基于变分法的超声图像斑点噪声自适应滤波算法

各向异性扩散模型在去除超声图像斑点噪声时不能有效保护图像细节,针对上述问题本文提出基于变分法的自适应最小能量去噪模型.首先直接将由微分方程表示的各向异性扩散模型转化为最小能量变分模型;然后引入欧拉弹性能量模型,在去除噪声的同时有效地保护和增强图像细节.同时为了解决数值求解过程中出现的迭代次数与迭代步长的矛盾,本文还提出迭代停止准则和自适应变步长去噪算法.仿真和真实超声图像的实验结果表明基于变分法的超声图像斑点噪声自适应滤波算法在去噪的同时能够很好地保护细节信息,而且能有效地减少迭代次数.     

基于SOM-FCM算法的脑MR多参数图像分割

目的:提出一种新的用于脑MR多参数图像的分割算法,并对算法性能进行评估.方法:应用自组织映射(SOM)神经网络将T1加权像和T2加权像的图像信息结合后进行粗分,粗分的结果作为模糊C均值聚类(FCM)算法的输入,并加入改进的聚类有效性函数作为最佳聚类数的判断依据.结果:对于组织类别数不同的图像,SOM-FCM算法能自动给...     

基于Gibbs随机场的有限混合模型改进与脑部MR图像的稳健分割

有限混合(FM)模型已经广泛地应用于图像分割，但是由于没有考虑空间信息，导致分割的结果对噪声很敏感，分割出的区域存在很多杂散的孤立点。本文Gibbs随机场理论的指导下，将空间信息引入FM模型，提出了改进的脑部MR图像分割算法。此外，由树形K平均聚类来估计初始参数，实现了全自动的图像分割。本研究进行了仿真MR图像和真实MR图像的分割实验，定量的数据分析表明，我们所提的改进算法对噪声不敏感，可以更精确地将脑部MR图像标记为灰质、白质与脑脊液三种组织类型。     

Diffeomorphic susceptibility artifact correction of diffusion-weighted magnetic resonance images

Diffusion-weighted magnetic resonance imaging is a key investigation technique in modern neuroscience. In clinical settings, diffusion-weighted imaging and its extension to diffusion tensor imaging (DTI) are usually performed applying the technique of echo-planar imaging (EPI). EPI is the commonly available ultrafast acquisition technique for single-shot acquisition with spatial encoding in a Cartesian system. A drawback of these sequences is their high sensitivity against small perturbations of the magnetic field, caused, e.g., by differences in magnetic susceptibility of soft tissue, bone and air. The resulting magnetic field inhomogeneities thus cause geometrical distortions and intensity modulations in diffusion-weighted images. This complicates the fusion with anatomical T1- or T2-weighted MR images obtained with conventional spin- or gradient-echo images and negligible distortion. In order to limit the degradation of diffusion-weighted MR data, we present here a variational approach based on a reference scan pair with reversed polarity of the phase- and frequency-encoding gradients and hence reversed distortion. The key novelty is a tailored nonlinear regularization functional to obtain smooth and diffeomorphic transformations. We incorporate the physical distortion model into a variational image registration framework and derive an accurate and fast correction algorithm. We evaluate the applicability of our approach to distorted DTI brain scans of six healthy volunteers. For all datasets, the automatic correction algorithm considerably reduced the image degradation. We show that, after correction, fusion with T1- or T2-weighted images can be obtained by a simple rigid registration. Furthermore, we demonstrate the improvement due to the novel regularization scheme. Most importantly, we show that it provides meaningful, i.e. diffeomorphic, geometric transformations, independent of the actual choice of the regularization parameters.     

融合感知损失的深度学习在常规MR图像转换的研究

目的:研究在完全无监督的条件下深度神经网络实现常规磁共振图像间相互转换的可行性。方法:在循环生成式对抗网络(CycleGAN)中引入感知损失,使网络利用对抗损失学习图像结构信息的同时,结合循环一致性损失和感知损失生成高质量的磁共振图像,并将生成图像与CycleGAN模型以及有监督的CycleGAN模型(S_CycleGAN)生成的图像进行定量比较。结果:引入感知损失后的网络生成的图像定量评估值均高于CycleGAN模型生成的图像,生成的T1加权图像(T1WI)的定量评估值也均高于S_CycleGAN模型生成的T1WI,生成的T2加权图像(T2WI)与S_CycleGAN模型生成的T2WI的定量评估值相似。结论:在CycleGAN中引入感知损失,可以在完全无监督的条件下生成高质量的磁共振图像,进而实现高质量的常规磁共振图像的相互转换。     

Arterial spin labeling MR image denoising and reconstruction using unsupervised deep learning

Arterial spin labeling (ASL) imaging is a powerful magnetic resonance imaging technique that allows to quantitatively measure blood perfusion non-invasively, which has great potential for assessing tissue viability in various clinical settings. However, the clinical applications of ASL are currently limited by its low signal-to-noise ratio (SNR), limited spatial resolution, and long imaging time. In this work, we propose an unsupervised deep learning-based image denoising and reconstruction framework to improve the SNR and accelerate the imaging speed of high resolution ASL imaging. The unique feature of the proposed framework is that it does not require any prior training pairs but only the subject's own anatomical prior, such as T1-weighted images, as network input. The neural network was trained from scratch in the denoising or reconstruction process, with noisy images or sparely sampled k-space data as training labels. Performance of the proposed method was evaluated using in vivo experiment data obtained from 3 healthy subjects on a 3T MR scanner, using ASL images acquired with 44-min acquisition time as the ground truth. Both qualitative and quantitative analyses demonstrate the superior performance of the proposed txtc framework over the reference methods. In summary, our proposed unsupervised deep learning-based denoising and reconstruction framework can improve the image quality and accelerate the imaging speed of ASL imaging.     

基于稀疏分解的医学CT图像去噪

医学CT图像成像过程中,由于成像机制的影响,不可避免的引入噪声。图像中的噪声会降低图像质量,影响临床诊断。因此,有必要对医学CT图像进行去噪处理。本文采用图像的稀疏分解方法来对混有噪声的肝癌CT图像进行消噪处理,提出分块稀疏分解去噪。实验表明,本文算法对医学图像中噪声去除有一定效果。在分解原子个数相同的条件下,本文方法去噪后重建图像比在整幅图像上进行稀疏去噪重建的计算速度提高了约15倍。     

Feature space analysis: effects of MRI protocols.

We present a method for exploring the relationship between the image segmentation results obtained by an optimal feature space method and the MRI protocols used. The steps of the work accomplished are as follows. (1) Patients with brain tumors were imaged on a 1.5 T General Electric Signa MRI System using multiple protocols (T1 and T2-weighted fast spin-echo and FLAIR). T1-weighted images were acquired before and after gadolinium injection. (2) Image volumes were co-registered, and images of a slice through the center of the tumor were selected for processing. (3) For each patient, several image sets were defined by selecting certain MR images (e.g., 4T2's+ IT1, 4T2's+FLAIR, 2T2's+ 1T1). (4) Using each image set, the optimal feature space was generated and images were segmented into normal tissues and different tumor zones. (5) Segmentation results obtained using the different MRI sets were compared. Based on the analysis results from 27 image sets, we found that the locations of the clusters for the tumor zones and their corresponding regions in the image domain changed as a function of the MR images (MRI protocols) used. However, the segmentation results for the total lesion and normal tissues remained relatively unchanged.     

Non-rigid image registration using a median-filtered coarse-to-fine displacement field and a symmetric correlation ratio

Conventional approaches to image registration are generally limited to image-wide rigid transformations. However, the body and its internal organs are non-rigid structures that change shape due to changes in the body's posture during image acquisition, and due to normal, pathological and treatment-related variations. Inter-subject matching also constitutes a non-rigid registration problem. In this paper, we present a fully automated non-rigid image registration method that maximizes a local voxel-based similarity metric. Overlapping image blocks are defined on a 3D grid. The transformation vector field representing image deformation is found by translating each block so as to maximize the local similarity measure. The resulting sparsely sampled vector field is median filtered and interpolated by a Gaussian function to ensure a locally smooth transformation. A hierarchical strategy is adopted to progressively establish local registration associated with image structures at diminishing scale. Simulation studies were carried out to evaluate the proposed algorithm and to determine the robustness of various voxel-based cost functions. Mutual information, normalized mutual information, correlation ratio (CR) and a new symmetric version of CR were evaluated and compared. A T1-weighted magnetic resonance (MR) image was used to test intra-modality registration. Proton density and T2-weighted MR images of the same subject were used to evaluate inter-modality registration. The proposed algorithm was tested on the 2D MR images distorted by known deformations and 3D images simulating inter-subject distortions. We studied the robustness of cost functions with respect to image sampling. Results indicate that the symmetric CR gives comparable registration to mutual information in intra- and inter-modality tasks at full sampling and is superior to mutual information in registering sparsely sampled images.     

Sequential Registration-Based Segmentation of the Prostate Gland in MR Image Volumes

Accurate and fast segmentation and volume estimation of the prostate gland in magnetic resonance (MR) images are necessary steps in the diagnosis, treatment, and monitoring of prostate cancer. This paper presents an algorithm for the prostate gland volume estimation based on the semi-automated segmentation of individual slices in T2-weighted MR image sequences. The proposed sequential registration-based segmentation (SRS) algorithm, which was inspired by the clinical workflow during medical image contouring, relies on inter-slice image registration and user interaction/correction to segment the prostate gland without the use of an anatomical atlas. It automatically generates contours for each slice using a registration algorithm, provided that the user edits and approves the marking in some previous slices. We conducted comprehensive experiments to measure the performance of the proposed algorithm using three registration methods (i.e., rigid, affine, and nonrigid). Five radiation oncologists participated in the study where they contoured the prostate MR (T2-weighted) images of 15 patients both manually and using the SRS algorithm. Compared to the manual segmentation, on average, the SRS algorithm reduced the contouring time by 62 % (a speedup factor of 2.64×) while maintaining the segmentation accuracy at the same level as the intra-user agreement level (i.e., Dice similarity coefficient of 91 versus 90 %). The proposed algorithm exploits the inter-slice similarity of volumetric MR image series to achieve highly accurate results while significantly reducing the contouring time.     

Registration of FA and T1-Weighted MRI Data of Healthy Human Brain Based on Template Matching and Normalized Cross-Correlation

In this work, we propose a new approach for three-dimensional registration of MR fractional anisotropy images with T1-weighted anatomy images of human brain. From the clinical point of view, this accurate coregistration allows precise detection of nerve fibers that is essential in neuroscience. A template matching algorithm combined with normalized cross-correlation was used for this registration task. To show the suitability of the proposed method, it was compared with the normalized mutual information-based B-spline registration provided by the Elastix software library, considered a reference method. We also propose a general framework for the evaluation of robustness and reliability of both registration methods. Both registration methods were tested by four evaluation criteria on a dataset consisting of 74 healthy subjects. The template matching algorithm has shown more reliable results than the reference method in registration of the MR fractional anisotropy and T1 anatomy image data. Significant differences were observed in the regions splenium of corpus callosum and genu of corpus callosum, considered very important areas of brain connectivity. We demonstrate that, in this registration task, the currently used mutual information-based parametric registration can be replaced by more accurate local template matching utilizing the normalized cross-correlation similarity measure.     

Content-Based Estimation of Brain MRI Tilt in Three Orthogonal Directions

In a general scenario, the brain images acquired from magnetic resonance imaging (MRI) may experience tilt, distorting brain MR images. The tilt experienced by the brain MR images may result in misalignment during image registration for medical applications. Manually correcting (or estimating) the tilt on a large scale is time-consuming, expensive, and needs brain anatomy expertise. Thus, there is a need for an automatic way of performing tilt correction in three orthogonal directions (X, Y, Z). The proposed work aims to correct the tilt automatically by measuring the pitch angle, yaw angle, and roll angle in X-axis, Z-axis, and Y-axis, respectively. For correction of the tilt around the Z-axis (pointing to the superior direction), image processing techniques, principal component analysis, and similarity measures are used. Also, for correction of the tilt around the X-axis (pointing to the right direction), morphological operations, and tilt correction around the Y-axis (pointing to the anterior direction), orthogonal regression is used. The proposed approach was applied to adjust the tilt observed in the T1- and T2-weighted MR images. The simulation study with the proposed algorithm yielded an error of 0.40 ± 0.09°, and it outperformed the other existing studies. The tilt angle (in degrees) obtained is ranged from 6.2 ± 3.94, 2.35 ± 2.61, and 5 ± 4.36 in X-, Z-, and Y-directions, respectively, by using the proposed algorithm. The proposed work corrects the tilt more accurately and robustly when compared with existing studies.

     

An anisotropic diffusion method for denoising dynamic susceptibility contrast-enhanced magnetic resonance images.

The purpose of this study was to present an application of a novel denoising technique for improving the accuracy of cerebral blood flow (CBF) images generated from dynamic susceptibility contrast-enhanced magnetic resonance imaging (DSC-MRI). The method presented in this study was based on anisotropic diffusion (AD). The usefulness of this method was firstly investigated using computer simulations. We applied this method to patient data acquired using a 1.5 T MR system. After a bolus injection of Gd-DTPA, we obtained 40-50 dynamic images with a 1.32-2.08 s time resolution in 4-6 slices. The dynamic images were processed using the AD method, and then the CBF images were generated using pixel-by-pixel deconvolution analysis. For comparison, the CBF images were also generated with or without processing the dynamic images using a median or Gaussian filter. In simulation studies, the standard deviation of the CBF values obtained after processing by the AD method was smaller than that of the CBF values obtained without any processing, while the mean value agreed well with the true CBF value. Although the median and Gaussian filters also reduced image noise, the mean CBF values were considerably underestimated compared with the true values. Clinical studies also suggested that the AD method was capable of reducing the image noise while preserving the quantitative accuracy of CBF images. In conclusion, the AD method appears useful for denoising DSC-MRI, which will make the CBF images generated from DSC-MRI more reliable.     

Automated cerebrum segmentation from three-dimensional sagittal brain MR images

We present a fully automated cerebrum segmentation algorithm for full three-dimensional sagittal brain MR images. First, cerebrum segmentation from a midsagittal brain MR image is performed utilizing landmarks, anatomical information, and a connectivity-based threshold segmentation algorithm as previously reported. Recognizing that cerebrum in laterally adjacent slices tends to have similar size and shape, we use the cerebrum segmentation result from the midsagittal brain MR image as a mask to guide cerebrum segmentation in adjacent lateral slices in an iterative fashion. This masking operation yields a masked image (preliminary cerebrum segmentation) for the next lateral slice, which may truncate brain region(s). Truncated regions are restored by first finding end points of their boundaries, by comparing the mask image and masked image boundaries, and then applying a connectivity-based algorithm. The resulting final extracted cerebrum image for this slice is then used as a mask for the next lateral slice. The algorithm yielded satisfactory fully automated cerebrum segmentations in three-dimensional sagittal brain MR images, and had performance superior to conventional edge detection algorithms for segmentation of cerebrum from 3D sagittal brain MR images.     

Relevance of apparent diffusion coefficient features for a radiomics-based prediction of response to induction chemotherapy in sinonasal cancer

In this paper, several radiomics-based predictive models of response to induction chemotherapy (IC) in sinonasal cancers (SNCs) are built and tested. Models were built as a combination of radiomic features extracted from three types of MRI images: T1-weighted images, T2-weighted images and apparent diffusion coefficient (ADC) maps. Fifty patients (aged 54 ± 12 years, 41 men) were included in this study. Patients were classified according to their response to IC (25 responders and 25 nonresponders). Not all types of images were acquired for all of the patients: 49 had T1-weighted images, 50 had T2-weighted images and 34 had ADC maps. Only in a subset of 33 patients were all three types of image acquired. Eighty-nine radiomic features were extracted from the MRI images. Dimensionality reduction was performed by using principal component analysis (PCA) and by selecting only the three main components. Different algorithms (trees ensemble, K-nearest neighbors, support vector machine, naïve Bayes) were used to classify the patients as either responders or nonresponders. Several radiomic models (either monomodality or multimodality obtained by a combination of T1-weighted, T2-weighted and ADC images) were developed and the performance was assessed through 100 iterations of train and test split. The area under the curve (AUC) of the models ranged from 0.56 to 0.78. Trees ensemble, support vector machine and naïve Bayes performed similarly, but in all cases ADC-based models performed better. Trees ensemble gave the highest AUC (0.78 for the T1-weighted+T2-weighted+ADC model) and was used for further analyses. For trees ensemble, the models based on ADC features performed better than those models that did not use those features (P < 0.02 for one-tail Hanley test, AUC range 0.68–0.78 vs 0.56–0.69) except the T1-weighted+ADC model (AUC 0.71 vs 0.69, nonsignificant differences). The results suggest the relevance of ADC-based radiomics for prediction of response to IC in SNCs.     

Image reconstruction for positron emission tomography using fuzzy nonlinear anisotropic diffusion penalty

Iterative algorithms such as maximum likelihood-expectation maximization (ML-EM) become the standard for the reconstruction in emission computed tomography. However, such algorithms are sensitive to noise artifacts so that the reconstruction begins to degrade when the number of iterations reaches a certain value. In this paper, we have investigated a new iterative algorithm for penalized-likelihood image reconstruction that uses the fuzzy nonlinear anisotropic diffusion (AD) as a penalty function. The proposed algorithm does not suffer from the same problem as that of ML-EM algorithm, and it converges to a low noisy solution even if the iteration number is high. The fuzzy reasoning instead of a nonnegative monotonically decreasing function was used to calculate the diffusion coefficients which control the whole diffusion. Thus, the diffusion strength is controlled by fuzzy rules expressed in a linguistic form. The proposed method makes use of the advantages of fuzzy set theory in dealing with uncertain problems and nonlinear AD techniques in removing the noise as well as preserving the edges. Quantitative analysis shows that the proposed reconstruction algorithm is suitable to produce better reconstructed images when compared with ML-EM, ordered subsets EM (OS-EM), Gaussian-MAP, MRP, TV-EM reconstructed images.     

MRI-guided Thermal Ablation Therapy: Model and Parameter Estimates to Predict Cell Death from MR Thermometry Images

Solid tumors and other pathologies can be treated using laser thermal ablation under interventional magnetic resonance imaging (iMRI) guidance. A model was developed to predict cell death from magnetic resonance (MR) thermometry measurements based on the temperature–time history, and validated using in vivo rabbit brain data. To align post-ablation T2-weighted spin-echo MR lesion images to gradient-echo MR images, from which temperature is derived, a registration method was used that aligned fiducials placed near the thermal lesion. The outer boundary of the hyperintense rim in the post-ablation MR lesion image was used as the boundary for cell death, as verified from histology. Model parameters were simultaneously estimated using an iterative optimization algorithm applied to every interesting voxel in 328 images from multiple experiments having various temperature histories. For a necrotic region of 766 voxels across all lesions, the model provided a voxel specificity and sensitivity of 98.1 and 78.5%, respectively. Mislabeled voxels were typically within one voxel from the segmented necrotic boundary with median distances of 0.77 and 0.22 mm for false positives (FP) and false negatives (FN), respectively. As compared to the critical temperature cell death model and the generalized Arrhenius model, our model typically predicted fewer FP and FN. This is good evidence that iMRI temperature maps can be used with our model to predict therapeutic regions in real-time during treatment.     

基于神经动力学的医学图像增强技术

目的探讨基于视觉神经元模型的图像增强算法在医学图像处理中的效果和自动实现的方便性。方法用基于视觉神经元ON—OFF模型的图像增强算法处理医学图像，实现对医学图像的自动增强；探讨增强算法的处理机制；分析衰减常数、增益系数和空间常数对图像增强处理的影响。结果选1例左额胶质瘤患者的T1W序列MR图像，1例右眶周及右额顶血管瘤患者的CTA图像。经图像增强处理，MR图像颅脑内部的结构更加清晰可见，图像层次丰富，组织边界分明，内容纹理层次丰富，易于观察。CTA图像处理后，血管瘤病变部位组织轮廓变得完整清晰，图像层次变得更加丰富。同时，整体对比度下降，图像视觉柔和。结论通过对大量医学图像的处理计算，证明选择适当的衰减常数、增益系数和空间常数，可以得到比较显著的图像增强效果。     

A tool for validating MRI-guided strategies: a digital breathing CT/MRI phantom of the abdominal site

Dynamic magnetic resonance imaging (MRI) is emerging as the elected image modality for organ motion quantification and management in image-guided radiotherapy. However, the lack of validation tools is an open issue for image guidance in the abdominal and thoracic organs affected by organ motion due to respiration. We therefore present an abdominal four-dimensional (4D) CT/MRI digital phantom, including the estimation of MR tissue parameters, simulation of dedicated abdominal MR sequences, modeling of radiofrequency coil response and noise, followed by k-space sampling and image reconstruction. The phantom allows the realistic simulation of images generated by MR pulse sequences with control of scan and tissue parameters, combined with co-registered CT images. In order to demonstrate the potential of the phantom in a clinical scenario, we describe the validation of a virtual T1-weighted 4D MRI strategy. Specifically, the motion extracted from a T2-weighted 4D MRI is used to warp a T1-weighted breath-hold acquisition, with the aim of overcoming trade-offs that limit T1-weighted acquisitions. Such an application shows the applicability of the digital CT/MRI phantom as a validation tool, which should be especially useful for cases unsuited to obtain real imaging data.     

Magnetic resonance imaging-guided attenuation and scatter corrections in three-dimensional brain positron emission tomography

Reliable attenuation correction represents an essential component of the long chain of modules required for the reconstruction of artifact-free, quantitative brain positron emission tomography (PET) images. In this work we demonstrate the proof of principle of segmented magnetic resonance imaging (MRI)-guided attenuation and scatter corrections in three-dimensional (3D) brain PET. We have developed a method for attenuation correction based on registered T1-weighted MRI, eliminating the need of an additional transmission (TX) scan. The MR images were realigned to preliminary reconstructions of PET data using an automatic algorithm and then segmented by means of a fuzzy clustering technique which identifies tissues of significantly different density and composition. The voxels belonging to different regions were classified into air, skull, brain tissue and nasal sinuses. These voxels were then assigned theoretical tissue-dependent attenuation coefficients as reported in the ICRU 44 report followed by Gaussian smoothing and addition of a good statistics bed image. The MRI-derived attenuation map was then forward projected to generate attenuation correction factors (ACFs) to be used for correcting the emission (EM) data. The method was evaluated and validated on 10 patient data where TX and MRI brain images were available. Qualitative and quantitative assessment of differences between TX-guided and segmented MRI-guided 3D reconstructions were performed by visual assessment and by estimating parameters of clinical interest. The results indicated a small but noticeable improvement in image quality as a consequence of the reduction of noise propagation from TX into EM data. Considering the difficulties associated with preinjection TX-based attenuation correction and the limitations of current calculated attenuation correction, MRI-based attenuation correction in 3D brain PET would likely be the method of choice for the foreseeable future as a second best approach in a busy nuclear medicine center and could be applied to other functional brain imaging modalities such as SPECT.