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.     

MRI segmentation: Methods and applications

The current literature on MRI segmentation methods is reviewed. Particular emphasis is placed on the relative merits of single image versus multispectral segmentation, and supervised versus unsupervised segmentation methods. Image pre-processing and registration are discussed, as well as methods of validation. The application of MRI segmentation for tumor volume measurements during the course of therapy is presented here as an example, illustrating problems associated with inter- and intra-observer variations inherent to supervised methods.     

Application of fuzzy c-means segmentation technique for tissue differentiation in MR images of a hemorrhagic glioblastoma multiforme

The application of a raw data-based, operator-independent MR segmentation technique to differentiate boundaries of tumor from edema or hemorrhage is demonstrated. A case of a glioblastoma multiforme with gross and histopathologic correlation is presented. The MR image data set was segmented into tissue classes based on three different MR weighted image parameters (T₁-, proton density-, and T₂-weighted) using unsupervised fuzzy c-means (FCM) clustering algorithm technique for pattern recognition. A radiological examination of the MR images and correlation with fuzzy clustering segmentations was performed. Results were confirmed by gross and histopathology which, to the best of our knowledge, reports the first application of this demanding approach. Based on the results of neuropathologic correlation, the application of FCM MR image segmentation to several MR images of a glioblastoma multiforme represents a viable technique for displaying diagnostically relevant tissue contrast information used in 3D volume reconstruction. With this technique, it is possible to generate segmentation images that display clinically important neuroanatomic and neuropathologic tissue contrast information from raw MR image data.     

3-D in vivo brain tumor geometry study by scaling analysis

A new method, based on scaling analysis, is used to calculate fractal dimension and local roughness exponents to characterize in vivo 3-D tumor growth in the brain. Image acquisition was made according to the standard protocol used for brain radiotherapy and radiosurgery, i.e., axial, coronal and sagittal magnetic resonance T₁-weighted images, and comprising the brain volume for image registration. Image segmentation was performed by the application of the k-means procedure upon contrasted images. We analyzed glioblastomas, astrocytomas, metastases and benign brain tumors. The results show significant variations of the parameters depending on the tumor stage and histological origin.     

Automatic segmentation of brain white matter and white matter lesions in normal aging: comparison of five multispectral techniques

White matter loss, ventricular enlargement and white matter lesions are common findings on brain scans of older subjects. Accurate assessment of these different features is therefore essential for normal aging research. Recently, we developed a novel unsupervised classification method, named ‘Multispectral Coloring Modulation and Variance Identification’ (MCMxxxVI), that fuses two different structural magnetic resonance imaging (MRI) sequences in red/green color space and uses Minimum Variance Quantization (MVQ) as the clustering technique to segment different tissue types. Here we investigate how this method performs compared with several commonly used supervised image classifiers in segmenting normal-appearing white matter, white matter lesions and cerebrospinal fluid in the brains of 20 older subjects with a wide range of white matter lesion load and brain atrophy. The three tissue classes were segmented from T₁-, T₂-, T₂?- and fluid attenuation inversion recovery (FLAIR)-weighted structural MRI data using MCMxxxVI and the four supervised multispectral classifiers available in the Analyze package, namely, Back-Propagated Neural Networks, Gaussian classifier, Nearest Neighbor and Parzen Windows. Bland–Altman analysis and Jaccard index values indicated that, in general, MCMxxxVI performed better than the supervised multispectral classifiers in identifying the three tissue classes, although final manual editing was still required to deliver radiologically acceptable results. These analyses show that MVQ, as implemented in MCMxxxVI, has the potential to provide quick and accurate white matter segmentations in the aging brain, although further methodological developments are still required to automate fully this technique.     

大豆冠层多光谱图像提取方法

为解决大豆冠层在近地端的多光谱图像边缘灰度不均,目标与背景之间灰度差别小,难以准确高效地获取大豆冠层目标区域的难题,将多光谱成像处理技术与经典图像分割方法有机融合,提出基于多光谱图像处理技术的大豆冠层提取方法。以东北大豆为对象,通过Sequoia多光谱相机采集绿光、近红外、红光、红边和可见光五类大豆多光谱图像,采用高斯平滑滤波法对原始大豆多光谱图像进行预处理,分析多光谱图像中大豆冠层和背景的灰度直方图分布特性,在此基础上利用迭代法、Otsu法和局部阈值法提取原大豆多光谱图像中冠层区域,并以图像形态学开运算处理细化和扩张背景,避免图像区域内干扰噪声对大豆冠层识别效果的影响,同时以有效分割率、过分割率、欠分割率、信息熵以及运行时间等为监督指标,对大豆冠层多光谱图像识别模型进行效果评价。大豆冠层识别模型中迭代法可以有效分割近红外和可见光大豆冠层图像,有效分割率分别为97.81%和87.99%,对绿光、红光和红边大豆冠层图像分割效果较差,有效分割率低于70%;Otsu法和局部阈值法可以有效分割除红光波段的其余四种多光谱大豆冠层图像,且有效分割率均在82%以上;三种算法对红光大豆冠层图像的有效分割率均低于20%,未达到较好效果。在原始多光谱图像中应用迭代法、Otsu法和局部阈值法提取大豆冠层图像与标准图像的信息熵平均值波动幅度分别为：0.120 1,0.054 7和0.059 8,其中Otsu法和局部阈值法较小,表明了对于大豆冠层多光谱图像识别中两种算法的有效性。该算法中Otsu法和局部阈值法均可以有效提取绿光、近红外、红边和可见光等多光谱的大豆冠层图像,二者较为完整地保留了大豆冠层信息,其中Otsu法实时性能较局部阈值法更好。该成果为提取农作物冠层多光谱图像提供理论依据和技术借鉴。     

An Interval Iteration Based Multilevel Thresholding Algorithm for Brain MR Image Segmentation

In this paper, we propose an interval iteration multilevel thresholding method (IIMT). This approach is based on the Otsu method but iteratively searches for sub-regions of the image to achieve segmentation, rather than processing the full image as a whole region. Then, a novel multilevel thresholding framework based on IIMT for brain MR image segmentation is proposed. In this framework, the original image is first decomposed using a hybrid L₁ − L₀ layer decomposition method to obtain the base layer. Second, we use IIMT to segment both the original image and its base layer. Finally, the two segmentation results are integrated by a fusion scheme to obtain a more refined and accurate segmentation result. Experimental results showed that our proposed algorithm is effective, and outperforms the standard Otsu-based and other optimization-based segmentation methods.     

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.     

Technical aspects and evaluation methodology for the application of two automated brain MRI tumor segmentation methods in radiation therapy planning

The purpose of this study was to design the steps necessary to create a tumor volume outline from the results of two automated multispectral magnetic resonance imaging segmentation methods and integrate these contours into radiation therapy treatment planning. Algorithms were developed to create a closed, smooth contour that encompassed the tumor pixels resulting from two automated segmentation methods: k-nearest neighbors and knowledge guided. These included an automatic three-dimensional (3D) expansion of the results to compensate for their undersegmentation and match the extended contouring technique used in practice by radiation oncologists. Each resulting radiation treatment plan generated from the automated segmentation and from the outlining by two radiation oncologists for 11 brain tumor patients was compared against the volume and treatment plan from an expert radiation oncologist who served as the control. As part of this analysis, a quantitative and qualitative evaluation mechanism was developed to aid in this comparison. It was found that the expert physician reference volume was irradiated within the same level of conformity when using the plans generated from the contours of the segmentation methods. In addition, any uncertainty in the identification of the actual gross tumor volume by the segmentation methods, as identified by previous research into this area, had small effects when used to generate 3D radiation therapy treatment planning due to the averaging process in the generation of margins used in defining a planning target volume.     

Quantification of cerebral perfusion using the "bookend technique": an evaluation in CNS tumors

We present a method of quantifying cerebral blood volume using dynamic susceptibility contrast. Our approach combines T₂-weighted echo planar imaging (EPI) pulse sequences and reference scans that determine the parenchymal T₁ changes resulting from an injection of a gadolinium chelate. This combined T₂- and T₁-weighted approach (the “bookend” technique) has been shown to be effective in the quantification of gradient-echo (GRE) (T₂*-weighted) perfusion images but has not been applied to spin-echo EPI (SE-EPI) (T₂-weighted) images. The physics related to blood volume measurement based on T₂- and T₂*-weighted EPI sequences is known to be different, and there is a question as to whether the bookend approach is effective with SE-EPI. We have compared the quantitative SE-EPI with GRE-EPI in a series of patients with central nervous system (CNS) tumors. We found that quantitative cerebral blood volume (qCBV) values for SE-EPI and GRE-EPI are in agreement with each other and with historical reference values. A subjective evaluation of image quality showed that image quality in the SE-EPI scans was high and exhibited high interreader agreement. We conclude that measuring qCBV using the bookend technique with SE-EPI images is possible and may be a viable alternative to GRE-EPI in the evaluation of CNS tumors.     

A Fast kNN Algorithm Using Multiple Space-Filling Curves

The paper considers a time-efficient implementation of the k nearest neighbours (kNN) algorithm. A well-known approach for accelerating the kNN algorithm is to utilise dimensionality reduction methods based on the use of space-filling curves. In this paper, we take this approach further and propose an algorithm that employs multiple space-filling curves and is faster (with comparable quality) compared with the kNN algorithm, which uses kd-trees to determine the nearest neighbours. A specific method for constructing multiple Peano curves is outlined, and statements are given about the preservation of object proximity information in the course of dimensionality reduction. An experimental comparison with known kNN implementations using kd-trees was performed using test and real-life data.     

Detection of T2 changes in an early mouse brain tumor

The aim of the study was to determine the effect of early tumor growth on T₂ relaxation times in an experimental glioma model. A 9.4-T magnetic resonance imaging (MRI) system was used for the investigations. An animal model (n=12) of glioma was established using an intracranial inoculation of U87MGdEGFRvIII cells. The imaging studies were performed from Day 10 through Day 13 following tumor inoculation. Tumor blood vessel density was determined using quantitative immunochemistry. Tumor volume was measured daily using MR images. T₂ values of the tumor were measured in five areas across the tumor and calculated using a single exponential fitting of the echo train. The measurements on Days 10 and 13 after tumor inoculation showed a 20% increase in T₂. The changes in T₂ correlated with the size of the tumor. Statistically significant differences in T₂ values were observed between the edge of the tumor and the brain tissue on Days 11, 12 and 13 (P=.014, .008, .001, respectively), but not on Day 10 (P=.364). The results show that T₂-weighted MRI may not detect glioma during an early phase of growth. T₂ increases in growing glioma and varies heterogenously across the tumor.     

Oxygen-induced MR signal changes in murine tumors

Breathing of 100% oxygen was used to challenge vascular autoregulation in 14 mice with either osteosarcomas (n = 6) or mammary carcinomas (n = 8). Reproducible and statistically significant signal intensity changes of –29 ± 6% to +35 ± 3% were observed on heavily T₂1-weighted images in the tumors during the oxygen challenge. No significant changes were observed in muscle. For the mammary carcinomas a higher percentage of tumor voxels showed significant signal-intensity decrease (31 ± 8%) compared to the percentage of voxels showing a signal-intensity increase (22 ± 3%). In contrast, for the osteosarcomas, a higher percentage of tumor voxels showed signal-intensity increase (52 ± 9%) compared to the percentage of voxels showing signal-intensity decrease (27 ± 9%). The regional distribution of these signal intensity changes did not correlate with the signal pattern on T₁-, T₂-,and T₂1-weighted and Gd-DTPA enhanced images acquired without breathing 100% oxygen. Most likely, the signal intensity changes represented the inability of the tumor’s neovascularization for autoregulation during the oxygen challenge, particularly in hypoxic regions. Although further investigation is needed, the findings that malignant tumor tissue showed signal intensity changes, whereas normal muscle tissue did not, suggests that this technique may prove useful in distinguishing benign from malignant tissue.     

Multispectral MR images segmentation based on fuzzy knowledge and modified seeded region growing

Magnetic resonance imaging (MRI) is a valuable diagnostic tool in medical science due to its capability for soft-tissue characterization and three-dimensional visualization. One potential application of MRI in clinical practice is brain parenchyma classification and segmentation. Based on fuzzy knowledge and modified seeded region growing, this work proposes a novel image segmentation method, called Fuzzy Knowledge-Based Seeded Region Growing (FKSRG), for multispectral MR images. In this work, fuzzy knowledge includes the fuzzy edge, fuzzy similarity and fuzzy distance, which are obtained from relationships between pixels in multispectral MR images and are applied to the modified seeded regions growing process. In conventional regions merging, the final number of regions is unknown. Therefore, a Target Generation Process is proposed and applied to support conventional regions merging, such that the FKSRG method does not over- or undersegment images. Finally, two image sets, namely, computer-generated phantom images and real MR images, are used in experiments to assess the effectiveness of the proposed FKSRG method. Experimental results demonstrate that the FKSRG method segments multispectral MR images much more effectively than the Functional MRI of the Brain Automated Segmentation Tool, K-means and Support Vector Machine methods.     

Utililization of experimental animal model for correlative multispectral MRI and pathological analysis of brain tumors

Magnetic resonance imaging is the method of choice for non-invasive detection and evaluation of tumors of the central nervous system. However, discrimination of tumor boundaries from normal tissue, and the evaluation of heterogeneous lesions have proven to be limitations in traditional magnetic resonance imaging. The use of post-image acquisition processing techniques, such as multispectral tissue segmentation analysis, may provide more accurate clinical information. In this report, we have employed an experimental animal model for brain tumors induced by glial cells transformed by the human neurotropic JC virus to examine the utility of multispectral tissue segmentation for tumor cell identification. Six individual tissue types were discriminated by segmentation analysis, including heterogeneous tumor tissue, a clear demarcation of the boundary between tumor and non-tumor tissue, deep and cortical gray matter, and cerebrospinal fluid. Furthermore, the segmentation analysis was confirmed by histopathological evaluation. The use of multispectral tissue segmentation analysis may optimize the non-invasive determination and volumetric analysis of CNS neoplasms, thus providing improved clinical evaluation of tumor growth and evaluation of the effectiveness of therapeutic treatments.     

Assessment of acute myocardial infarction in man with magnetic resonance imaging and the use of a new paramagnetic contrast agent gadolinium-bopta

To assess the feasibility of and characterize the new paramagnetic contrast agent gadolinium-BOPTA/dimeglumine (Gd-BOPTA) to detect acute myocardial infarctions with MR imaging, 24 patients (53.3 ± 8.3 yr) were examined 9.3 ± 3.6 days after a first myocardial infarction. Short-axis T₁-weighted and T₂-weighted MR imaging was performed at three slice levels. T₁-weighted images were obtained before, immediately after, 15, 30, and 45 min after injection. Patients received either 0.05 or 0.1 mmol/kg body weight Gd-BOPTA. Images were qualitatively and quantitatively analyzed. Two patients showed no signs of infarction on T₂-weighted images as opposed to contrast-enhanced T₁-weighted images. Contrast-to-noise ratio was not affected by the dosage level. Signal intensity (SI) of normal to infarcted myocardium was significantly improved by both dosages (p < .0005) but a dosage of 0.05 mmol/kg produced significantly higher SI inf/norm (1.42 ± 0.07 vs. 1.34 ± 0.06, respectively, p = .015). SI of normal and infarcted myocardium enhanced immediately after administration of 0.05 mmol/kg (29.3 ± 5.1% and 53.8 ± 9.6% respectively), which decreased thereafter to 5.3 ± 4.8% and 40.2 ± 8.5% respectively, at 45 min (p < .002 for normal myocardium). SI enhancement immediately after 0.1 mmol/kg Gd-BOPTA showed no decrease within the first 45 min. Gd-BOPTA enables the detection of myocardial infarction. Optimal infarct delineation is achieved from 15 to 45 min after administration of 0.05 mmol/kg body weight Gd-BOPTA. Gd-BOPTA at 0.05 mmol/kg does improve image quality as measured by contrast-to-noise ratio and SI enhancement as compared to 0.10 mmol/kg.     

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.     

Magnetic Resonance Imaging of Rat C6 Glioma Model Enhanced by Using Water-Soluble Gadolinium Fullerene

Water-soluble gadofullerene Gd@Ful with composition Gd³⁺@C₈₂(OH) _X ^3– (x ~ 20) was synthesized for theranostic study. Nanosuspensions of Gd@Ful were used for magnetic relaxation measurements in vitro and for magnetic resonance imaging of a rat with intracranially implanted C6 glioma. Gd@Ful was shown to reduce proton relaxation times in vitro and provide dual contrast of T ₁- and T ₂-weighted images in a rat brain tumor model after paramagnetic intravenous delivery. Magnetic relaxation times of water protons under action of Gd@Ful were strongly shortened due to cluster formation and increase of motional correlation times of protons in the vicinity of the fullerene cage. The Gd@Ful administration promoted the improvement of glioma contrast enhancement at T ₂-weighted images due to accumulation of paramagnetic substance at the tumor site. The contrast efficiency of Gd@Ful corresponds to the characteristics of negative contrast agent. The Gd@Ful nanosuspension is shown to be a contrast enhancer with high anti-tumor therapeutic potency. The retention of the Gd@Ful in the tumor resulted in a 75 % increase in survival times of the tumor-bearing animals.     

Whole volume brain extraction for multi-centre,multi-disease FLAIR MRI datasets

Automatic segmentation of the brain from magnetic resonance images (MRI) is a fundamental step in many neuroimaging processing frameworks. There are mature technologies for this task for T1- and T2-weighted MRI; however, a widely-accepted brain extraction method for Fluid-Attenuated Inversion Recovery (FLAIR) MRI has yet to be established. FLAIR MRI are becoming increasingly important for the analysis of neurodegenerative diseases and tools developed for this sequence would have clinical value. To maximize translation opportunities and for large scale research studies, algorithms for brain extraction in FLAIR MRI should generalize to multi-centre (MC) data. To this end, this work proposes a fully automated, whole volume brain extraction methodology for MC FLAIR MRI datasets. The framework is built using a novel standardization framework which reduces acquisition artifacts, standardizes the intensities of tissues and normalizes the spatial coordinates of brain tissue across MC datasets. Using the standardized datasets, an intuitive set of features based on intensity, spatial location and gradients are extracted and classified using a random forest (RF) classifier to segment the brain tissue class. A series of experiments were conducted to optimize classifier parameters, and to determine segmentation accuracy for standardized and unstandardized (original) data, as a function of scanner vendor, feature type and disease type. The models are trained, tested and validated on 156 image volumes (∼8000 image slices) from two multi-centre, multi-disease datasets, acquired with varying imaging parameters from 30 centres and three scanner vendors. The image datasets, denoted as CAIN and ADNI for vascular and dementia disease, respectively, represent a diverse collection of MC data to test the generalization capabilities of the proposed design. Results demonstrate the importance of standardization for segmentation of MC data, as models trained on standardized data yielded a drastic improvement in brain extraction accuracy compared to the original, unstandardized data (CAIN: DSC = 91% and ADNI: DSC = 86% vs. CAIN: 78% and ADNI: 65%). It was also found that models created from one scanner vendor based on unstandardized data yielded poor segmentation results in data acquired from other scanner vendors, which was improved through standardization. These results demonstrate that to create consistency in segmentations from multi-institutional datasets it is paramount that MC variability be mitigated to improve stability and to ensure generalization of machine learning algorithms for MRI.