Évaluation du contenu tissulaire rénal en oxygène par la technique IRM BOLD

Multi-parametric MRI-based machine learning model for prediction of pathological grade of renal injury in a rat kidney cold ischemia-reperfusion injury model

BACKGROUND

Renal cold ischemia-reperfusion injury (CIRI), a pathological process during kidney transplantation, may result in delayed graft function and negatively impact graft survival and function. There is a lack of an accurate and non-invasive tool for evaluating the degree of CIRI. Multi-parametric MRI has been widely used to detect and evaluate kidney injury. The machine learning algorithms introduced the opportunity to combine biomarkers from different MRI metrics into a single classifier.

OBJECTIVE

To evaluate the performance of multi-parametric magnetic resonance imaging for grading renal injury in a rat model of renal cold ischemia-reperfusion injury using a machine learning approach.

METHODS

Eighty male SD rats were selected to establish a renal cold ischemia -reperfusion model, and all performed multiparametric MRI scans (DWI, IVIM, DKI, BOLD, T1mapping and ASL), followed by pathological analysis. A total of 25 parameters of renal cortex and medulla were analyzed as features. The pathology scores were divided into 3 groups using K-means clustering method. Lasso regression was applied for the initial selecting of features. The optimal features and the best techniques for pathological grading were obtained. Multiple classifiers were used to construct models to evaluate the predictive value for pathology grading.

RESULTS

All rats were categorized into mild, moderate, and severe injury group according the pathologic scores. The 8 features that correlated better with the pathologic classification were medullary and cortical Dp, cortical T2*, cortical Fp, medullary T2*, ∆T1, cortical RBF, medullary T1. The accuracy(0.83, 0.850, 0.81, respectively) and AUC (0.95, 0.93, 0.90, respectively) for pathologic classification of the logistic regression, SVM, and RF are significantly higher than other classifiers. For the logistic model and combining logistic, RF and SVM model of different techniques for pathology grading, the stable and perform are both well. Based on logistic regression, IVIM has the highest AUC (0.93) for pathological grading, followed by BOLD(0.90).

CONCLUSION

The multi-parametric MRI-based machine learning model could be valuable for noninvasive assessment of the degree of renal injury.

Noninvasive assessment of kidney dysfunction in children by using blood oxygenation level-dependent MRI and intravoxel incoherent motion diffusion-weighted imaging

Objectives

To explore whether multiparametric approach including blood oxygenation level-dependent MRI (BOLD-MRI) and intravoxel incoherent motion diffusion-weighted imaging (IVIM-DWI) can be applied in the assessment of renal function in children with chronic kidney disease (CKD).

Materials and methods

This prospective study included 74 children (CKD stage 1–3, 51; CKD stage 4–5, 12; healthy volunteers, 11) for renal MRI examinations including coronal T2WI, axial T1WI and T2WI, BOLD-MRI, and DWI sequences. We measured the renal cortex and medulla T2*, ADC, D_t, D_p, and f_p values on BOLD and DWI images. Appropriate statistical methods were applied for comparing MRI-derived parameters among the three groups and calculating the correlation coefficients between MRI-derived parameters and clinical data. Receiver operating characteristic (ROC) curves were used to assess the diagnostic performance of MRI-derived parameters.

Results

There were significant differences in cortex T2*, ADC, D_t, f_p and medulla T2*, ADC, D_t among the three groups. Cortex T2*, ADC, D_t, f_p and medulla T2*, ADC, D_t had a trend: CKD stage 4–5 < CKD stage 1–3 < healthy volunteers. Cortex and medulla T2*, ADC, D_t were significantly correlated with eGFR, serum creatinine (Scr), cystatin C. In addition, cortex T2* and eGFR showed the highest correlation coefficient (r = 0.824, p < 0.001). Cortex D_t and medulla T2* were optimal parameters for differentiating healthy volunteers and CKD stage 1–3 or CKD stage 4–5 and CKD stage 1–3, respectively.

Conclusions

BOLD-MRI and IVIM-DWI might be used as a feasible method for noninvasive assessment of renal function in children with CKD.

The use of fetal MRI for renal and urogenital tract anomalies

Fetal anomalies are detected in approximately 2% of all fetuses and, among these, genitourinary tract abnormalities account for 30% to 50% of all structural anomalies present at birth. Although ultrasound remains the first line diagnostic modality, fetal MRI provides important additional structural and functional information, especially with the development of faster sequences and the use of functional sequences. The added value of MRI-based imaging is three-fold: (a) improvement of diagnostic accuracy by adequate morphological examination, (b) detection of additional anomalies, and (c) in addition, MRI has the potential to provide information regarding renal function. In this review, we describe the role of fetal MRI in the anatomical evaluation of renal and urogenital tract anomalies, and we also touch upon the contribution of functional MRI to the diagnostic workup of these conditions.

Detailing the relation between renal T2* and renal tissue pO2 using an integrated approach of parametric magnetic resonance imaging and invasive physiological measurements

OBJECTIVES

This study was designed to detail the relation between renal T2* and renal tissue pO2 using an integrated approach that combines parametric magnetic resonance imaging (MRI) and quantitative physiological measurements (MR-PHYSIOL).

MATERIALS AND METHODS

Experiments were performed in 21 male Wistar rats. In vivo modulation of renal hemodynamics and oxygenation was achieved by brief periods of aortic occlusion, hypoxia, and hyperoxia. Renal perfusion pressure (RPP), renal blood flow (RBF), local cortical and medullary tissue pO2, and blood flux were simultaneously recorded together with T2*, T2 mapping, and magnetic resonance-based kidney size measurements (MR-PHYSIOL). Magnetic resonance imaging was carried out on a 9.4-T small-animal magnetic resonance system. Relative changes in the invasive quantitative parameters were correlated with relative changes in the parameters derived from MRI using Spearman analysis and Pearson analysis.

RESULTS

Changes in T2* qualitatively reflected tissue pO2 changes induced by the interventions. T2* versus pO2 Spearman rank correlations were significant for all interventions, yet quantitative translation of T2*/pO2 correlations obtained for one intervention to another intervention proved not appropriate. The closest T2*/pO2 correlation was found for hypoxia and recovery. The interlayer comparison revealed closest T2*/pO2 correlations for the outer medulla and showed that extrapolation of results obtained for one renal layer to other renal layers must be made with due caution. For T2* to RBF relation, significant Spearman correlations were deduced for all renal layers and for all interventions. T2*/RBF correlations for the cortex and outer medulla were even superior to those between T2* and tissue pO2. The closest T2*/RBF correlation occurred during hypoxia and recovery. Close correlations were observed between T2* and kidney size during hypoxia and recovery and for occlusion and recovery. In both cases, kidney size correlated well with renal vascular conductance, as did renal vascular conductance with T2*. Our findings indicate that changes in T2* qualitatively mirror changes in renal tissue pO2 but are also associated with confounding factors including vascular volume fraction and tubular volume fraction.

CONCLUSIONS

Our results demonstrate that MR-PHYSIOL is instrumental to detail the link between renal tissue pO2 and T2* in vivo. Unravelling the link between regional renal T2* and tissue pO2, including the role of the T2* confounding parameters vascular and tubular volume fraction and oxy-hemoglobin dissociation curve, requires further research. These explorations are essential before the quantitative capabilities of parametric MRI can be translated from experimental research to improved clinical understanding of hemodynamics/oxygenation in kidney disorders.

How bold is blood oxygenation level-dependent (BOLD) magnetic resonance imaging of the kidney? Opportunities, challenges and future directions

Renal tissue hypoperfusion and hypoxia are key elements in the pathophysiology of acute kidney injury and its progression to chronic kidney disease. Yet, in vivo assessment of renal haemodynamics and tissue oxygenation remains a challenge. Many of the established approaches are invasive, hence not applicable in humans. Blood oxygenation level-dependent (BOLD) magnetic resonance imaging (MRI) offers an alternative. BOLD-MRI is non-invasive and indicative of renal tissue oxygenation. Nonetheless, recent (pre-) clinical studies revived the question as to how bold renal BOLD-MRI really is. This review aimed to deliver some answers. It is designed to inspire the renal physiology, nephrology and imaging communities to foster explorations into the assessment of renal oxygenation and haemodynamics by exploiting the powers of MRI. For this purpose, the specifics of renal oxygenation and perfusion are outlined. The fundamentals of BOLD-MRI are summarized. The link between tissue oxygenation and the oxygenation-sensitive MR biomarker T2∗ is outlined. The merits and limitations of renal BOLD-MRI in animal and human studies are surveyed together with their clinical implications. Explorations into detailing the relation between renal T2∗ and renal tissue partial pressure of oxygen (pO2 ) are discussed with a focus on factors confounding the T2∗ vs. tissue pO2 relation. Multi-modality in vivo approaches suitable for detailing the role of the confounding factors that govern T2∗ are considered. A schematic approach describing the link between renal perfusion, oxygenation, tissue compartments and renal T2∗ is proposed. Future directions of MRI assessment of renal oxygenation and perfusion are explored.