Multi-channel MR Images Research Articles

PIC-GAN: A Parallel Imaging Coupled Generative Adversarial Network for Accelerated Multi-Channel MRI Reconstruction.

In this study, we proposed a model combing parallel imaging (PI) with generative adversarial network (GAN) architecture (PIC-GAN) for accelerated multi-channel magnetic resonance imaging (MRI) reconstruction. This model integrated data fidelity and regularization terms into the generator to benefit from multi-coils information and provide an “end-to-end” reconstruction. Besides, to better preserve image details during reconstruction, we combined the adversarial loss with pixel-wise loss in both image and frequency domains. The proposed PIC-GAN framework was evaluated on abdominal and knee MRI images using 2, 4 and 6-fold accelerations with different undersampling patterns. The performance of the PIC-GAN was compared to the sparsity-based parallel imaging (L1-ESPIRiT), the variational network (VN), and conventional GAN with single-channel images as input (zero-filled (ZF)-GAN). Experimental results show that our PIC-GAN can effectively reconstruct multi-channel MR images at a low noise level and improved structure similarity of the reconstructed images. PIC-GAN has yielded the lowest Normalized Mean Square Error (in ) (PIC-GAN: 0.58 ± 0.37, ZF-GAN: 1.93 ± 1.41, VN: 1.87 ± 1.28, L1-ESPIRiT: 2.49 ± 1.04 for abdominal MRI data and PIC-GAN: 0.80 ± 0.26, ZF-GAN: 0.93 ± 0.29, VN:1.18 ± 0.31, L1-ESPIRiT: 1.28 ± 0.24 for knee MRI data) and the highest Peak Signal to Noise Ratio (PIC-GAN: 34.43 ± 1.92, ZF-GAN: 31.45 ± 4.0, VN: 29.26 ± 2.98, L1-ESPIRiT: 25.40 ± 1.88 for abdominal MRI data and PIC-GAN: 34.10 ± 1.09, ZF-GAN: 31.47 ± 1.05, VN: 30.01 ± 1.01, L1-ESPIRiT: 28.01 ± 0.98 for knee MRI data) compared to ZF-GAN, VN and L1-ESPIRiT with an under-sampling factor of 6. The proposed PIC-GAN framework has shown superior reconstruction performance in terms of reducing aliasing artifacts and restoring tissue structures as compared to other conventional and state-of-the-art reconstruction methods.

Regression based overall survival prediction of glioblastoma multiforme patients using a single discovery cohort of multi-institutional multi-channel MR images.

Glioblastoma multiforme (GBM) are malignant brain tumors, associated with poor overall survival (OS). This study aims to predict OS of GBM patients (in days) using a regression framework and assess the impact of tumor shape features on OS prediction. Multi-channel MR image derived texture features, tumor shape, and volumetric features, and patient age were obtained for 163 GBM patients. In order to assess the impact of tumor shape features on OS prediction, two feature sets, with and without tumor shape features, were created. For the feature set with tumor shape features, the mean prediction error (MPE) was 14.6days and its 95% confidence interval (CI) was 195.8days. For the feature set excluding shape features, the MPE was 17.1days and its 95% CI was observed to be 212.7days. The coefficient of determination (R2) value obtained for the feature set with shape features was 0.92, while it was 0.90 for the feature set excluding shape features. Although marginal, inclusion of shape features improves OS prediction in GBM patients. The proposed OS prediction method using regression provides good accuracy and overcomes the limitations of GBM OS classification, like choosing data-derived or pre-decided thresholds to define the OS groups. Graphical abstract Two feature sets: with and without tumor shape features were extracted from T1-weighted contrast-enhanced, T2-weighted and FLAIR MRI. These feature sets were analyzed using the Mean Prediction Error (MPE) and its 95% Confidence Interval (CI) obtained from the Bland-Altman plot, along with the coefficient of determination (R2) value to assess the impact of tumor shape features on overall survival prediction of glioblastoma multiforme patients.

Incorporating reference guided priors into calibrationless parallel imaging reconstruction

PurposeTo propose and evaluate a new calibrationless parallel imaging method aimed at further improving the reconstruction accuracy of the accelerated multi-channel MR images. MethodWe introduce a new calibrationless parallel imaging method. On top of exploiting joint sparsity cross channels of the target image to be reconstructed, it incorporates similar priors on the grey-level intensity and edge orientation, which both come from a high-spatial resolution reference image that can be easily obtained in many clinical MRI scenarios. The mixed l2-l1 norm is used to enforce joint sparsity and a multi-scale gradient operator is applied to extract fine edges from the reference image. Additionally, this optimization problem can be solved via a non-linear conjugate gradient algorithm with line search in this work. ResultsThe proposed method is compared with the existing state-of-the-art auto-calibration and calibrationless parallel imaging techniques. The experiments on different in-vivo brain MR datasets show that the proposed method has the superior performance in terms of both artifact suppression and detail preservation. ConclusionThe reference guided calibrationless parallel imaging method can significantly improve the performance of joint reconstruction of target channel images. Even when the reduction factor is high, it can keep edge structures well.

A Generalized Structured Low-Rank Matrix Completion Algorithm for MR Image Recovery.

Recent theory of mapping an image into a structured low-rank Toeplitz or Hankel matrix has become an effective method to restore images. In this paper, we introduce a generalized structured low-rank algorithm to recover images from their undersampled Fourier coefficients using infimal convolution regularizations. The image is modeled as the superposition of a piecewise constant component and a piecewise linear component. The Fourier coefficients of each component satisfy an annihilation relation, which results in a structured Toeplitz matrix. We exploit the low-rank property of the matrices to formulate a combined regularized optimization problem. In order to solve the problem efficiently and to avoid the high-memory demand resulting from the large-scale Toeplitz matrices, we introduce a fast and a memory-efficient algorithm based on the half-circulant approximation of the Toeplitz matrix. We demonstrate our algorithm in the context of single and multi-channel MR images recovery. Numerical experiments indicate that the proposed algorithm provides improved recovery performance over the state-of-the-art approaches.

Local contrast-enhanced MR images via high dynamic range processing.

PurposeTo develop a local contrast‐enhancing and feature‐preserving high dynamic range (HDR) image processing algorithm for multichannel and multisequence MR images of multiple body regions and tissues, and to evaluate its performance for structure visualization, bias field (correction) mitigation, and automated tissue segmentation.MethodsA multiscale‐shape and detail‐enhancement HDR‐MRI algorithm is applied to data sets of multichannel and multisequence MR images of the brain, knee, breast, and hip. In multisequence 3T hip images, agreement between automatic cartilage segmentations and corresponding synthesized HDR‐MRI series were computed for mean voxel overlap established from manual segmentations for a series of cases. Qualitative comparisons between the developed HDR‐MRI and standard synthesis methods were performed on multichannel 7T brain and knee data, and multisequence 3T breast and knee data.ResultsThe synthesized HDR‐MRI series provided excellent enhancement of fine‐scale structure from multiple scales and contrasts, while substantially reducing bias field effects in 7T brain gradient echo, T1 and T2 breast images and 7T knee multichannel images. Evaluation of the HDR‐MRI approach on 3T hip multisequence images showed superior outcomes for automatic cartilage segmentations with respect to manual segmentation, particularly around regions with hyperintense synovial fluid, across a set of 3D sequences.ConclusionThe successful combination of multichannel/sequence MR images into a single‐fused HDR‐MR image format provided consolidated visualization of tissues within 1 omnibus image, enhanced definition of thin, complex anatomical structures in the presence of variable or hyperintense signals, and improved tissue (cartilage) segmentation outcomes.

Volumetric brain tumour detection from MRI using visual saliency.

Medical image processing has become a major player in the world of automatic tumour region detection and is tantamount to the incipient stages of computer aided design. Saliency detection is a crucial application of medical image processing, and serves in its potential aid to medical practitioners by making the affected area stand out in the foreground from the rest of the background image. The algorithm developed here is a new approach to the detection of saliency in a three dimensional multi channel MR image sequence for the glioblastoma multiforme (a form of malignant brain tumour). First we enhance the three channels, FLAIR (Fluid Attenuated Inversion Recovery), T2 and T1C (contrast enhanced with gadolinium) to generate a pseudo coloured RGB image. This is then converted to the CIE L*a*b* color space. Processing on cubes of sizes k = 4, 8, 16, the L*a*b* 3D image is then compressed into volumetric units; each representing the neighbourhood information of the surrounding 64 voxels for k = 4, 512 voxels for k = 8 and 4096 voxels for k = 16, respectively. The spatial distance of these voxels are then compared along the three major axes to generate the novel 3D saliency map of a 3D image, which unambiguously highlights the tumour region. The algorithm operates along the three major axes to maximise the computation efficiency while minimising loss of valuable 3D information. Thus the 3D multichannel MR image saliency detection algorithm is useful in generating a uniform and logistically correct 3D saliency map with pragmatic applicability in Computer Aided Detection (CADe). Assignment of uniform importance to all three axes proves to be an important factor in volumetric processing, which helps in noise reduction and reduces the possibility of compromising essential information. The effectiveness of the algorithm was evaluated over the BRATS MICCAI 2015 dataset having 274 glioma cases, consisting both of high grade and low grade GBM. The results were compared with that of the 2D saliency detection algorithm taken over the entire sequence of brain data. For all comparisons, the Area Under the receiver operator characteristic (ROC) Curve (AUC) has been found to be more than 0.99 ± 0.01 over various tumour types, structures and locations.

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.

Non-locally regularized segmentation of multiple sclerosis lesion from multi-channel MRI data

Segmentation of multiple sclerosis (MS) lesion is important for many neuroimaging studies. In this paper, we propose a novel algorithm for automatic segmentation of MS lesions from multi-channel MR images (T1W, T2W and FLAIR images). The proposed method is an extension of Li et al.'s algorithm in [1], which only segments the normal tissues from T1W images. The proposed method is aimed to segment MS lesions, while normal tissues are also segmented and bias field is estimated to handle intensity inhomogeneities in the images. Another contribution of this paper is the introduction of a nonlocal means technique to achieve spatially regularized segmentation, which overcomes the influence of noise. Experimental results have demonstrated the effectiveness and advantages of the proposed algorithm.

Automated brain tumor segmentation using spatial accuracy-weighted hidden Markov Random Field

A variety of algorithms have been proposed for brain tumor segmentation from multi-channel sequences, however, most of them require isotropic or pseudo-isotropic resolution of the MR images. Although co-registration and interpolation of low-resolution sequences, such as T2-weighted images, onto the space of the high-resolution image, such as T1-weighted image, can be performed prior to the segmentation, the results are usually limited by partial volume effects due to interpolation of low-resolution images. To improve the quality of tumor segmentation in clinical applications where low-resolution sequences are commonly used together with high-resolution images, we propose the algorithm based on Spatial accuracy-weighted Hidden Markov random field and Expectation maximization (SHE) approach for both automated tumor and enhanced-tumor segmentation. SHE incorporates the spatial interpolation accuracy of low-resolution images into the optimization procedure of the Hidden Markov Random Field (HMRF) to segment tumor using multi-channel MR images with different resolutions, e.g., high-resolution T1-weighted and low-resolution T2-weighted images. In experiments, we evaluated this algorithm using a set of simulated multi-channel brain MR images with known ground-truth tissue segmentation and also applied it to a dataset of MR images obtained during clinical trials of brain tumor chemotherapy. The results show that more accurate tumor segmentation results can be obtained by comparing with conventional multi-channel segmentation algorithms.

Talairach-Based Parcellation of Neonatal Brain Magnetic Resonance Imaging Data: Validation of a New Approach

Talairach-based parcellation (TP) of human brain magnetic resonance imaging (MRI) data has been used increasingly in clinical research to make regional measurements of brain structures in vivo. Recently, TP has been applied to pediatric research to elucidate the changes in regional brain volumes related to several neurological disorders. However, all freely available tools have been designed to parcellate adult brain MRI data. Parcellation of neonatal MRI data is very challenging owing to the lack of strong signal contrast, variability in signal intensity within tissues, and the small size and thus difficulty in identifying small structures used as landmarks for TP. Hence the authors designed and validated a new interactive tool to parcellate brain MRI data from newborns and young infants. The authors' tool was developed as part of a postprocessing pipeline, which includes registration of multichannel MR images, segmentation, and parcellation of the segmented data. The tool employs user-friendly interactive software to visualize and assign the anatomic landmarks required for parcellation, after which the planes and parcels are generated automatically by the algorithm. The authors then performed 3 sets of validation experiments to test the precision and reliability of their tool. Validation experiments of intra-and interrater reliability on data obtained from newborn and 1-year-old children showed a very high sensitivity of >95% and specificity >99.9%. The authors also showed that rotating and reformatting the original MRI data results in a statistically significant difference in parcel volumes, demonstrating the importance of using a tool such as theirs that does not require realignment of the data prior to parcellation. To the authors' knowledge, the presented approach is the first TP method that has been developed and validated specifically for neonatal brain MRI data. Their approach would also be valuable for the analysis of brain MRI data from older children and adults.

Talairach‐Based Parcellation of Neonatal Brain Magnetic Resonance Imaging Data: Validation of a New Approach

ABSTRACTBackground and Purpose. Talairach‐based parcellation (TP) of human brain magnetic resonance imaging (MRI) data has been used increasingly in clinical research to make regional measurements of brain structures in vivo. Recently, TP has been applied to pediatric research to elucidate the changes in regional brain volumes related to several neurological disorders. However, all freely available tools have been designed to parcellate adult brain MRI data. Parcellation of neonatal MRI data is very challenging owing to the lack of strong signal contrast, variability in signal intensity within tissues, and the small size and thus difficulty in identifying small structures used as landmarks for TP. Hence the authors designed and validated a new interactive tool to parcellate brain MRI data from newborns and young infants. Methods. The authors' tool was developed as part of a postprocessing pipeline, which includes registration of multichannel MR images, segmentation, and parcellation of the segmented data. The tool employs user‐friendly interactive software to visualize and assign the anatomic landmarks required for parcellation, after which the planes and parcels are generated automatically by the algorithm. The authors then performed 3 sets of validation experiments to test the precision and reliability of their tool. Results. Validation experiments of intra‐and interrater reliability on data obtained from newborn and 1‐year‐old children showed a very high sensitivity of >95% and specificity >99.9%. The authors also showed that rotating and reformatting the original MRI data results in a statistically significant difference in parcel volumes, demonstrating the importance of using a tool such as theirs that does not require realignment of the data prior to parcellation. Conclusions. To the authors' knowledge, the presented approach is the first TP method that has been developed and validated specifically for neonatal brain MRI data. Their approach would also be valuable for the analysis of brain MRI data from older children and adults.