Deep learning-based method for reducing residual motion effects in diffusion parameter estimation

Deep learning-based compressed SENSE improved diffusion-weighted image quality and liver cancer detection: A prospective study

PURPOSE

To assess whether diffusion-weighted imaging (DWI) with Compressed SENSE (CS) and deep learning (DL-CS-DWI) can improve image quality and lesion detection in patients at risk for hepatocellular carcinoma (HCC).

METHODS

This single-center prospective study enrolled consecutive at-risk participants who underwent 3.0 T gadoxetate disodium-enhanced MRI. Conventional DWI was acquired using parallel imaging (PI) with SENSE (PI-DWI). In CS-DWI and DL-CS-DWI, CS but not PI with SENSE was used to accelerate the scan with 2.5 as the acceleration factor. Qualitative and quantitative image quality were independently assessed by two masked reviewers, and were compared using the Wilcoxon signed-rank test. The detection rates of clinically-relevant (LR-4/5/M based on the Liver Imaging Reporting and Data System v2018) liver lesions for each DWI sequence were independently evaluated by another two masked reviewers against their consensus assessments based on all available non-DWI sequences, and were compared by the McNemar test.

RESULTS

67 participants (median age, 58.0 years; 56 males) with 197 clinically-relevant liver lesions were enrolled. Among the three DWI sequences, DL-CS-DWI showed the best qualitative and quantitative image qualities (p range, <0.001-0.039). For clinically-relevant liver lesions, the detection rates (91.4%-93.4%) of DL-CS-DWI showed no difference with CS-DWI (87.3%-89.8%, p = 0.230-0.231) but were superior to PI-DWI (82.7%-85.8%, p = 0.015-0.025). For lesions located in the hepatic dome, DL-CS-DWI demonstrated the highest detection rates (94.8%-97.4% vs 76.9%-79.5% vs 64.1%-69.2%, p = 0.002-0.045) among the three DWI sequences.

CONCLUSION

In patients at high-risk for HCC, DL-CS-DWI improved image quality and detection for clinically-relevant liver lesions, especially for the hepatic dome.

Deep Learning for Image Enhancement and Correction in Magnetic Resonance Imaging-State-of-the-Art and Challenges

Magnetic resonance imaging (MRI) provides excellent soft-tissue contrast for clinical diagnoses and research which underpin many recent breakthroughs in medicine and biology. The post-processing of reconstructed MR images is often automated for incorporation into MRI scanners by the manufacturers and increasingly plays a critical role in the final image quality for clinical reporting and interpretation. For image enhancement and correction, the post-processing steps include noise reduction, image artefact correction, and image resolution improvements. With the recent success of deep learning in many research fields, there is great potential to apply deep learning for MR image enhancement, and recent publications have demonstrated promising results. Motivated by the rapidly growing literature in this area, in this review paper, we provide a comprehensive overview of deep learning-based methods for post-processing MR images to enhance image quality and correct image artefacts. We aim to provide researchers in MRI or other research fields, including computer vision and image processing, a literature survey of deep learning approaches for MR image enhancement. We discuss the current limitations of the application of artificial intelligence in MRI and highlight possible directions for future developments. In the era of deep learning, we highlight the importance of a critical appraisal of the explanatory information provided and the generalizability of deep learning algorithms in medical imaging.

Effect of number of diffusion encoding directions in Diffusion Metrics of 5-year-olds using Tract-Based Spatial Statistical analysis

Methodological aspects and effects of different imaging parameters on DTI (diffusion tensor imaging) results and their reproducibility have been recently studied comprehensively in adult populations. Although MR imaging of children's brains has become common, less interest has been focussed on researching whether adult‐based optimised parameters and pre‐processing protocols can be reliably applied to paediatric populations. Furthermore, DTI scalar values of preschool aged children are rarely reported. We gathered a DTI dataset from 5‐year‐old children (N = 49) to study the effect of the number of diffusion‐encoding directions on the reliability of resultant scalar values with TBSS (tract‐based spatial statistics) method. Additionally, the potential effect of within‐scan head motion on DTI scalars was evaluated. Reducing the number of diffusion‐encoding directions deteriorated both the accuracy and the precision of all DTI scalar values. To obtain reliable scalar values, a minimum of 18 directions for TBSS was required. For TBSS fractional anisotropy values, the intraclass correlation coefficient with two‐way random‐effects model (ICC[2,1]) for the subsets of 6 to 66 directions ranged between 0.136 [95%CI 0.0767;0.227] and 0.639 [0.542;0.740], whereas the corresponding values for subsets of 18 to 66 directions were 0.868 [0.815;0.913] and 0.995 [0.993;0.997]. Following the exclusion of motion‐corrupted volumes, minor residual motion did not associate with the scalar values. A minimum of 18 diffusion directions is recommended to result in reliable DTI scalar results with TBSS. We suggest gathering extra directions in paediatric DTI to enable exclusion of volumes with motion artefacts and simultaneously preserve the overall data quality.

Recommendation for Cardiac Magnetic Resonance Imaging-Based Phenotypic Study: Imaging Part

Cardiac magnetic resonance (CMR) imaging provides important biomarkers for the early diagnosis of many cardiovascular diseases and has been reported to reveal phenome-wide associations of cardiac/aortic structure and functionality in population studies. Nevertheless, due to the complexity of operation and variations among manufactural vendors, magnetic field strengths, coils, sequences, scan parameters, and image analysis approaches, CMR is rarely used in large cohort studies. Existing guidelines mainly focused on the diagnosis of cardiovascular diseases, which did not aim to basic research. The purpose of this study was to propose a recommendation for CMR based phenotype measurements for cohort study. We classify the imaging sequences of CMR into three categories according to the importance and universality of corresponding measurable phenotypes. The acquisition time and repeatability of the phenotypic measurement were also taken into consideration during the categorization. Unlike other guidelines, this recommendation focused on quantitative measurement of large amount of phenotypes from CMR.

Progressive microstructural alterations in subcortical nuclei in Parkinson's disease: A diffusion magnetic resonance imaging study

OBJECTIVES

To explore the microstructural alterations in subcortical nuclei in Parkinson's disease (PD) at different stages with diffusion kurtosis imaging (DKI) and tensor imaging and to test the performance of diffusion metrics in identifying PD.

METHODS

108 PD patients (64 patients in early-stage PD group (EPD) and 44 patients in moderate-late-stage PD group (MLPD)) and 64 healthy controls (HC) were included. Tensor and kurtosis metrics in the subcortical nuclei were compared. Partial correlation was used to correlate the diffusion metrics and Unified Parkinson's Disease Rating Scale part-III (UPDRS-III) score. Logistic regression and receiver operating characteristic analysis were applied to test the diagnostic performance of the diffusion metrics.

RESULTS

Compared with HC, both EPD and MLPD patients showed higher fractional anisotropy and axial diffusivity, lower mean kurtosis (MK) and axial kurtosis in substantia nigra, lower MK and radial kurtosis (RK) in globus pallidus (GP) and thalamus (all p < 0.05). Compared with EPD, MLPD patients showed lower MK and RK in GP and thalamus (all p < 0.05). MK and RK in GP and thalamus were negatively correlated with UPDRS-III score (all p < 0.01). The logistic regression model combining kurtosis and tensor metrics showed the best performance in diagnosing PD, EPD, and MLPD (areas under curve were 0.817, 0.769, and 0.914, respectively).

CONCLUSIONS

PD has progressive microstructural alterations in the subcortical nuclei. DKI is sensitive to detect microstructural alterations in GP and thalamus during PD progression. Combining kurtosis and tensor metrics can achieve a good performance in diagnosing PD.