversion recovery (DIR) images. STAGE also provides quantitative data in the form of proton spin density, T1, T2* and susceptibility maps as well as segmentation of white matter, gray matter and cerebrospinal fluid. STAGE uses vendors' product gradient echo sequences. It can be applied from 0.35 T to 7 T across all manufacturers producing similar results in contrast and quantification of the data. In this paper, we discuss the strengths and weaknesses of STAGE, demonstrate its contrast-to-noise (CNR) behavior relative to a large clinical data set and introduce a few new image contrasts derived from STAGE, including DIR images and a new concept referred to as true susceptibility weighted imaging (tSWI) linked to fluid attenuated inversion recovery (FLAIR) or tSWI-FLAIR for the evaluation of multiple sclerosis lesions. The robustness of STAGE T1 mapping was tested using the NIST/NIH phantom, while the reproducibility was tested by scanning a given individual ten times in one session and the same subject scanned once a week over a 12-week period. Assessment of the CNR for the enhanced T1W image (T1WE) showed a significantly better contrast between gray matter and white matter than conventional T1W images in both patients with Parkinson's disease and healthy controls. We also present some clinical cases using STAGE imaging in patients with stroke, metastasis, multiple sclerosis and a fetus with ventriculomegaly. Overall, STAGE is a comprehensive protocol that provides the clinician with numerous qualitative and quantitative images.     

基于偏振测量的雾天图像场景分割

现有场景分割方法主要依赖于图像亮度、颜色和纹理等特征,然而在雾天图像中提取这些特征将变得困难且不稳定.基于此本文提出了适用于雾天图像场景分割的特征矢量,以及相应的特征提取算法.特征矢量由目标偏振度、深度和颜色三部分组成.特征提取算法分别为:用去相关的方法从图像偏振度分离出大气偏振度和目标偏振度;根据雾天退化模型和雾天图像偏振表示形式推导出场景深度信息;利用两幅偏振图像求出非偏振彩色图像,从而得到场景的颜色信息.将这些特征构成的特征矢量用于基于图的分割算法中,并从两个方面比较了仅使用颜色特征和使用本文特征矢量的分割结果.最后得出结论:对于雾天图像而言,这些特征比通常的颜色特征更加有效和鲁棒.     

Hybrid segmentation of left ventricle in cardiac MRI using gaussian-mixture model and region restricted dynamic programming

Segmentation of the left ventricle from cardiac magnetic resonance images (MRI) is very important to quantitatively analyze global and regional cardiac function. The aim of this study is to develop a novel and robust algorithm which can improve the accuracy of automatic left ventricle segmentation on short-axis cardiac MRI. The database used in this study consists of three data sets obtained from the Sunnybrook Health Sciences Centre. Each data set contains 15 cases (4 ischemic heart failures, 4 non-ischemic heart failures, 4 left ventricle (LV) hypertrophies and 3 normal cases). Three key techniques are developed in this segmentation algorithm: (1) ray scanning approach is designed for segmentation of images with left ventricular outflow tract (LVOT), (2) a region restricted technique is employed for epicardial contour extraction, and (3) an edge map with non-maxima gradient suppression approach is put forward to improve the dynamic programming to derive the epicardial boundary. The validation experiments were performed on a pool of data sets of 45 cases. For both endo- and epi-cardial contours of our results, percentage of good contours is about 91%, the average perpendicular distance is about 2 mm. The overlapping dice metric is about 0.92. The regression and determination coefficient between the experts and our proposed method on the ejection fraction (EF) is 1.01 and 0.9375, respectively; they are 0.9 and 0.8245 for LV mass. The proposed segmentation method shows the better performance and is very promising in improving the accuracy of computer-aided diagnosis systems in cardiovascular diseases.     

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.     

Target extraction in forward-looking infrared images using fuzzy thresholding via local region analysis

In this paper, a target extraction method in forward-looking infrared (FLIR) images based on fuzzy thresholding which used local characteristics, bi-modality and adjacency, is proposed. The bi-modality represents how a pixel is classified into a part of a target using distribution of pixel values in a local region, and the adjacency is a measure to represent how far each pixel is from the target region. Segmentation is processed by the following: First, membership values for each pixel are calculated using bi-modality and adjacency. Second, fuzzy thresholding is performed to extract the target from the background. Finally, we extract the precise target in the thresholded image by post-processing. To evaluate the performance of the proposed target extraction method, we compare the proposed method with other segmentation methods using various FLIR images. Experimental results show that the proposed algorithm has good segmentation performance.     

Multiplicative intrinsic component optimization (MICO) for MRI bias field estimation and tissue segmentation

This paper proposes a new energy minimization method called multiplicative intrinsic component optimization (MICO) for joint bias field estimation and segmentation of magnetic resonance (MR) images. The proposed method takes full advantage of the decomposition of MR images into two multiplicative components, namely, the true image that characterizes a physical property of the tissues and the bias field that accounts for the intensity inhomogeneity, and their respective spatial properties. Bias field estimation and tissue segmentation are simultaneously achieved by an energy minimization process aimed to optimize the estimates of the two multiplicative components of an MR image. The bias field is iteratively optimized by using efficient matrix computations, which are verified to be numerically stable by matrix analysis. More importantly, the energy in our formulation is convex in each of its variables, which leads to the robustness of the proposed energy minimization algorithm. The MICO formulation can be naturally extended to 3D/4D tissue segmentation with spatial/sptatiotemporal regularization. Quantitative evaluations and comparisons with some popular softwares have demonstrated superior performance of MICO in terms of robustness and accuracy.     

First-order kernel density estimation of abdomen medical image intensity and spatial information and application to segmentation

Kernel density estimators (KDE) used for many medical image applications only consider the intensity information of each pixel or its neighbors without the ability of expressing the structure and shape of tissues and organs, and they suffer from boundary bias problem. In this paper, we propose a new first-order kernel density estimation (FOKDE) method for 1D intensity information and 2D spatial information of medical image in two steps. First, the FOKDE of intensity information is estimated and applied to medical image segmentation with the multi-thresholding algorithm. Second, we estimate the FOKDE of spatial information on the initial segmentation, which can express the structure and shape of organs and tissues. In order to evaluate the FOKDE and KDE of the 2D spatial information, we apply them to medical image segmentation with the hill-climbing strategy. Density estimation experiments and segmentation application results on the simulated dataset and real abdomen CT images show us that the FOKDE has smaller boundary bias than the KDE, and that it can estimate the structure and shape of tissues and organs with spatial information effectively.     

A Hybrid Preaching Optimization Algorithm Based on Kapur Entropy for Multilevel Thresholding Color Image Segmentation

Multilevel thresholding segmentation of color images plays an important role in many fields. The pivotal procedure of this technique is determining the specific threshold of the images. In this paper, a hybrid preaching optimization algorithm (HPOA) for color image segmentation is proposed. Firstly, the evolutionary state strategy is adopted to evaluate the evolutionary factors in each iteration. With the introduction of the evolutionary state, the proposed algorithm has more balanced exploration-exploitation compared with the original POA. Secondly, in order to prevent premature convergence, a randomly occurring time-delay is introduced into HPOA in a distributed manner. The expression of the time-delay is inspired by particle swarm optimization and reflects the history of previous personal optimum and global optimum. To better verify the effectiveness of the proposed method, eight well-known benchmark functions are employed to evaluate HPOA. In the interim, seven state-of-the-art algorithms are utilized to compare with HPOA in the terms of accuracy, convergence, and statistical analysis. On this basis, an excellent multilevel thresholding image segmentation method is proposed in this paper. Finally, to further illustrate the potential, experiments are respectively conducted on three different groups of Berkeley images. The quality of a segmented image is evaluated by an array of metrics including feature similarity index (FSIM), peak signal-to-noise ratio (PSNR), structural similarity index (SSIM), and Kapur entropy values. The experimental results reveal that the proposed method significantly outperforms other algorithms and has remarkable and promising performance for multilevel thresholding color image segmentation.     

The study and application of the improved region growing algorithm for liver segmentation

In order to improve the accuracy of the medical image segmentation and reduce the effect of selecting seed points using region growing algorithm, an improved region growing method is proposed in this paper. First, the source images are pre-processed using non-linear mapping method and the region of interest in the liver is selected by man–machine interaction; Quasi-Monte Carlo method is used for generating low-dispersion sequences points in the region of interest and the optical seed points are selected by computing these points; In addition, the region growing criteria is also improved. The improved region growing algorithm is used for segmenting three discontinuous abdomen CT images. Compared with the traditional region growing method, the improved method can get better liver segmentation effects. The proposed method can be effectively applied to liver segmentation and it can improve the accuracy of liver segmentation.     

An improved lesion detection approach based on similarity measurement between fuzzy intensity segmentation and spatial probability maps

The application of automatic segmentation methods in lesion detection is desirable. However, such methods are restricted by intensity similarities between lesioned and healthy brain tissue. Using multi-spectral magnetic resonance imaging (MRI) modalities may overcome this problem but it is not always practicable. In this article, a lesion detection approach requiring a single MRI modality is presented, which is an improved method based on a recent publication. This new method assumes that a low similarity should be found in the regions of lesions when the likeness between an intensity based fuzzy segmentation and a location based tissue probabilities is measured. The usage of a normalized similarity measurement enables the current method to fine-tune the threshold for lesion detection, thus maximizing the possibility of reaching high detection accuracy. Importantly, an extra cleaning step is included in the current approach which removes enlarged ventricles from detected lesions. The performance investigation using simulated lesions demonstrated that not only the majority of lesions were well detected but also normal tissues were identified effectively. Tests on images acquired in stroke patients further confirmed the strength of the method in lesion detection. When compared with the previous version, the current approach showed a higher sensitivity in detecting small lesions and had less false positives around the ventricle and the edge of the brain.