Neuroradiologic MR applications with multiparametric color composite display

The purpose of this article is to demonstrate the application of a PC-based multiparameter full color composite display technique of MR images of 14 selected patients with neuropathology while assessing the ability of this technique to display clinically important neuroanatomic and neuropathologic tissues. Using a PC with a 386 microprocessor and full color 24-bit graphics display capabilities, custom and commercially available image-processing softwares were applied to spatially aligned multiparameter proton density, T₁-weighted (with and/or without gadolinium-DTPA) and T₂-weighted MR image sets obtained from 14 patients with known neuropathology to generate intensity-based color composites. Quantitative color channel applications were used to assess the ability of this technique to differentiate anatomically and pathologically confirmed tissue types into unique color regions within the full color spectrum display in each patient case. Based on the results of pathologic correlation and quantitative color imaging analysis, the application of full color composite generation techniques to multiple MR images of selected neuropathology cases represents a viable technique for displaying diagnostically relevant tissue contrast information in one color image. With this technique, it is possible to generate composites that simultaneously display uniquely color-coded neuroanatomic and neuropathologic tissue information within the context of partially natural-appearing images.     

Deriving new soft tissue contrasts from conventional MR images using deep learning

Versatile soft tissue contrast in magnetic resonance imaging is a unique advantage of the imaging modality. However, the versatility is not fully exploited. In this study, we propose a deep learning-based strategy to derive more soft tissue contrasts from conventional MR images obtained in standard clinical MRI. Two types of experiments are performed. First, MR images corresponding to different pulse sequences are predicted from one or more images already acquired. As an example, we predict T_1ρ weighted knee image from T₂ weighted image and/or T₁ weighted image. Furthermore, we estimate images corresponding to alternative imaging parameter values. In a representative case, variable flip angle images are predicted from a single T₁ weighted image, whose accuracy is further validated in quantitative T₁ map subsequently derived. To accomplish these tasks, images are retrospectively collected from 56 subjects, and self-attention convolutional neural network models are trained using 1104 knee images from 46 subjects and tested using 240 images from 10 other subjects. High accuracy has been achieved in resultant qualitative images as well as quantitative T₁ maps. The proposed deep learning method can be broadly applied to obtain more versatile soft tissue contrasts without additional scans or used to normalize MR data that were inconsistently acquired for quantitative analysis.     

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.     

Characterization of trabecular bone structure from high-resolution magnetic resonance images using fuzzy logic

The purpose of this work was to apply fuzzy logic image processing techniques to characterize the trabecular bone structure with high-resolution magnetic resonance images. Fifteen ex vivo high-resolution magnetic resonance images of specimens of human radii at 1.5 T and 12 in vivo high-resolution magnetic resonance images of the calcanei of peri- and postmenopausal women at 3 T were obtained. Soft segmentation using fuzzy clustering was applied to MR data to obtain fuzzy bone volume fraction maps, which were then analyzed with three-dimensional (3D) fuzzy geometrical parameters and measures of fuzziness. Geometrical parameters included fuzzy perimeter and fuzzy compactness, while measures of fuzziness included linear index of fuzziness, quadratic index of fuzziness, logarithmic fuzzy entropy, and exponential fuzzy entropy. Fuzzy parameters were validated at 1.5 T with 3D structural parameters computed from microcomputed tomography images, which allow the observation of true trabecular bone structure and with apparent MR structural indexes at 1.5 T and 3 T. The validation was statistically performed with the Pearson correlation coefficient as well as with the Bland-Altman method. Bone volume fraction correlation values (r) were up to .99 (P<.001) with good agreements based on Bland-Altman analysis showing that fuzzy clustering is a valid technique to quantify this parameter. Measures of fuzziness also showed consistent correlations to trabecular number parameters (r>.85; P<.001) and good agreements based on Bland-Altman analysis, suggesting that the level of fuzziness in high-resolution magnetic resonance images could be related to the trabecular bone structure.     

Segmentation techniques for tissue differentiation in MRI of ophthalmology using fuzzy clustering algorithms

This paper presents MRI segmentation techniques to differentiate abnormal and normal tissues in Ophthalmology using fuzzy clustering algorithms. Applying the best-known fuzzy c-means (FCM) clustering algorithm, a newly proposed algorithm, called an alternative fuzzy c-mean (AFCM), was used for MRI segmentation in Ophthalmology. These unsupervised segmentation algorithms can help Ophthalmologists to reduce the medical imaging noise effects originating from low resolution sensors and/or the structures that move during the data acquisition. They may be particularly helpful in the clinical oncological field as an aid to the diagnosis of Retinoblastoma, an inborn oncological disease in which symptoms usually show in early childhood. For the purpose of early treatment with radiotherapy and surgery, the newly proposed AFCM is preferred to provide more information for medical images used by Ophthalmologists. Comparisons between FCM and AFCM segmentations are made. Both fuzzy clustering segmentation techniques provide useful information and good results. However, the AFCM method has better detection of abnormal tissues than FCM according to a window selection. Overall, the newly proposed AFCM segmentation technique is recommended in MRI segmentation.     

Comparison of supervised MRI segmentation methods for tumor volume determination during therapy

Two different multispectral pattern recognition methods are used to segment magnetic resonance images (MRI) of the brain for quantitative estimation of tumor volume and volume changes with therapy. A supervised k-nearest neighbor (kNN) rule and a semi-supervised fuzzy c-means (SFCM) method are used to segment MRI slice data. Tumor volumes as determined by the kNN and SFCM segmentation methods are compared with two reference methods, based on image grey scale, as a basis for an estimation of ground truth, namely: (a) a commonly used seed growing method that is applied to the contrast enhanced T₁-weighted image, and (b) a manual segmentation method using a custom-designed graphical user interface applied to the same raw image (T₁-weighted) dataset. Emphasis is placed on measurement of intra and inter observer reproducibility using the proposed methods. Intra- and interobserver variation for the kNN method was 9% and 5%, respectively. The results for the SFCM method was a little better at 6% and 4%, respectively. For the seed growing method, the intra-observer variation was 6% and the interobserver variation was 17%, significantly larger when compared with the multispectral methods. The absolute tumor volume determined by the multispectral segmentation methods was consistently smaller than that observed for the reference methods. The results of this study are found to be very patient case-dependent. The results for SFCM suggest that it should be useful for relative measurements of tumor volume during therapy, but further studies are required. This work demonstrates the need for minimally supervised or unsupervised methods for tumor volume measurements.     

Fast flair imaging of the brain using the fast spin-echo and gradient spin-echo technique

The purpose of this study was to compare the gradient spin-echo (GRASE) to the fast spin-echo (FSE) implementation of fast fluid-attenuated inversion recovery (FLAIR) sequences for brain imaging. Thirty patients with high signal intensity lesions on T₂-weighted images were examined on a 1.5 T MR system. Scan time-minimized thin-section FLAIR-FSE and FLAIR-GRASE sequences were obtained and compared side by side. Image assessment criteria were lesion conspicuity, contrast between different types of normal tissue, image quality, and artifacts. In addition, contrast ratios and contrast-to-noise ratios were determined. Compared to FSE, the GRASE technique allowed a 17% reduction in scan time but conspicuity of small lesions in particular was significantly lower on FLAIR-GRASE images because of higher image noise and increased artifacts. Gray-white differentiation was slightly worse on FLAIR-GRASE. Physiological ferritin deposition appeared slightly darker on FLAIR-GRASE images and susceptibility artifacts were stronger. Fatty tissue was less bright with FLAIR-GRASE. With current standard hardware equipment, the GRASE technique is not an adequate alternative to FSE for the implementation of fast FLAIR sequences in routine clinical MR brain imaging.     

Alterations in MR relaxation of normal canine gallbladder bile during fasting

The correlation between the concentration and proton relaxation of bile was studied by examining sequential changes in the MR image appearance and relaxation times of gallbladder bile during a 24-h fasting period in dogs. Bile relaxation times computed from images showed progressive shortening during the first 4–8 h of fasting: T₁ decreased from 500–900 ms to 250–400 ms and T₂ from 130–190 ms to 70–100 ms at 0.15 T. Similar in vitro results at 0.47 T were obtained on aspirated bile samples. Relaxation times of gallbladder bile remained longer than those of the liver, and we conclude that in general the gallbladder will appear less intense than the liver on T₁-weighted images (with short enough TE) and more intense on T₂-weighted images regardless of the bile concentration. The liver/gallbladder contrast may reverse in a normal subject during fasting for pulse sequences combining both T₁ and T₂ effects, which may be explored for the possible visual detection of abnormal gallbladder function on an image.     

MR imaging of non-cancerous hepatic lesions in Long-Evans Cinnamon rats

We measured MR images of the liver of Long-Evans Cinnamon (LEC) rats with pathologic correlation and assessed the effectiveness of MR imaging (MRI) for diagnosis of noncancerous hepatic lesions. T₁- and T₂-weighted images of their livers were obtained, and the dynamic and delayed studies after intravenous gadolinium injection were also performed. Cholangiofibrosis showed low signal intensity on T₁-weighted images and high signal intensity on T₂-weighted images. The T₂ relaxation time of cholangiofibrosis was significantly prolonged (p < .01), and the signal intensity ratio of this lesion to muscle on T₁-weighted images was significantly lower than that of normal liver parenchyma to muscle (p < .01). The lesion was enhanced immediately after gadolinium injection and the enhancement was prolonged. Among three cases of peliosis hepatis identified, one showed heterogeneous intensities on both T₁- and T₂-weighted images and the other two showed similar intensity pattern to cholangiofibrosis. The characteristic MR appearance of cholangiofibrosis may be useful to distinguish it from hepatocellular carcinoma (HCC).     

Automatic knee cartilage segmentation from multi-contrast MR images using support vector machine classification with spatial dependencies

Accurate segmentation of knee cartilage is required to obtain quantitative cartilage measurements, which is crucial for the assessment of knee pathology caused by musculoskeletal diseases or sudden injuries. This paper presents an automatic knee cartilage segmentation technique which exploits a rich set of image features from multi-contrast magnetic resonance (MR) images and the spatial dependencies between neighbouring voxels. The image features and the spatial dependencies are modelled into a support vector machine (SVM)-based association potential and a discriminative random field (DRF)-based interaction potential. Subsequently, both potentials are incorporated into an inference graphical model such that the knee cartilage segmentation is cast into an optimal labelling problem which can be efficiently solved by loopy belief propagation. The effectiveness of the proposed technique is validated on a database of multi-contrast MR images. The experimental results show that using diverse forms of image and anatomical structure information as the features are helpful in improving the segmentation, and the joint SVM-DRF model is superior to the classification models based solely on DRF or SVM in terms of accuracy when the same features are used. The developed segmentation technique achieves good performance compared with gold standard segmentations and obtained higher average DSC values than the state-of-the-art automatic cartilage segmentation studies.     

MRI anatomy of the rat kidney at 1.5 T in different states of hydration

The objective of this study was to determine correlation between structural anatomy and surface coil spin-echo MR imaging of the rat kidney and the effect of hydration state on MR signal intensities of the cortex and medulla. Twelve rats were studied in a pilot study with a 3-inch surface coil in a 1.5 T magnet under five different states of hydration. Serum and urine osmolality measurements were obtained immediately prior to each scan. Signal intensity measurements were made from both T₁- and T₂-weighted images of the cortex and medulla of both kidneys in each state of hydration. Gross and histological anatomy of the rat kidneys was correlated with the MR images. Four distinct layers were detected in vivo on MRI images of the rat kidney; these correlated with the histological layers. T₁-weighted cortico-medullary differentiation was most pronounced at 48 h dehydration; T₂ cortico-medullary differentiation was greatest at 72 h of dehydration. We concluded that different parts of the mammalian nephron can be identified by MR imaging and that cortico-medullary differentiation is affected by the hydration state of the animal.     

Accelerating quantitative MR imaging with the incorporation of B1 compensation using deep learning

Quantitative magnetic resonance imaging (MRI) attracts attention due to its support to quantitative image analysis and data driven medicine. However, the application of quantitative MRI is severely limited by the long data acquisition time required by repetitive image acquisition and measurement of field map. Inspired by recent development of artificial intelligence, we propose a deep learning strategy to accelerate the acquisition of quantitative MRI, where every quantitative T₁ map is derived from two highly undersampled variable-contrast images with radiofrequency field inhomogeneity automatically compensated. In a multi-step framework, variable-contrast images are first jointly reconstructed from incoherently undersampled images using convolutional neural networks; then T₁ map and B₁ map are predicted from reconstructed images employing deep learning. Thus, the acceleration includes undersampling in every input image, a reduction in the number of variable contrast images, as well as a waiver of B₁ map measurement. The strategy is validated in T₁ mapping of cartilage. Acquired with a consistent imaging protocol, 1224 image sets from 51 subjects are used for the training of the prediction models, and 288 image sets from 12 subjects are used for testing. High degree of acceleration is achieved with image fidelity well maintained. The proposed method can be broadly applied to quantify other tissue properties (e.g. T₂, T_1ρ) as well.     

中医按摩机器人专家控制系统的研究

为改进传统模糊C均值聚类(FCM)算法对初始聚类中心敏感、易陷入局部收敛、抗噪性差、计算量大的问题,提出一种新的基于改进粒子群算法的快速模糊聚类图像分割方法(PSOFFCM)。方法首先利用自适应中值滤波对图像进行滤波处理,增强算法的鲁棒性;然后,将图像像素灰度值映射到二维直方图特征空间,作为聚类样本,优化FCM的目标函数,减少图像分割的计算量;最后,利用PSO算法代替FCM的梯度迭代过程,减弱了算法对初始聚类中心的依赖,同时增强全局搜索能力。实验结果表明,该方法不仅克服了FCM算法对初始聚类中心的依赖,而且抗噪能力强,收敛速度快,分割精度明显优于传统FCM。     

Determination of T1ρ values for head and neck tissues at 0.1 T: a comparison to T1 and T2 relaxation times

In order to optimize head and neck magnetic resonance (MR) imaging with the spin-lock (SL) technique, the T₁ρ relaxation times for normal tissues were determined. Furthermore, T₁ρ was compared to T₁ and T₂ relaxation times. Ten healthy volunteers were studied with a 0.1 T clinical MR imager. T₁ρ values were determined by first measuring the tissue signal intensities with different locking pulse durations (TL), and then by fitting the signal intensity values to the equation with the least-squares method. The T₁ρ relaxation times were shortest for the muscle and tongue, intermediate for lymphatic and parotid gland tissue and longest for fat. T₁ρ demonstrated statistically significant differences (p < 0.05) between all tissues, except between muscle and tongue. T₁ρ values measured at locking field strength (B1L) of 35 μT were close to T₂ values, the only exception being fat tissue, which showed T₁ρ values much longer than T₂ values. Determination of tissue relaxation times may be utilized to optimize image contrast, and also to achieve better tissue discrimination potential, by choosing appropriate imaging parameters for the head and neck spin-lock sequences.     

A statistical fMRI model for differential T2* contrast incorporating T1 and T2* of gray matter

Relaxation parameter estimation and brain activation detection are two main areas of study in magnetic resonance imaging (MRI) and functional magnetic resonance imaging (fMRI). Relaxation parameters can be used to distinguish voxels containing different types of tissue whereas activation determines voxels that are associated with neuronal activity. In fMRI, the standard practice has been to discard the first scans to avoid magnetic saturation effects. However, these first images have important information on the MR relaxivities for the type of tissue contained in voxels, which could provide pathological tissue discrimination. It is also well-known that the voxels located in gray matter (GM) contain neurons that are to be active while the subject is performing a task. As such, GM MR relaxivities can be incorporated into a statistical model in order to better detect brain activation. Moreover, although the MR magnetization physically depends on tissue and imaging parameters in a nonlinear fashion, a linear model is what is conventionally used in fMRI activation studies. In this study, we develop a statistical fMRI model for Differential T₂^? ConTrast Incorporating T₁ and T₂^? of GM, so-called DeTeCT-ING Model, that considers the physical magnetization equation to model MR magnetization; uses complex-valued time courses to estimate T₁ and T₂^? for each voxel; then incorporates gray matter MR relaxivities into the statistical model in order to better detect brain activation, all from a single pulse sequence by utilizing the first scans.     

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.     

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

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

A Texture Combined Multispectral Magnetic Resonance Imaging Segmentation for Nasopharyngeal Carcinoma

Tumor segmentation from magnetic resonance imaging (MRI) is important for volume estimation and visualization of nasopharyngeal carcinoma (NPC). In some cases, segmentation using the general multispectral (GM) method often obtained poor results due to the high false positives caused by complex anatomic structures and serious overlap in feature space. In this study, a texture combined multispectral fuzzy clustering (TCMFC) segmentation algorithm was proposed. A texture measure of T1-weighted (T1) MR image was introduced by calculating the two-order central statistical information of every pixel within a window after the window convolution operation. The texture measure and the intensities in T1 and contrast-enhanced T1 images formed the new 3-D feature vector for fuzzy clustering implemented by semi-supervised fuzzy c-means (SFCM). Testing showed that by reducing the false positives significantly, the TCMFC method achieved improved segmentation results, compared with the GM method.     

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.     

High field NMR microscopic imaging of cultivated strawberry fruit

The experimental conditions required for discrimination of various types of tissue in fruits of cultivated strawberry (Fragaria × Ananassa) at high fields (ca. 7 T) have been investigated. In marked contrast to soft fruits of other species, from which informative images have been derived at high fields using a variety of pulse sequences and acquisition parameters, appreciable image intensities from parenchymal and vascular tissues in healthy strawberry fruits were obtained only with a spin-echo imaging sequence using large sweep widths (ca. 100,000 Hz), and consequently small values for TE (<5 ms), indicating predominantly short T₂ values for these tissues. Damage caused by infection by the fungal pathogen Botrytis cinerea is readily seen as a result of a large increase in T₂ in the infected tissue, whereas ripening processes appear to be characterized primarily by small variations in the T₂-weighted contrast and in the relative magnitudes of T₁ between vascular and parenchymal tissue. In addition, it was possible selectively to enhance the contributions to images from the achenes (“seeds”) by using very short relaxation delays, thereby enhancing T₁-dominated contrast mechanisms.