A multi-scale residual network for accelerated radial MR parameter mapping

A deep learning MR parameter mapping framework which combines accelerated radial data acquisition with a multi-scale residual network (MS-ResNet) for image reconstruction is proposed. The proposed supervised learning strategy uses input image patches from multi-contrast images with radial undersampling artifacts and target image patches from artifact-free multi-contrast images. Subspace filtering is used during pre-processing to denoise input patches. For each anatomy and relaxation parameter, an individual network is trained. in vivo T₁ mapping results are obtained on brain and abdomen datasets and in vivo T₂ mapping results are obtained on brain and knee datasets. Quantitative results for the T₂ mapping of the knee show that MS-ResNet trained using either fully sampled or undersampled data outperforms conventional model-based compressed sensing methods. This is significant because obtaining fully sampled training data is not possible in many applications. in vivo brain and abdomen results for T₁ mapping and in vivo brain results for T₂ mapping demonstrate that MS-ResNet yields contrast-weighted images and parameter maps that are comparable to those achieved by model-based iterative methods while offering two orders of magnitude reduction in reconstruction times. The proposed approach enables recovery of high-quality contrast-weighted images and parameter maps from highly accelerated radial data acquisitions. The rapid image reconstructions enabled by the proposed approach makes it a good candidate for routine clinical use.     

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.     

Image registration guided,sparsity constrained reconstructions for dynamic MRI

It is generally a challenging task to reconstruct dynamic magnetic resonance (MR) images with high spatial and high temporal resolutions, especially with highly incomplete k-space sampling. In this work, a novel method that combines a non-rigid image registration technique with sparsity-constrained image reconstruction is introduced. Employing a multi-resolution free-form deformation technique with B-spline interpolations, the non-rigid image registration accurately models the complex deformations of the physiological dynamics, and provides artifact-suppressed high spatial-resolution predictions. Based on these prediction images, the sparsity-constrained data fidelity-enforced image reconstruction further improves the reconstruction accuracy. When compared with the k-t FOCUSS with motion estimation/motion compensation (MEMC) technique on volunteer scans, the proposed method consistently outperforms in both the spatial and the temporal accuracy with variously accelerated k-space sampling. High fidelity reconstructions for dynamic systolic phases with reduction factor of 10 and cardiac perfusion series with reduction factor of 3 are presented.     

The influence of the resolution and contrast on measuring the articular cartilage volume in magnetic resonance images

The progression of OA in patients may be followed by measuring the volume of articular cartilage from MR images. We attempted to determine the reproducibility of volume measurements of articular cartilage made from magnetic resonance images of the knees and the dependence of the reproducibility on image resolution and contrast-to-noise. A fat-suppressed 3D technique was used to generate four image sets with different image resolution. Each patient was imaged twice to obtain image pairs at each resolution. To assess the dependence of reproducibility on noise we generated six image sets for each patient by adding noise to the original images and repeating the comparison. On each image set, the femoral, tibial, and patellar cartilage were outlined by a combination of computer and manual methods, and the images were used to calculate the volume of each cartilage plate. Comparing the coefficient of variance between the volume measurements made from the two visits, the volume measurements made from images with the highest resolution (0.275 x 0.275 x 1.0 mm) had the highest reproducibility. The high resolution images of the tibia and femur had the least partial-volume averaging and, as a result, better defined the boundaries between cartilage and adjacent tissues. A different trend was evident for the patella. For studies of osteoarthritis therapies, we recommend using MR images with the highest possible in-plane spatial resolution to provide the most reproducible volume measurements of knee cartilage.     

基于级联网络的膝关节图像分割与模型构建

采用膝关节模型进行电磁仿真是计算膝关节局部射频功率沉积（SAR）的主要方法,为了构建膝关节模型,本文提出了一种包含两个卷积神经网络——U-Net的级联网络结构,用于膝关节磁共振图像的分割.第一个网络在整幅图上分割肌肉、脂肪等占比较大的组织,并从分割结果中预测软骨与半月板的大致位置信息,第二个网络基于该信息在一个更小的子图上分割小组织以提高分割精度.两个网络均采用焦点损失函数,它们的分割结果合并在一起构成膝关节模型.我们将该方法与其它4种方法的分割结果进行了定量指标的对比研究,并分别构建膝关节模型,计算局部SAR值.结果表明本文提出的级联网络结构可以更精确的构建用于SAR仿真的膝关节模型.     

A fully automatic three-step liver segmentation method on LDA-based probability maps for multiple contrast MR images

Automatic 3D liver segmentation in magnetic resonance (MR) data sets has proven to be a very challenging task in the domain of medical image analysis. There exist numerous approaches for automatic 3D liver segmentation on computer tomography data sets that have influenced the segmentation of MR images. In contrast to previous approaches to liver segmentation in MR data sets, we use all available MR channel information of different weightings and formulate liver tissue and position probabilities in a probabilistic framework. We apply multiclass linear discriminant analysis as a fast and efficient dimensionality reduction technique and generate probability maps then used for segmentation. We develop a fully automatic three-step 3D segmentation approach based upon a modified region growing approach and a further threshold technique. Finally, we incorporate characteristic prior knowledge to improve the segmentation results. This novel 3D segmentation approach is modularized and can be applied for normal and fat accumulated liver tissue properties.     

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

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

Joint Reconstruction of Multi-contrast Images and Multi-channel Coil Sensitivities

Magnetic resonance imaging (MRI) has an important feature that it provides multiple images with different contrasts for complementary diagnostic information. However, a large amount of data is needed for multi-contrast images depiction, and thus, the scan is time-consuming. Many methods based on parallel magnetic resonance imaging (pMRI) and compressed sensing (CS) are applied to accelerate multi-contrast MR imaging. Nevertheless, the image reconstructed by sophisticated pMRI methods contains residual aliasing artifact that degrades the quality of the image when the acceleration factor is high. Other methods based on CS always suffer the regularization parameter-selecting problem. To address these issues, a new method is presented for joint multi-contrast image reconstruction and coil sensitivity estimation. The coil sensitivities can be shared during the reconstruction due to the identity of coil sensitivity profiles of different contrast images for imaging stationary tissues. The proposed method uses the coil sensitivities as sharable information during the reconstruction to improve the reconstruction quality. As a result, the residual aliasing artifact can be effectively removed in the reconstructed multi-contrast images even if the acceleration factor is high. Besides, as there is no regularization term in the proposed method, the troublesome regularization parameter selection in the CS can also be avoided. Results from multi-contrast in vivo experiments demonstrated that multi-contrast images can be jointly reconstructed by the proposed method with effective removal of the residual aliasing artifact at a high acceleration factor.     

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.     

用于压缩感知磁共振成像的分割字典学习算法

字典学习算法可以根据数据本身的特点构建稀疏域中的基,从而使数据的表示更加稀疏.该文在传统的字典学习算法基础上提出了分割字典学习算法,由于部分磁共振图像组织结构简单、可以进行图像分割,因此可根据此特点来优化字典中基函数的构建,使磁共振图像的表达更为稀疏,从而获得更高的重建图像质量.该文利用模拟数据和真实数据进行了重建实验,结果表明与传统的字典学习算法相比,分割字典学习算法能进一步改善重建图像质量.     

用于SAR估计的基于U-Net网络的快速膝关节模型重建

膝关节高场磁共振成像（MRI）时，射频功率沉积（SAR）是一个关键的安全指标.目前对于局部SAR的准确估计只能通过电磁仿真实现，这就要求得到每一个个体的膝关节模型.本文提出一种针对低场磁共振图像的基于卷积神经网络的分割方法，以实现膝关节磁共振图像的快速重建.数据集来自于矢位T₁加权自旋回波图像，将膝关节组织按照"肌肉-脂肪-骨骼"模型进行简化，除脂肪与骨骼之外的其他组织归类为肌肉.采用一种全卷积的神经网络，即U-Net进行逐层的图像分割，卷积层数为4，训练采用交叉熵函数.本文对图像的自动分割结果与手动标注结果进行了定量的比较.此外，采用3 T正交鸟笼线圈进行了SAR仿真，结果验证了组织简化对于SAR估计的可行性，并且所提方法构建的模型可以得到较为精准的局部SAR分布.     

Handcrafted fuzzy rules for tissue classification

This article proposes a handcrafted fuzzy rule-based system for segmentation and identification of different tissue types in magnetic resonance (MR) brain images. The proposed fuzzy system uses a combination of histogram and spatial neighborhood-based features. The intensity variation from one type of tissue to another is gradual at the boundaries due to the inherent nature of the MR signal (MR physics). A fuzzy rule-based approach is expected to better handle these variations and variability in features corresponding to different types of tissues. The proposed segmentation is tested to classify the pixels of the T2-weighted axial MR images of the brain into three primary tissue types: white matter, gray matter and cerebral-spinal fluid. The results are compared with those from manual segmentation by an expert, demonstrating good agreement between them.     

Stable Atlas-based Mapped Prior (STAMP) machine-learning segmentation for multicenter large-scale MRI data

Machine learning (ML)-based segmentation methods are a common technique in the medical image processing field. In spite of numerous research groups that have investigated ML-based segmentation frameworks, there remains unanswered aspects of performance variability for the choice of two key components: ML algorithm and intensity normalization. This investigation reveals that the choice of those elements plays a major part in determining segmentation accuracy and generalizability. The approach we have used in this study aims to evaluate relative benefits of the two elements within a subcortical MRI segmentation framework. Experiments were conducted to contrast eight machine-learning algorithm configurations and 11 normalization strategies for our brain MR segmentation framework. For the intensity normalization, a Stable Atlas-based Mapped Prior (STAMP) was utilized to take better account of contrast along boundaries of structures. Comparing eight machine learning algorithms on down-sampled segmentation MR data, it was obvious that a significant improvement was obtained using ensemble-based ML algorithms (i.e., random forest) or ANN algorithms. Further investigation between these two algorithms also revealed that the random forest results provided exceptionally good agreement with manual delineations by experts. Additional experiments showed that the effect of STAMP-based intensity normalization also improved the robustness of segmentation for multicenter data sets. The constructed framework obtained good multicenter reliability and was successfully applied on a large multicenter MR data set (n > 3000). Less than 10% of automated segmentations were recommended for minimal expert intervention. These results demonstrate the feasibility of using the ML-based segmentation tools for processing large amount of multicenter MR images. We demonstrated dramatically different result profiles in segmentation accuracy according to the choice of ML algorithm and intensity normalization chosen.     

Fast multi-contrast MRI reconstruction

Multi-contrast magnetic resonance imaging (MRI) is a useful technique to aid clinical diagnosis. This paper proposes an efficient algorithm to jointly reconstruct multiple T1/T2-weighted images of the same anatomical cross section from partially sampled k-space data. The joint reconstruction problem is formulated as minimizing a linear combination of three terms, corresponding to a least squares data fitting, joint total variation (TV) and group wavelet-sparsity regularization. It is rooted in two observations: 1) the variance of image gradients should be similar for the same spatial position across multiple contrasts; 2) the wavelet coefficients of all images from the same anatomical cross section should have similar sparse modes. To efficiently solve this problem, we decompose it into joint TV regularization and group sparsity subproblems, respectively. Finally, the reconstructed image is obtained from the weighted average of solutions from the two subproblems, in an iterative framework. Experiments demonstrate the efficiency and effectiveness of the proposed method compared to existing multi-contrast MRI methods.     

Automatic measurement of changes in brain volume on consecutive 3D MR images by segmentation propagation

This article presents a technique to automatically measure changes in the volume of a structure of interest in successive 3D magnetic resonance (MR) images and its application in the study of the brain and lateral cerebral ventricles. The only manual step is a segmentation of the structure of interest in the first image. The analysis comprises, first, precise rigid co-registration of the time series of images; second, computation of residual deformations between pairs of images; third, automatic quantification of the volume change, obtained by propagation of the segmentation of the structure of interest through the series of MR images. This approach has been applied to monitor changes in the volume of the brain and lateral cerebral ventricles in a healthy subject and a patient with primary progressive aphasia (PPA). Results are consistent with those obtained by application of the boundary shift integral (BSI) and by stereology in the same subjects.     

Segmentation of whole breast and fibroglandular tissue using nnU-Net in dynamic contrast enhanced MR images

PurposeSegmentation of the whole breast and fibroglandular tissue (FGT) is important for quantitatively analyzing the breast cancer risk in the dynamic contrast-enhanced magnetic resonance (DCE-MR) images. The purpose of this study is to improve the accuracy and efficiency of the segmentation of the whole breast and FGT in 3-D fat-suppressed DCE-MR images with a versatile deep learning (DL) framework.MethodsWe randomly collected 100 breast DCE-MR scans from Shanghai Cancer Hospital of Fudan University. The MR scans in the dataset were different in both the spatial resolution and the MR scanners employed. Furthermore, four breast density categories were assessed by radiologists based on Breast Imaging Reporting and Data System (BI-RADS) of American College of Radiology. The dataset was separated into the training and the testing sets, while keeping a balanced distribution of scans with different imaging parameters and density categories. The nnU-Net has been recently proposed to automatically adapt preprocessing strategies and network architectures for a given medical image dataset, thus showing a great potential in the systematic adaptation of DL methods to different datasets. In this study, we applied the nnU-Net to segment the whole breast and FGT in 3-D fat-suppressed DCE-MR images. Five-fold cross validation was employed to train and validate the segmentation method.ResultsThe segmentation performance was evaluated with the volume and surface agreement metrics between the DL-based automatic and the manually delineated masks, as quantified with the following measures: the average Dice volume overlap (0.968 ± 0.017 and 0.877 ± 0.081), the average surface distances (0.201 ± 0.080 mm and 0.310 ± 0.043 mm), and the Pearson correlation coefficient of masks (0.995 and 0.972) between the automatic and the manually delineated masks, as calculated for the whole breast and the FGT segmentation, respectively. The correlation coefficient between the breast densities obtained with the DL-based segmentation and the manual delineation was 0.981. There was a positive bias of 0.8% (DL-based relative to manual) in breast density measurement with the Bland-Altman plot. The execution time of the DL-based segmentation was approximately 20 s for the whole breast segmentation and 15 s for the FGT segmentation.ConclusionsOur DL-based segmentation framework using nnU-Net could robustly achieve high accuracy and efficiency across variable MR imaging settings without extra pre- or post-processing procedures. It would be useful for developing DCE-MR-based CAD systems to quantify breast cancer risk and to be integrated into the clinical workflow.     

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.     

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

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

一种基于图像特征和神经网络的苹果图像分割算法

苹果识别是开发苹果采摘机器人的关键环节,利用图像处理技术和神经网络分类器探索苹果图像分割算法.从苹果树图片中选取苹果图像样本和背景网像样本.分别计算这两类图像样本的颜色特征和纹理特征.颜色特征的计算基于RGB色彩模型,纹理特征的计算基于灰度共生矩阵.选取适当的颜色特征(R/B值)和纹理特征(对比度值和相关性值)作为输入节点,利用反向传播神经网络分类器建模,输出值是一个O～1之间的计算值.通过阈值将输出结果分类为苹果或背景.试验结果表明,该算法正确率大于87.6%,对光照的影响不敏感,是一利较为实用的苹果分割算法.     

Interobserver reproducibility of quantitative cartilage measurements: comparison of B-spline snakes and manual segmentation.

The objective of this work was to develop a segmentation technique for thickness measurements of the articular cartilage in MR images and to assess the interobserver reproducibility of the method in comparison with manual segmentation. The algorithm is based on a B-spline snakes approach and is able to delineate the cartilage boundaries in real time and with minimal user interaction. The interobserver reproducibility of the method, ranging from 3.3 to 13.6% for various section orientations and joint surfaces, proved to be significantly superior to manual segmentation.