Denoising MRI using spectral subtraction

RAVE-T2/T1 - Feasibility of a new hybrid MR-sequence for free-breathing abdominal MRI in children and adolescents

BACKGROUND

The new radial volumetric encoding RAVE-T₂/T₁ hybrid sequence is a modern three-dimensional sequence with multiparametric approach, which includes T₂- and T₁-weighted contrasts obtained in identical slice position during one measurement. However, the RAVE-T₂/T₁ hybrid sequence is not yet being used in clinical routine.

PURPOSE

The aim of this study was to evaluate the RAVE-T₂/T₁ hybrid sequence in a pediatric population with a clinical indication for an abdominal MRI examination to demonstrate that the hybrid imaging may be less challenging to perform on children.

MATERIALS AND METHODS

Our retrospective observational study included pediatric patients of all age groups and required for an abdominal MRI examination. Non-contrast standard axial T₁ DIXON and non-contrast RAVE-T₂/T₁ hybrid sequence were obtained at 3 T. MRI studies were analyzed independently by two pediatric radiologists using a 5-point Likert-type scale in five different categories. T₁- and T₂-weighted sequences were each compared with the RAVE-T₂/T₁-sequence using a Wilcoxon signed-rank test.

RESULTS

The analysis included 15 children (mean age, 11 years and 4 months, 7 girls and 8 boys). The Cohens Kappa of interrater agreement measured 0.62. The T₂ weighted part of the RAVE-T₂/T₁ sequence was significantly better than the standard T₂ HASTE sequence in four of five image quality categories: overall image quality (2.2 ± 0.7 vs 1.8 ± 0,7, p = 0.03), respiratory motion artefacts (3.8 ± 0.4 vs 2.0 ± 0.7, p <= 0.01), portal vein clarity (3.3 ± 0.8 vs 2.2 ± 0.7, p <= 0.01), hepatic margin sharpness (2.4 ± 1,0 vs 1.8 ± 0.7, p <= 0.01). The T₁ weighted part of the RAVE-T₂/T₁ sequence was significantly better than the standard T₁ DIXON weighted sequence in three of five image quality categories: respiratory motion artefacts (4.0 ± 0.2 vs 3.6 ± 0.8, p = 0.01), portal vein clarity (2.7 ± 0.9 vs 2.1 ± 0.7, p <= 0.01), hepatic margin sharpness (3.2 ± 0.7 vs 2.6 ± 0.9, p <= 0.01).

CONCLUSIONS

The RAVE-T₂/T₁ hybrid sequence is feasible and equal compared to standard T₁- and T₂-weighted sequences in the assessment of abdominal organs in a pediatric population. Due to non-inferiority to the current standard sequences for abdominal imaging, the RAVE-T₂/T₁ hybrid sequence is a good alternative for children who cannot be examined in breath-hold technique.

Denoising Medical Images Using Machine Learning, Deep Learning Approaches: A Survey

OBJECTIVE

Several denoising methods for medical images have been applied, such as Wavelet Transform, CNN, linear and Non-linear methods.

METHODS

In this paper, A median filter algorithm will be modified and the image denoising method to wavelet transform and Non-local means (NLM), deep convolutional neural network (Dn- CNN), Gaussian noise, and Salt and pepper noise used in the medical image is explained.

RESULTS

PSNR values of the CNN method are higher and showed better results than different filters (Adaptive Wiener filter, Median filter, and Adaptive Median filter, Wiener filter).

CONCLUSION

Denoising methods performance with indices SSIM, PSNR, and MSE have been tested, and the results of simulation image denoising are also presented in this article.

A preliminary study of deep learning-based reconstruction specialized for denoising in high-frequency domain: usefulness in high-resolution three-dimensional magnetic resonance cisternography of the cerebellopontine angle

PURPOSE

Deep learning-based reconstruction (DLR) has been developed to reduce image noise and increase the signal-to-noise ratio (SNR). We aimed to evaluate the efficacy of DLR for high spatial resolution (HR)-MR cisternography.

METHODS

This retrospective study included 35 patients who underwent HR-MR cisternography. The images were reconstructed with or without DLR. The SNRs of the CSF and pons, contrast of the CSF and pons, and sharpness of the normal-side trigeminal nerve using full width at half maximum (FWHM) were compared between the two image types. Noise quality, sharpness, artifacts, and overall image quality of these two types of images were qualitatively scored.

RESULTS

The SNRs of the CSF and pons were significantly higher with DLR than without DLR (CSF 21.81 ± 7.60 vs. 15.33 ± 4.03, p < 0.001; pons 5.96 ± 1.38 vs. 3.99 ± 0.48, p < 0.001). There were no significant differences in the contrast of the CSF and pons (p = 0.225) and sharpness of the normal-side trigeminal nerve using FWHM (p = 0.185) without and with DLR, respectively. Noise quality and the overall image quality were significantly higher with DLR than without DLR (noise quality 3.95 ± 0.19 vs. 2.53 ± 0.44, p < 0.001; overall image quality 3.97 ± 0.17 vs. 2.97 ± 0.12, p < 0.001). There were no significant differences in sharpness (p = 0.371) and artifacts (p = 1) without and with DLR.

CONCLUSION

DLR can improve the image quality of HR-MR cisternography by reducing image noise without sacrificing contrast or sharpness.

Exploring in vivo placental microstructure in healthy and growth-restricted pregnancies through diffusion-weighted magnetic resonance imaging

INTRODUCTION

Gross and microstructural changes in placental development can influence placental function and adversely impact fetal growth and well-being; however, there is a paucity of invivo tools available to reliably interrogate in vivo placental microstructural development. The objective of this study is to characterize invivo placental microstructural diffusion and perfusion in healthy and growth-restricted pregnancies (FGR) using non-invasive diffusion-weighted imaging (DWI).

METHODS

We prospectively enrolled healthy pregnant women and women whose pregnancies were complicated by FGR. Each woman underwent DWI-MRI between 18 and 40 weeks gestation. Placental measures of small (D) and large (D*) scale diffusion and perfusion (f) were estimated using the intra-voxel incoherent motion (IVIM) model.

RESULTS

We studied 137 pregnant women (101 healthy; 36 FGR). D and D* are increased in late-onset FGR, and the placental perfusion fraction, f, is decreased (p < 0.05 for all).

DISCUSSION

Placental DWI revealed microstructural alterations of the invivo placenta in FGR, particularly in late-onset FGR. Early and reliable identification of placental pathology in vivo may better guide future interventions.

Adaptive phase correction of diffusion-weighted images

Phase correction (PC) is a preprocessing technique that exploits the phase of images acquired in Magnetic Resonance Imaging (MRI) to obtain real-valued images containing tissue contrast with additive Gaussian noise, as opposed to magnitude images which follow a non-Gaussian distribution, e.g. Rician. PC finds its natural application to diffusion-weighted images (DWIs) due to their inherent low signal-to-noise ratio and consequent non-Gaussianity that induces a signal overestimation bias that propagates to the calculated diffusion indices. PC effectiveness depends upon the quality of the phase estimation, which is often performed via a regularization procedure. We show that a suboptimal regularization can produce alterations of the true image contrast in the real-valued phase-corrected images. We propose adaptive phase correction (APC), a method where the phase is estimated by using MRI noise information to perform a complex-valued image regularization that accounts for the local variance of the noise. We show, on synthetic and acquired data, that APC leads to phase-corrected real-valued DWIs that present a reduced number of alterations and a reduced bias. The substantial absence of parameters for which human input is required favors a straightforward integration of APC in MRI processing pipelines.

Abbreviated MRI Protocols for the Abdomen

Technical advances in MRI have improved image quality and have led to expanding clinical indications for its use. However, long examination and interpretation times, as well as higher costs, still represent barriers to use of MRI. Abbreviated MRI protocols have emerged as an alternative to standard MRI protocols. These abbreviated MRI protocols seek to reduce longer MRI protocols by eliminating unnecessary or redundant sequences that negatively affect cost, MRI table time, patient comfort, image quality, and image interpretation time. However, the diagnostic information is generally not compromised. Abbreviated MRI protocols have already been used successfully for hepatocellular carcinoma screening, for prostate cancer detection, and for screening for nonalcoholic fatty liver disease as well as monitoring patients with this disease. It has been reported that image acquisition time and costs can be considerably reduced with abbreviated MRI protocols, compared with standard MRI protocols, while maintaining a similar sensitivity and accuracy. Nevertheless, multiple applications still need to be explored in the abdomen and pelvis (eg, surveillance of metastases to the liver; follow-up of cystic pancreatic lesions, adrenal incidentalomas, and small renal masses; evaluation of ovarian cysts in postmenopausal women; staging of cervical and uterine corpus neoplasms; evaluation of müllerian duct anomalies). This article describes some successful applications of abbreviated MRI protocols, demonstrates how they can help in improving the MRI workflow, and explores potential future directions. ^©RSNA, 2019.

Comparison of image intensity, local, and multi-atlas priors in brain tissue classification

PURPOSE

Automated and accurate tissue classification in three-dimensional brain magnetic resonance images is essential in volumetric morphometry or as a preprocessing step for diagnosing brain diseases. However, noise, intensity in homogeneity, and partial volume effects limit the classification accuracy of existing methods. This paper provides a comparative study on the contributions of three commonly used image information priors for tissue classification in normal brains: image intensity, local, and multi-atlas priors.

METHODS

We compared the effectiveness of the three priors by comparing the four methods modeling them: K-Means (KM), KM combined with a Markov Random Field (KM-MRF), multi-atlas segmentation (MAS), and the combination of KM, MRF, and MAS (KM-MRF-MAS). The key parameters and factors in each of the four methods are analyzed, and the performance of all the models is compared quantitatively and qualitatively on both simulated and real data.

RESULTS

The KM-MRF-MAS model that combines the three image information priors performs best.

CONCLUSIONS

The image intensity prior is insufficient to generate reasonable results for a few images. Introducing local and multi-atlas priors results in improved brain tissue classification. This study provides a general guide on what image information priors can be used for effective brain tissue classification.

A robust adaptive sampling method for faster acquisition of MR images

A robust adaptive k-space sampling method is proposed for faster acquisition and reconstruction of MR images. In this method, undersampling patterns are generated based on magnitude profile of a fully acquired 2-D k-space data. Images are reconstructed using compressive sampling reconstruction algorithm. Simulation experiments are done to assess the performance of the proposed method under various signal-to-noise ratio (SNR) levels. The performance of the method is better than non-adaptive variable density sampling method when k-space SNR is greater than 10dB. The method is implemented on a fully acquired multi-slice raw k-space data and a quality assurance phantom data. Data reduction of up to 60% is achieved in the multi-slice imaging data and 75% is achieved in the phantom imaging data. The results show that reconstruction accuracy is improved over non-adaptive or conventional variable density sampling method. The proposed sampling method is signal dependent and the estimation of sampling locations is robust to noise. As a result, it eliminates the necessity of mathematical model and parameter tuning to compute k-space sampling patterns as required in non-adaptive sampling methods.