Registration and quantification network (RQnet) for IVIM-DKI analysis in MRI

Self-supervised learning for denoising of multidimensional MRI data

PURPOSE

To develop a fast denoising framework for high-dimensional MRI data based on a self-supervised learning scheme, which does not require ground truth clean image.

THEORY AND METHODS

Quantitative MRI faces limitations in SNR, because the variation of signal amplitude in a large set of images is the key mechanism for quantification. In addition, the complex non-linear signal models make the fitting process vulnerable to noise. To address these issues, we propose a fast deep-learning framework for denoising, which efficiently exploits the redundancy in multidimensional MRI data. A self-supervised model was designed to use only noisy images for training, bypassing the challenge of clean data paucity in clinical practice. For validation, we used two different datasets of simulated magnetization transfer contrast MR fingerprinting (MTC-MRF) dataset and in vivo DWI image dataset to show the generalizability.

RESULTS

The proposed method drastically improved denoising performance in the presence of mild-to-severe noise regardless of noise distributions compared to previous methods of the BM3D, tMPPCA, and Patch2self. The improvements were even pronounced in the following quantification results from the denoised images.

CONCLUSION

The proposed MD-S2S (Multidimensional-Self2Self) denoising technique could be further applied to various multi-dimensional MRI data and improve the quantification accuracy of tissue parameter maps.

ssVERDICT: Self-supervised VERDICT-MRI for enhanced prostate tumor characterization

PURPOSE

Demonstrating and assessing self-supervised machine-learning fitting of the VERDICT (vascular, extracellular and restricted diffusion for cytometry in tumors) model for prostate cancer.

METHODS

We derive a self-supervised neural network for fitting VERDICT (ssVERDICT) that estimates parameter maps without training data. We compare the performance of ssVERDICT to two established baseline methods for fitting diffusion MRI models: conventional nonlinear least squares and supervised deep learning. We do this quantitatively on simulated data by comparing the Pearson's correlation coefficient, mean-squared error, bias, and variance with respect to the simulated ground truth. We also calculate in vivo parameter maps on a cohort of 20 prostate cancer patients and compare the methods' performance in discriminating benign from cancerous tissue via Wilcoxon's signed-rank test.

RESULTS

In simulations, ssVERDICT outperforms the baseline methods (nonlinear least squares and supervised deep learning) in estimating all the parameters from the VERDICT prostate model in terms of Pearson's correlation coefficient, bias, and mean-squared error. In vivo, ssVERDICT shows stronger lesion conspicuity across all parameter maps, and improves discrimination between benign and cancerous tissue over the baseline methods.

CONCLUSION

ssVERDICT significantly outperforms state-of-the-art methods for VERDICT model fitting and shows, for the first time, fitting of a detailed multicompartment biophysical diffusion MRI model with machine learning without the requirement of explicit training labels.

Comparison of methods for intravoxel incoherent motion parameter estimation in the brain from flow-compensated and non-flow-compensated diffusion-encoded data

PURPOSE

Joint analysis of flow-compensated (FC) and non-flow-compensated (NC) diffusion MRI (dMRI) data has been suggested for increased robustness of intravoxel incoherent motion (IVIM) parameter estimation. For this purpose, a set of methods commonly used or previously found useful for IVIM analysis of dMRI data obtained with conventional diffusion encoding were evaluated in healthy human brain.

METHODS

Five methods for joint IVIM analysis of FC and NC dMRI data were compared: (1) direct non-linear least squares fitting, (2) a segmented fitting algorithm with estimation of the diffusion coefficient from higher b-values of NC data, (3) a Bayesian algorithm with uniform prior distributions, (4) a Bayesian algorithm with spatial prior distributions, and (5) a deep learning-based algorithm. Methods were evaluated on brain dMRI data from healthy subjects and simulated data at multiple noise levels. Bipolar diffusion encoding gradients were used with b-values 0-200 s/mm2 and corresponding flow weighting factors 0-2.35 s/mm for NC data and by design 0 for FC data. Data were acquired twice for repeatability analysis.

RESULTS

Measurement repeatability as well as estimation bias and variability were at similar levels or better with the Bayesian algorithm with spatial prior distributions and the deep learning-based algorithm for IVIM parametersD $$ D $$ andf $$ f $$ , and for the Bayesian algorithm only forv d $$ {v}_d $$ , relative to the other methods.

CONCLUSION

A Bayesian algorithm with spatial prior distributions is preferable for joint IVIM analysis of FC and NC dMRI data in the healthy human brain, but deep learning-based algorithms appear promising.

Probing Renal Microstructure and Function with Advanced Diffusion MRI: Concepts, Applications, Challenges, and Future Directions

Diffusion measurements in the kidney are affected not only by renal microstructure but also by physiological processes (i.e., glomerular filtration, water reabsorption, and urine formation). Because of the superposition of passive tissue diffusion, blood perfusion, and tubular pre-urine flow, the limitations of the monoexponential apparent diffusion coefficient (ADC) model in assessing pathophysiological changes in renal tissue are becoming apparent and motivate the development of more advanced diffusion-weighted imaging (DWI) variants. These approaches take advantage of the fact that the length scale probed in DWI measurements can be adjusted by experimental parameters, including diffusion-weighting, diffusion gradient directions and diffusion time. This forms the basis by which advanced DWI models can be used to capture not only passive diffusion effects, but also microcirculation, compartmentalization, tissue anisotropy. In this review, we provide a comprehensive overview of the recent advancements in the field of renal DWI. Following a short introduction on renal structure and physiology, we present the key methodological approaches for the acquisition and analysis of renal DWI data, including intravoxel incoherent motion (IVIM), diffusion tensor imaging (DTI), non-Gaussian diffusion, and hybrid IVIM-DTI. We then briefly summarize the applications of these methods in chronic kidney disease and renal allograft dysfunction. Finally, we discuss the challenges and potential avenues for further development of renal DWI. LEVEL OF EVIDENCE: 5 TECHNICAL EFFICACY: Stage 2.

Early assessment of acute kidney injury in severe acute pancreatitis with multimodal DWI: an animal model

OBJECTIVES

To evaluate the feasibility of multimodal diffusion-weighted imaging (DWI) for detecting the occurrence and severity of acute kidney injury (AKI) caused by severe acute pancreatitis (SAP) in rats.

METHODS

SAP was induced in thirty rats by the retrograde injection of 5.0% sodium taurocholate through the biliopancreatic duct. Six rats underwent MRI of the kidneys 24 h before and 2, 4, 6, and 8 h after this AKI model was generated. Conventional and functional MRI sequences were used, including intravoxel incoherent motion imaging (IVIM), diffusion tensor imaging (DTI), and diffusion kurtosis imaging (DTI). The main DWI parameters and histological results were analyzed.

RESULTS

The fast apparent diffusion coefficient (ADC) of the renal cortex was significantly reduced at 2 h, as was the fractional anisotropy (FA) value of the renal cortex on DTI. The mean kurtosis (MK) values for the renal cortex and medulla gradually increased after model generation. The renal histopathological score was negatively correlated with the medullary slow ADC, fast ADC, and perfusion scores for both the renal cortex and medulla, as were the ADC and FA values of the renal medulla in DTI, whereas the MK values of the cortex and medulla were positively correlated (r = 0.733, 0.812). Thus, the cortical fast ADC, medullary MK, FADTI, and slow ADC were optimal parameters for diagnosing AKI. Of these parameters, cortical fast ADC had the highest diagnostic efficacy (AUC = 0.950).

CONCLUSIONS

The fast ADC of the renal cortex is the core indicator of early AKI, and the medullary MK value might serve as a sensitive biomarker for grading renal injury in SAP rats.

CLINICAL RELEVANCE STATEMENT

The multimodal parameters of renal IVIM, DTI, and DKI are potential beneficial for the early diagnosis and severity grading of renal injury in SAP patients.

KEY POINTS

• The multimodal parameters of renal DWI, including IVIM, DTI, and DKI, may be valuable for the noninvasive detection of early AKI and the severity grading of renal injury in SAP rats. • Cortical fast ADC, medullary MK, FA, and slow ADC are optimal parameters for early diagnosis of AKI, and cortical fast ADC has the highest diagnostic efficacy. • Medullary fast ADC, MK, and FA as well as cortical MK are useful for predicting the severity grade of AKI, and the renal medullary MK value exhibits the strongest correlation with pathological scores.