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.     

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.     

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.     

Tissue classification and segmentation of MR images

Previously reported classification or segmentation methods are reviewed, and some statistical approaches that may be capable of automatically classifying tissues and segmenting magnetic resonance (MR) images are discussed. The image segmentation methods reviewed are edge detection methods and region detection methods. The key feature of statistical approaches toward automatically classifying tissues and segmenting MR images is the determination of the number of image classes and the model parameters of these classes from the image data directly by a computer. Any free parameter requiring extensive user interactions should be avoided. Further research on the Gaussian Markov random field (GMRF) model and the MRF penalty term will push the statistical approaches further along the automatic track. As these approaches become more practical they will become more valuable     

Tissue segmentation: a crucial tool for quantitative MRI and visualization of anatomical structures

Automatic or semi-automatic segmentation of tissue types or organs is well established for X-ray-based computed tomography, with its fixed grey-scale and tissue classes with well-established ranges of Hounsfield units. MRI is much more powerful with regard to soft tissue contrast and quantitative assessment of tissue properties (e.g., perfusion, diffusion, fat content), but the principle of signal generation and recording in MRI leads to inherent problems if simple threshold based segmentation procedures are applied. In this editorial in the special issue of MAGMA on tissue segmentation, a number of relevant methodical, scientific, and clinical aspects of reliable tissue segmentation using data recording by MRI are reported and discussed.     

2D sense for faster 3D MRI

Sensitivity encoding in two spatial dimensions (2D SENSE) with a receiver coil array is discussed as a means of improving the encoding efficiency of three-dimensional (3D) Fourier MRI. it is shown that in Fourier imaging with two phase encoding directions, 2D SENSE has key advantages over one-dimensional parallel imaging approaches. By exploiting two dimensions for hybrid encoding, the conditioning of the reconstruction problem can be considerably improved, resulting in superior signal-to-noise behavior. As a consequence, 2D SENSE permits greater scan time reduction, which particularly benefits the inherently time-consuming 3D techniques. Along with the principles of 2D SENSE imaging, the properties of the technique are discussed and investigated by means of simulations. Special attention is given to the role of the coil configuration, yielding practical setups with four and six coils. The in vivo feasibility of the two-dimensional approach is demonstrated for 3D head imaging, permitting four-fold scan time reduction. Presented in parts at the 16th meeting of the ESMRMB, Sevilla, September, 1999.     

Two-dimensional MR spectroscopy of healthy and cancerous prostates in vivo

Objectives  A major goal of this article is to summarize the current status of evaluating prostate metabolites non-invasively using spatially resolved two-dimensional (2D) MR Spectroscopy (MRS). Materials and Methods  Due to various technical challenges, the spatially resolved versions of 2D MRS techniques are currently going through the developmental stage. During the last decade, four different versions of 2D MRS sequences have been successfully implemented on 3T and 1.5T MRI scanners manufactured by three different vendors. These sequences include half and maximum echo sampled J-resolved spectroscopy (JPRESS), S-PRESS and L-COSY, which are single volume localizing sequences, and the multi-voxel based JPRESS sequence. Results  Even though greater than 1ml voxels have been used, preliminary evaluations of 2D JPRESS, S-PRESS and L-COSY sequences have demonstrated unambiguous detection of citrate, creatine, choline, spermine and more metabolites in human prostates. ProFIT-based quantitation of JPRESS and L-COSY data clearly shows the superiority of 2D MRS over conventional one-dimensional (1D) MRS and more than six metabolites have been successfully quantified. These sequences have been evaluated in a small group of prostate pathologies and pilot investigations using these sequences show promising results in prostate pathologies. Conclusion  Implementation of the state-of-the-art 2D MRS techniques and preliminary evaluation in prostate pathologies are discussed in this review. Even though these techniques are going through developmental and early testing phases, it is evident that 2D MRS can be easily added on to any clinical Magnetic Resonance Imaging (MRI) protocol to non-invasively record the biochemical contents of the prostate.     

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     

Segmentation of the human spinal cord

Segmenting the spinal cord contour is a necessary step for quantifying spinal cord atrophy in various diseases. Delineating gray matter (GM) and white matter (WM) is also useful for quantifying GM atrophy or for extracting multiparametric MRI metrics into specific WM tracts. Spinal cord segmentation in clinical research is not as developed as brain segmentation, however with the substantial improvement of MR sequences adapted to spinal cord MR investigations, the field of spinal cord MR segmentation has advanced greatly within the last decade. Segmentation techniques with variable accuracy and degree of complexity have been developed and reported in the literature. In this paper, we review some of the existing methods for cord and WM/GM segmentation, including intensity-based, surface-based, and image-based methods. We also provide recommendations for validating spinal cord segmentation techniques, as it is important to understand the intrinsic characteristics of the methods and to evaluate their performance and limitations. Lastly, we illustrate some applications in the healthy and pathological spinal cord. One conclusion of this review is that robust and automatic segmentation is clinically relevant, as it would allow for longitudinal and group studies free from user bias as well as reproducible multicentric studies in large populations, thereby helping to further our understanding of the spinal cord pathophysiology and to develop new criteria for early detection of subclinical evolution for prognosis prediction and for patient management. Another conclusion is that at the present time, no single method adequately segments the cord and its substructure in all the cases encountered (abnormal intensities, loss of contrast, deformation of the cord, etc.). A combination of different approaches is thus advised for future developments, along with the introduction of probabilistic shape models. Maturation of standardized frameworks, multiplatform availability, inclusion in large suite and data sharing would also ultimately benefit to the community.     

Recent advances in image reconstruction, coil sensitivity calibration, and coil array design for SMASH and generalized parallel MRI

Parallel magnetic resonance imaging (MRI) techniques use spatial information from arrays of radiofrequency (RF) detector coils to accelerate imaging. A number of parallel MRI techniques have been described in recent years, and numerous clinical applications are currently being explored. The advent of practical parallel imaging presents various challenges for image reconstruction and RF system design. Recent advances in tailored SiMultaneous Acquisition of Spatial Harmonics (SMASH) image reconstructions are summarized. These advances enable robust SMASH imaging in arbitrary image planes with a wide range of coil array geometries. A generalized formalism is described which may be used to understand the relations between SMASH and SENSE, to derive typical implementations of each as special cases, and to form hybrid techniques combining some of the advantages of both. Accurate knowledge of coil sensitivities is crucial for parallel MRI, and errors in calibration represent one of the most common and the most pernicious sources of error in parallel image reconstructions. As one example, motion of the patient and or the coil array between the sensitivity reference scan and the accelerated acquisition can lead to calibration errors and reconstruction artifacts. Self-calibrating parallel MRI approaches that address this problem by eliminating the need for external sensitivity references are reviewed. The ultimate achievable signal-to-noise ratio (SNR) for parallel MRI studies is closely tied to the geometry and sensitivity patterns of the coil arrays used for spatial encoding. Several parallel imaging array designs that depart from the traditional model of overlapped adjacent loop elements are described. Summary of material presented at the 2001 ISMRM workshop on MRI hardware, Cleveland, OH, USA.     

Recent advances in image reconstruction, coil sensitivity calibration, and coil array design for SMASH and generalized parallel MRI.

Parallel magnetic resonance imaging (MRI) techniques use spatial information from arrays of radiofrequency (RF) detector coils to accelerate imaging. A number of parallel MRI techniques have been described in recent years, and numerous clinical applications are currently being explored. The advent of practical parallel imaging presents various challenges for image reconstruction and RF system design. Recent advances in tailored SiMultaneous Acquisition of Spatial Harmonics (SMASH) image reconstructions are summarized. These advances enable robust SMASH imaging in arbitrary image planes with a wide range of coil array geometries. A generalized formalism is described which may be used to understand the relations between SMASH and SENSE, to derive typical implementations of each as special cases, and to form hybrid techniques combining some of the advantages of both. Accurate knowledge of coil sensitivities is crucial for parallel MRI, and errors in calibration represent one of the most common and the most pernicious sources of error in parallel image reconstructions. As one example, motion of the patient and/or the coil array between the sensitivity reference scan and the accelerated acquisition can lead to calibration errors and reconstruction artifacts. Self-calibrating parallel MRI approaches that address this problem by eliminating the need for external sensitivity references are reviewed. The ultimate achievable signal-to-noise ratio (SNR) for parallel MRI studies is closely tied to the geometry and sensitivity patterns of the coil arrays used for spatial encoding. Several parallel imaging array designs that depart from the traditional model of overlapped adjacent loop elements are described.     

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.     

7 T renal MRI: challenges and promises

The progression to 7 Tesla (7 T) magnetic resonance imaging (MRI) yields promises of substantial increase in signal-to-noise (SNR) ratio. This increase can be traded off to increase image spatial resolution or to decrease acquisition time. However, renal 7 T MRI remains challenging due to inhomogeneity of the radiofrequency field and due to specific absorption rate (SAR) constraints. A number of studies has been published in the field of renal 7 T imaging. While the focus initially was on anatomic imaging and renal MR angiography, later studies have explored renal functional imaging. Although anatomic imaging remains somewhat limited by inhomogeneous excitation and SAR constraints, functional imaging results are promising. The increased SNR at 7 T has been particularly advantageous for blood oxygen level-dependent and arterial spin labelling MRI, as well as sodium MR imaging, thanks to changes in field-strength-dependent magnetic properties. Here, we provide an overview of the currently available literature on renal 7 T MRI. In addition, we provide a brief overview of challenges and opportunities in renal 7 T MR imaging.     

Automatic MRI adipose tissue mapping using overlapping mosaics

This paper presents an automatic method of correcting non-uniform RF coil response for the classification of body composition using MR imaging. By linear mosaic modelling, the smoothly but non-linearly varying bias field, which modulates tissue intensities within the image, was corrected. The overlapping between adjacent mosaics ensured consistent segmentation of body fat content and the effectiveness of the technique was validated by both phantom and in vivo experiments. Ten whole body composition data sets, each with 39 trans-axial slices, were acquired. Automatic segmentation results using the proposed technique were compared with those from manual delineations. The automatic segmentation method was found to be highly accurate and the mean percentage error between the two methods was less than 1.5%.     

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.     

基于几何仿射与注意力的三维激光点云分类

三维点云分类和分割对于三维重建和自动驾驶等技术的发展具有积极的推动作用。三维点云数据具有无序、不规则和稀疏等特点，因此三维点云分类和分割的研究面临诸多挑战。PCT分类网络采用标量注意力机制提取三维点云局部特征，具有良好的三维点云特征学习能力，在三维点云分类和分割任务中表现出先进的分类精度。然而PCT在对三维点云数据进行下采样时忽视了其稀疏性对几何结构所产生的影响，从而无法充分地提取局部特征致使三维点云分类和分割精度下降。针对该问题，本文提出一种基于注意力机制的三维点云分类分割网络GAM-PCT，具体地，GAM-PCT网络采用了向量注意力机制对单通道特征的权重进行调节，利用减法关系和邻域位置编码对三维点云邻域求取注意力特征，同时在对整体点云下采样时插入即插即用的几何形状仿射（GAM）模块来解决三维点云局部区域的稀疏性问题，进而提升网络的分类准确率。实验结果表明，与PCT三维点云分类和分割网络相比，所提出GAM-PCT网络在数据集ModelNet40上的分类精度提升了0.3%，而在ScanObjectNN数据集上的分类精度提升了1.9%，在ShapeNet数据集上的分割平均交并比值提升了0.2%。同时在网络参数量和FLOPs指标上分别降低了0.31 G和0.69 M。实验结果表明改进后网络的复杂度得到了简化，充分验证了改进方法的有效性。     

肝脏MR图像的初步分割

为实现肝脏磁共振（Magnetic Resonance,MR）图像分割,在四叉树分裂方法的基础上,通过删除一J、区块和填充孔洞的操作,得到初步的MR图像分割结果。处理结果表明该方法的可行性,并为后续的精确分割奠定基础。     

MR imaging of the prostate in clinical practice

Magnetic resonance imaging (MRI) is the imaging tool of choice in the evaluation of prostate cancer. The main applications of MR imaging in the management of prostate cancer are: (1) to guide targeted biopsy when prostate cancer is clinically suspected and previous ultrasound-guided biopsy results are negative; (2) to localize and stage prostate cancer and provide a roadmap for treatment planning; and (3) to detect residual or locally recurrent cancer after treatment. Other MR techniques such as proton MR spectroscopic imaging (MRSI), diffusion-weighted imaging (DWI), and contrast-enhanced MRI (CE-MRI) complement conventional MR imaging by providing metabolic and functional information that can improve the accuracy of prostate cancer detection and characterization. In everyday clinical practice, and to account for patient comfort, MR imaging studies are limited to 1 h. To obtain consistently high-quality images, a well-designed protocol is necessary. Routine MR imaging can be supplemented by other MR techniques such as MRSI, DWI or CE-MRI depending on the expertise available and the clinical questions that need to be answered. This review summarizes the role of MR imaging in the management of prostate cancer and describes practical approaches to implementing anatomic, metabolic and functional MR imaging techniques in the clinic.     

A PC-based workstation for processing and analysis of MRI data

The present work demonstrates that a low cost, flexible and user-friendly workstation for the MRI laboratory can be implemented by using a personal computer and public-domain software. The workstation is based on a Pentium^® personal computer, operating under the Linux operative system, and uses the software Khoros^® (Khoral Research, Albuquerque, NM). This software is a general purpose package for handling signals and we here report its suitability for MR images analysis. Khoros^® allows to create workspaces where different procedures (also written by the users) can be combined for implementing more complex procedures. We created workspaces for obtaining 2D and 3D images from time domain data which also allow for apodization and zero-filling. The time required for a 3D-FFT (matrix size 128×128×128) is about 12 min with the presently used microprocessor. We have also created workspaces for calculating apparent diffusion coefficient maps and for segmentation of MR images. Our results demonstrate that a personal computer equipped with public-domain software can represent a powerful tool to fulfil the MRI laboratory common needs.     

On spatially selective RF excitation and its analogy with spiral MR image acquisition

The basic principles of the design of spatially selective RF pulses are described, and their analogy with MR image acquisition and reconstruction is shown. The paper focuses on RF-pulse design and imaging schemes in which spiral k-space trajectories are used. The sensitivity of RF excitation to gradient-system imperfections and to spatially varying off-resonance are analyzed, and suitable measures of correction are discussed. The spatial resolution obtainable with selective RF pulses and the consequences of the linearity of the pulse-design problem are examined. Phantom experiments showing the performance of multidimensional spatially selective RF pulses further illustrate the analogy with MR image acquisition.