Segmentation and quantification of adipose tissue by magnetic resonance imaging

In this brief review, introductory concepts in animal and human adipose tissue segmentation using proton magnetic resonance imaging (MRI) and computed tomography are summarized in the context of obesity research. Adipose tissue segmentation and quantification using spin relaxation-based (e.g., T1-weighted, T2-weighted), relaxometry-based (e.g., T1-, T2-, T2*-mapping), chemical-shift selective, and chemical-shift encoded water–fat MRI pulse sequences are briefly discussed. The continuing interest to classify subcutaneous and visceral adipose tissue depots into smaller sub-depot compartments is mentioned. The use of a single slice, a stack of slices across a limited anatomical region, or a whole body protocol is considered. Common image post-processing steps and emerging atlas-based automated segmentation techniques are noted. Finally, the article identifies some directions of future research, including a discussion on the growing topic of brown adipose tissue and related segmentation considerations.     

Principles and methods for automatic and semi-automatic tissue segmentation in MRI data

The development of magnetic resonance imaging (MRI) revolutionized both the medical and scientific worlds. A large variety of MRI options have generated a huge amount of image data to interpret. The investigation of a specific tissue in 3D or 4D MR images can be facilitated by image processing techniques, such as segmentation and registration. In this work, we provide a brief review of the principles and methods that are commonly applied to achieve superior tissue segmentation results in MRI. The impacts of MR image acquisition on segmentation outcome and the principles of selecting and exploiting segmentation techniques tailored for specific tissue identification tasks are discussed. In the end, two exemplary applications, breast and fibroglandular tissue segmentation in MRI and myocardium segmentation in short-axis cine and real-time MRI, are discussed to explain the typical challenges that can be posed in practical segmentation tasks in MRI data. The corresponding solutions that are adopted to deal with these challenges of the two practical segmentation tasks are thoroughly reviewed.     

Segmentation of joint and musculoskeletal tissue in the study of arthritis

As the most frequent cause of physical disability, musculoskeletal diseases such as arthritis and osteoporosis have a great social and economical impact. Quantitative magnetic resonance imaging (MRI) biomarkers are important tools that allow clinicians to better characterize, monitor, and even predict musculoskeletal disease progression. Post-processing pipelines often include image segmentation. Manually identifying the border of the region of interest (ROI) is a difficult and time-consuming task. Manual segmentation is also affected by inter- and intrauser variability, thus limiting standardization. Fully automatic or semi-automatic methods that minimize the user interaction are highly desirable. Unfortunately, an ultimate, highly reliable and extensively evaluated solution for joint and musculoskeletal tissue segmentation has not yet been proposed, and many clinical studies still adopt fully manual procedures. Moreover, the clinical translation of several promising quantitative MRI techniques is highly affected by the lack of an established, fast, and accurate segmentation method. The goal of this review is to present some of the techniques proposed in recent literature that have been adopted in clinical studies for joint and musculoskeletal tissue analyses in arthritis patients. The most widely used MRI sequences and image processing algorithms employed to accomplish segmentation challenges will be discussed in this paper.     

Real-time direct volume rendering in functional magnetic resonance imaging

Direct volume rendering is a visualization method that allows display of all information hidden in three-dimensional data sets of, for example, computed tomography or magnetic resonance imaging (MRI). In contrast to commonly used surface rendering methods, these algorithms need no preprocessing but suffer from a high computational complexity. A real-time rendering system, VIRIM (Vitec: Visualization Technology GmbH, Mannheim, Germany), cuts down rendering times of minutes on normal workstations to an interactive rate of 1 second or less. The immediate visual feedback allows interactive steering of the visualization process to achieve insight into the internal three-dimensional structure of objects. Additional information is obtained by using an interactive gray-value segmentation tool that both allows segmentation of the data set according to bone, tissue, and liquor and display of multifunctional data sets (e.g., functional MRI [fMRI] data sets). Thus, real-time direct volume rendering allows segmentation and volume data processing of functional and anatomical MR data sets simultaneously. As this method can be integrated in the clinical routine, it is of great importance for real-time motion artifact detection and the interpretation of fMRI data acquired during cognitive experiments with normal subjects and psychiatric patients. Because of the free programmability of VIRIM, more complex matching procedures are currently being investigated for future implementation.     

Validation of an active shape model-based semi-automated segmentation algorithm for the analysis of thigh muscle and adipose tissue cross-sectional areas

Objective

To validate a semi-automated method for thigh muscle and adipose tissue cross-sectional area (CSA) segmentation from MRI.

Materials and methods

An active shape model (ASM) was trained using 113 MRI CSAs from the Osteoarthritis Initiative (OAI) and combined with an active contour model and thresholding-based post-processing steps. This method was applied to 20 other MRIs from the OAI and to baseline and follow-up MRIs from a 12-week lower-limb strengthening or endurance training intervention (n = 35 females). The agreement of semi-automated vs. previous manual segmentation was assessed using the Dice similarity coefficient and Bland-Altman analyses. Longitudinal changes observed in the training intervention were compared between semi-automated and manual segmentations.

Results

High agreement was observed between manual and semi-automated segmentations for subcutaneous fat, quadriceps and hamstring CSAs. With strength training, both the semi-automated and manual segmentation method detected a significant reduction in adipose tissue CSA and a significant gain in quadriceps, hamstring and adductor CSAs. With endurance training, a significant reduction in adipose tissue CSAs was observed with both methods.

Conclusion

The semi-automated approach showed high agreement with manual segmentation of thigh muscle and adipose tissue CSAs and showed longitudinal training effects similar to that observed using manual segmentation.

     

MRI for attenuation correction in PET: methods and challenges

In current combined PET/MR systems, PET attenuation correction is based on MRI, since the small bore inside MRI systems and the strong magnetic field do not permit a rotating PET transmission source or a CT device to be integrated. Unlike CT measurements in PET/CT scanners, the MR signal is not directly correlated to tissue density and thus cannot be converted by a simple transformation of intensity values. Various approaches have been developed based on templates, atlas information, direct segmentation of T1-weighted MR images, or segmentation of images from special MR sequences. The advantages and disadvantages of these approaches as well as additional challenges will be discussed in this review.     

Overestimation of grey matter atrophy in glioblastoma patients following radio(chemo)therapy

Objective

Brain atrophy has the potential to become a biomarker for severity of radiation-induced side-effects. Particularly brain tumour patients can show great MRI signal changes over time caused by e.g. oedema, tumour progress or necrosis. The goal of this study was to investigate if such changes affect the segmentation accuracy of normal appearing brain and thus influence longitudinal volumetric measurements.

Materials and methods

T1-weighted MR images of 52 glioblastoma patients with unilateral tumours acquired before and three months after the end of radio(chemo)therapy were analysed. GM and WM volumes in the contralateral hemisphere were compared between segmenting the whole brain (full) and the contralateral hemisphere only (cl) with SPM and FSL. Relative GM and WM volumes were compared using paired t tests and correlated with the corresponding mean dose in GM and WM, respectively.

Results

Mean GM atrophy was significantly higher for full segmentation compared to cl segmentation when using SPM (mean ± std: ΔV_GM,full = − 3.1% ± 3.7%, ΔV_GM,cl = − 1.6% ± 2.7%; p < 0.001, d = 0.62). GM atrophy was significantly correlated with the mean GM dose with the SPM cl segmentation (r = − 0.4, p = 0.004), FSL full segmentation (r = − 0.4, p = 0.004) and FSL cl segmentation (r = -0.35, p = 0.012) but not with the SPM full segmentation (r = − 0.23, p = 0.1).

Conclusions

For accurate normal tissue volume measurements in brain tumour patients using SPM, abnormal tissue needs to be masked prior to segmentation, however, this is not necessary when using FSL.

     

Deep learning for automatic segmentation of thigh and leg muscles

Objective

In this study we address the automatic segmentation of selected muscles of the thigh and leg through a supervised deep learning approach.

Material and methods

The application of quantitative imaging in neuromuscular diseases requires the availability of regions of interest (ROI) drawn on muscles to extract quantitative parameters. Up to now, manual drawing of ROIs has been considered the gold standard in clinical studies, with no clear and universally accepted standardized procedure for segmentation. Several automatic methods, based mainly on machine learning and deep learning algorithms, have recently been proposed to discriminate between skeletal muscle, bone, subcutaneous and intermuscular adipose tissue. We develop a supervised deep learning approach based on a unified framework for ROI segmentation.

Results

The proposed network generates segmentation maps with high accuracy, consisting in Dice Scores ranging from 0.89 to 0.95, with respect to “ground truth” manually segmented labelled images, also showing high average performance in both mild and severe cases of disease involvement (i.e. entity of fatty replacement).

Discussion

The presented results are promising and potentially translatable to different skeletal muscle groups and other MRI sequences with different contrast and resolution.

     

Challenges of imaging structure and function with MRI

Deals with current image reconstruction and processing issues in MRI for the study of tissue structure and function. In image reconstruction, the authors discuss the need for new algorithms that can produce high-resolution images with good signal-to-noise ratio from reduced amounts of data. In image processing, the authors describe outstanding problems in automatic image registration and segmentation     

Automated assessment of thigh composition using machine learning for Dixon magnetic resonance images

Objectives

To develop and validate a machine learning based automated segmentation method that jointly analyzes the four contrasts provided by Dixon MRI technique for improved thigh composition segmentation accuracy.

Materials and methods

The automatic detection of body composition is formulized as a three-class classification issue. Each image voxel in the training dataset is assigned with a correct label. A voxel classifier is trained and subsequently used to predict unseen data. Morphological operations are finally applied to generate volumetric segmented images for different structures. We applied this algorithm on datasets of (1) four contrast images, (2) water and fat images, and (3) unsuppressed images acquired from 190 subjects.

Results

The proposed method using four contrasts achieved most accurate and robust segmentation compared to the use of combined fat and water images and the use of unsuppressed image, average Dice coefficients of 0.94 ± 0.03, 0.96 ± 0.03, 0.80 ± 0.03, and 0.97 ± 0.01 has been achieved to bone region, subcutaneous adipose tissue (SAT), inter-muscular adipose tissue (IMAT), and muscle respectively.

Conclusion

Our proposed method based on machine learning produces accurate tissue quantification and showed an effective use of large information provided by the four contrast images from Dixon MRI.

     

基于MRF的膝关节半月板快速自动分割算法

核磁共振成像（magnetic resonance imaging,MRI）图像形态、纹理均较为复杂,从图像中分割出感兴趣组织结构具有一定难度。提出一种＂分割-粗定位-提取＂思路,充分利用MRI成像特征和膝关节解剖学的先验知识,快速、全自动地精确分割形态复杂、尺寸细小的膝关节半月板：首先利用多尺度马尔可夫随机场（Markov random field,MRF）方法自动、快速地分割与目标有相似灰度分布的组织结构,然后结合sobel算子和直方图投影方法粗定位半月板区域,最后通过判断连通区域面积提取出精确的半月板区域。实验结果表明,与目前手动、半自动的半月板分割等研究工作相比,可以客观可重复地分割出半月板前后角等区域,并且算法耗时极低。     

基于自组织小波神经网络的磁共振图像分割方法

磁共振图像的准确分割对于辅助医生确定病灶的位置和形状、制订治疗方案和评价治疗效果具有重要的意义。本文提出了一种新的磁共振图像（MRI）分割方法。构造了一种自组织小波神经网络,通过融合T1、r12和Pd图像的特征来识别MRI中生物组织的类别。该网络继承了小波分析局部精度高和神经网络自学习能力强的优点,采用自组织算法利用训练数据的稀疏性对网络的结构和初始参数进行优化,简化了网络结构,提高了网络学习的速度,避免了网络陷入局部最优学习。将所提方法应用于大脑磁共振图像分割的实验结果表明,所设计的自组织小波神经网络MRI图像分割方法具有精度高和学习速度快的优点。     

Brain tumor evaluation and segmentation by in vivo proton spectroscopy and relaxometry

A new methodology has been developed for the evaluation and segmentation of brain tumors using information obtained by different magnetic resonance techniques such as in vivo proton magnetic resonance spectroscopy (¹HMRS) and relaxometry. In vivo ¹HMRS may be used as a preoperative technique that allows noninvasive monitoring of metabolites to identify the different tissue types present in the lesion (active tumor, necrotic tissue, edema, and normal or non-affected tissue). Spatial resolution for treatment consideration may be improved by using ¹HMRS combined or fused with images obtained by relaxometry which exhibit excellent spatial resolution. Some segmentation schemes are presented and discussed. The results show that segmentation performed in this way efficiently determines the spatial localization of the tumor both qualitatively and quantitatively. It provides appropriate information for therapy planning and application of therapies such as radiosurgery or radiotherapy and future control of patient evolution.     

结合分水岭算法和WKFCM算法的MRI图像分割

针对传统分水岭算法对MRI图像过分割的缺点,提出了一种基于分水岭算法和改进核聚类算法的MRI图像分割新方法.首先,通过传统的分水岭分割算法将MRI图像分割成不同的区域,然后根据改进的核聚类算法,利用Mercer核将各个区域的平均灰度值映射到高维特征空间,使得原来未显示出来的特征显现出来.这样就可以实现更准确的聚类,用灰...     

基于梯度分割的磁光记录薄膜磁畴图像特征提取

提出了一种基于梯度分割的图像特征提取方法,对低对比度磁光记录薄膜磁畴图像进行处理.该方法采用如下三个步骤:首先,采用Lee滤波器进行预滤波和消除噪声;接下来进行梯度特征分割,将目标区域从背景中提取出来;最后对边缘进行连接并计算磁畴的特性参数.本文重点在于梯度特征分割方法.     

Monitoring the survival of islet transplants by MRI using a novel technique for their automated detection and quantification

Object  There is a clinical need to be able to assess graft loss of transplanted pancreatic islets (PI) non-invasively with clear-cut quantification of islet survival. We tracked transplanted PI in diabetic mice during the early post-transplant period by magnetic resonance imaging (MRI) and quantified the islet loss using automatic segmentation technique. Materials and methods  Magnetically labeled islet iso-, allo- and xenografts were injected into the right liver lobes. Animals underwent MRI scanning during 14 days after PI transplantation. MR images were processed using custom-made software, which automatically detects hypointense regions representing PI. It is based on morphological top-hat and bottom-hat transforms. Results  Manually and automatically detected areas, corresponding to PI, differed by 4% in phantoms. Signal loss regions due to PI decreased comparably in all groups during the first week post transplant. Throughout the second week post-transplant, the signal loss area continued in a steep decline in case of allografts and xenografts, whereas the decline in case of isografts slowed down. Conclusion  Automatic segmentation allows for the more reproducible, objective assessment of transplanted PI. Quantification confirms the assumption that a significant number of islets are destroyed in the first week following transplantation irrespective of allografts, xenografts or isografts.     

Magnetic resonance imaging of the pulsing brain: a systematic review

Objective

To perform a systematic review of the literature exploring magnetic resonance imaging (MRI) methods for measuring natural brain tissue pulsations (BTPs) in humans.

Methods

A prospective systematic search of MEDLINE, SCOPUS and OpenGrey databases was conducted by two independent reviewers using a pre-determined strategy. The search focused on identifying reported measurements of naturally occurring BTP motion in humans. Studies involving non-human participants, MRI in combination with other modalities, MRI during invasive procedures and MRI studies involving externally applied tests were excluded. Data from the retrieved records were combined to create Forest plots comparing brain tissue displacement between Chiari-malformation type 1 (CM-I) patients and healthy controls using an independent samples t-test.

Results

The search retrieved 22 eligible articles. Articles described 5 main MRI techniques for visualisation or quantification of intrinsic brain motion. MRI techniques generally agreed that the amplitude of BTPs varies regionally from 0.04 mm to ~ 0.80 mm, with larger tissue displacements occurring closer to the centre and base of the brain compared to peripheral regions. Studies of brain pathology using MRI BTP measurements are currently limited to tumour characterisation, idiopathic intracranial hypertension (IIH), and CM-I. A pooled analysis confirmed that displacement of tissue in the cerebellar tonsillar region of CM-I patients was + 0.31 mm [95% CI 0.23, 0.38, p < 0.0001] higher than in healthy controls.

Discussion

MRI techniques used for measurements of brain motion are at an early stage of development with high heterogeneity across the methods used. Further work is required to provide normative data to support systematic BTPs characterisation in health and disease.

     

Volume measurements of individual muscles in human <Emphasis Type="Italic">quadriceps femoris</Emphasis> using atlas-based segmentation approaches

Objectives

Atlas-based segmentation is a powerful method for automatic structural segmentation of several sub-structures in many organs. However, such an approach has been very scarcely used in the context of muscle segmentation, and so far no study has assessed such a method for the automatic delineation of individual muscles of the quadriceps femoris (QF). In the present study, we have evaluated a fully automated multi-atlas method and a semi-automated single-atlas method for the segmentation and volume quantification of the four muscles of the QF and for the QF as a whole.

Subjects and methods

The study was conducted in 32 young healthy males, using high-resolution magnetic resonance images (MRI) of the thigh. The multi-atlas-based segmentation method was conducted in 25 subjects. Different non-linear registration approaches based on free-form deformable (FFD) and symmetric diffeomorphic normalization algorithms (SyN) were assessed. Optimal parameters of two fusion methods, i.e., STAPLE and STEPS, were determined on the basis of the highest Dice similarity index (DSI) considering manual segmentation (MSeg) as the ground truth. Validation and reproducibility of this pipeline were determined using another MRI dataset recorded in seven healthy male subjects on the basis of additional metrics such as the muscle volume similarity values, intraclass coefficient, and coefficient of variation. Both non-linear registration methods (FFD and SyN) were also evaluated as part of a single-atlas strategy in order to assess longitudinal muscle volume measurements. The multi- and the single-atlas approaches were compared for the segmentation and the volume quantification of the four muscles of the QF and for the QF as a whole.

Results

Considering each muscle of the QF, the DSI of the multi-atlas-based approach was high 0.87 ± 0.11 and the best results were obtained with the combination of two deformation fields resulting from the SyN registration method and the STEPS fusion algorithm. The optimal variables for FFD and SyN registration methods were four templates and a kernel standard deviation ranging between 5 and 8. The segmentation process using a single-atlas-based method was more robust with DSI values higher than 0.9. From the vantage of muscle volume measurements, the multi-atlas-based strategy provided acceptable results regarding the QF muscle as a whole but highly variable results regarding individual muscle. On the contrary, the performance of the single-atlas-based pipeline for individual muscles was highly comparable to the MSeg, thereby indicating that this method would be adequate for longitudinal tracking of muscle volume changes in healthy subjects.

Conclusion

In the present study, we demonstrated that both multi-atlas and single-atlas approaches were relevant for the segmentation of individual muscles of the QF in healthy subjects. Considering muscle volume measurements, the single-atlas method provided promising perspectives regarding longitudinal quantification of individual muscle volumes.

     

Comparative evaluation of active contour model extensions for automated cardiac MR image segmentation by regional error assessment

OBJECTIVE: In the field of cardiac MR image segmentation, active contour models, or snakes have been extensively used, owing to their promising results and to the numerous extensions proposed to improve their performance. This paper explores a methodology for evaluating cardiac MR image segmentation algorithms, which assesses the distance between computer-generated and the observer's hand-outlined boundaries. This metric was applied to various external force extensions of the traditional snake, since no systematic comparison has been performed. MATERIALS AND METHODS: Cardiac MRI from six patients were analyzed. Imaging was performed on a 1.5 T MR scanner with ECG-gated balanced steady-state free precession (b-SSFP) sequences. Segmentation performances were established for traditional snake, gradient vector flow snake, standard- and guided- pressure force-based snake. The use of a pre-treatment with non-linear anisotropic filtering was also compared to non-filtered images. RESULTS: Agreement between manual and segmentation algorithms was satisfactory for ejection fraction for every segmentation scheme. However end-systolic and end-diastolic volumes were systematically underestimated. CONCLUSION: The developed regional error metric provided a more rigorous evaluation of the segmentation schemes in comparison to the classical derived parameters based on left ventricle volume estimation, usually used in functional cardiac MR studies. These derived parameters can furthermore mask local segmentation errors.     

The reliability of a segmentation methodology for assessing intramuscular adipose tissue and other soft-tissue compartments of lower leg MRI images

Objective

Determine the reliability of a magnetic resonance (MR) image segmentation protocol for quantifying intramuscular adipose tissue (IntraMAT), subcutaneous adipose tissue, total muscle and intermuscular adipose tissue (InterMAT) of the lower leg.

Materials and methods

Ten axial lower leg MRI slices were obtained from 21 postmenopausal women using a 1 Tesla peripheral MRI system. Images were analyzed using sliceOmatic? software. The average cross-sectional areas of the tissues were computed for the ten slices. Intra-rater and inter-rater reliability were determined and expressed as the standard error of measurement (SEM) (absolute reliability) and intraclass coefficient (ICC) (relative reliability).

Results

Intra-rater and inter-rater reliability for IntraMAT were 0.991 (95 % confidence interval [CI] 0.978–0.996, p < 0.05) and 0.983 (95 % CI 0.958–9.993, p < 0.05), respectively. For the other soft tissue compartments, the ICCs were all >0.90 (p < 0.05). The absolute intra-rater and inter-rater reliability (expressed as SEM) for segmenting IntraMAT were 22.19 mm² (95 % CI 16.97–32.04) and 78.89 mm² (95 % CI 60.36–113.92), respectively.

Conclusion

This is a reliable segmentation protocol for quantifying IntraMAT and other soft-tissue compartments of the lower leg. A standard operating procedure manual is provided to assist users, and SEM values can be used to estimate sample size and determine confidence in repeated measurements in future research.