Subsegmentation of the Kidney in Experimental MR Images Using Morphology-Based Regions-of-Interest or Multiple-Layer Concentric Objects

Riazy, Leili; Milani, Bastien; Periquito, Joao; Cantow, Kathleen; Niendorf, Thoralf; Pruijm, Menno; Seeliger, Erdmann; Pohlmann, Andreas

doi:10.1007/978-1-0716-0978-1_33

Cited by 3 publications

(6 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Median T 2 * and T 2 values for regions‐of‐interest (ROI) within the renal cortex (CO), outer medulla (OM), and inner medulla (IM) were calculated from the parameter maps. ROI placement was done with a standardized semi‐automatic method, as previously described 75 . This procedure positions the ROIs (5 for CO and OM each, 3 for IM) such that they exclude the transition regions between renal layers to avoid partial volume effects.…”

Section: Methodsmentioning

confidence: 99%

“…ROI placement was done with a standardized semi-automatic method, as previously described. 75 This procedure positions the ROIs (5 for CO and OM each, 3 for IM) such that they exclude the transition regions between renal layers to avoid partial volume effects. For T 2 *, T 2 mapping-based determination of KS, segmentation of the coronal mid-slice cross-sectional area of the kidney (here referred to as "kidney size," KS) was done using a previously described automatic bean-shaped model.…”

Section: Image Analysismentioning

confidence: 99%

See 1 more Smart Citation

Monitoring kidney size to interpret MRI‐based assessment of renal oxygenation in acute pathophysiological scenarios

et al. 2022

Self Cite

View full text Add to dashboard Cite

Aim: Tissue hypoxia is an early key feature of acute kidney injury. Assessment of renal oxygenation using magnetic resonance imaging (MRI) markers T 2 and T 2 * enables insights into renal pathophysiology. This assessment can be confounded by changes in the blood and tubular volume fractions, occurring upon pathological insults. These changes are mirrored by changes in kidney size (KS). Here, we used dynamic MRI to monitor KS for physiological interpretation of T 2 * and T 2 changes in acute pathophysiological scenarios. Methods: KS was determined from T 2 *, T 2 mapping in rats. Six interventions that acutely alter renal tissue oxygenation were performed directly within the scanner, including interventions that change the blood and/or tubular volume. A biophysical model was used to estimate changes in O 2 saturation of hemoglobin from changes in T 2 * and KS.Results: Upon aortic occlusion KS decreased; this correlated with a decrease in T 2 *, T 2 . Upon renal vein occlusion KS increased; this negatively correlated with a decrease in T 2 *, T 2 . Upon simultaneous occlusion of both vessels KS remained unchanged; there was no correlation with decreased T 2 *, T 2 . Hypoxemia induced mild reductions in KS and T 2 *, T 2 . Administration of an X-ray contrast medium induced sustained KS increase, with an initial increase in T 2 *, T 2 followed by a decrease. Furosemide caused T 2 *, T 2 elevation and a minor increase in KS. Model calculations yielded physiologically plausible calibration ratios for T 2 *. Conclusion: Monitoring KS allows physiological interpretation of acute renal oxygenation changes obtained by T 2 *, T 2 . KS monitoring should accompany MRIoximetry, for new insights into renal pathophysiology and swift translation into human studies.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Image Analysismentioning

confidence: 99%

Monitoring kidney size to interpret MRI‐based assessment of renal oxygenation in acute pathophysiological scenarios

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…The placement of ROIs was conducted using a standardized semiautomatic approach, following a previously described method. 78 This method involved positioning the ROIs (five for the CO and OM, and three for the IM) in a way that excludes the transitional regions between renal layers, ensuring that partial volume effects are avoided. Because of the T 2 shortage induced by ferumoxytol, T 2 values were not analyzed after the administration of USPIO.…”

Section: Discussionmentioning

confidence: 99%

“…T 2 values for the renal cortex (CO), outer medulla (OM), and inner medulla (IM) were determined using baseline T 2 maps before the respective interventions and the T 2 map during or right after the respective intervention. The placement of ROIs was conducted using a standardized semiautomatic approach, following a previously described method 78 . This method involved positioning the ROIs (five for the CO and OM, and three for the IM) in a way that excludes the transitional regions between renal layers, ensuring that partial volume effects are avoided.…”

Section: Methodsmentioning

confidence: 99%

Dynamic parametric MRI and deep learning: Unveiling renal pathophysiology through accurate kidney size quantification

Klein,

Gladytz,

Millward

et al. 2023

NMR in Biomedicine

Self Cite

View full text Add to dashboard Cite

Renal pathologies often manifest as alterations in kidney size, providing a valuable avenue for employing dynamic parametric MRI as a means to derive kidney size measurements for the diagnosis, treatment, and monitoring of renal disease. Furthermore, this approach holds significant potential in supporting MRI data‐driven preclinical investigations into the intricate mechanisms underlying renal pathophysiology. The integration of deep learning algorithms is crucial in achieving rapid and precise segmentation of the kidney from temporally resolved parametric MRI, facilitating the use of kidney size as a meaningful (pre)clinical biomarker for renal disease. To explore this potential, we employed dynamic parametric T2 mapping of the kidney in rats in conjunction with a custom‐tailored deep dilated U‐Net (DDU‐Net) architecture. The architecture was trained, validated, and tested on manually segmented ground truth kidney data, with benchmarking against an analytical segmentation model and a self‐configuring no new U‐Net. Subsequently, we applied our approach to in vivo longitudinal MRI data, incorporating interventions that emulate clinically relevant scenarios in rats. Our approach achieved high performance metrics, including a Dice coefficient of 0.98, coefficient of determination of 0.92, and a mean absolute percentage error of 1.1% compared with ground truth. The DDU‐Net enabled automated and accurate quantification of acute changes in kidney size, such as aortic occlusion (−8% ± 1%), venous occlusion (5% ± 1%), furosemide administration (2% ± 1%), hypoxemia (−2% ± 1%), and contrast agent‐induced acute kidney injury (11% ± 1%). This approach can potentially be instrumental for the development of dynamic parametric MRI‐based tools for kidney disorders, offering unparalleled insights into renal pathophysiology.

show abstract

“…Parametric maps of absolute T 2 were calculated by pixel‐wise mono‐exponential fitting to the signal intensities of the T 2 ‐weighted images acquired at different TEs 23 . Median T 2 values for regions of interest (ROIs) within CO, OM, and IM were calculated from the T 2 ‐weighted images acquired at different TEs 46,47 . TVF maps were extracted using pixel‐wise bi‐exponential fitting to the signal intensities of the T 2 ‐weighted images acquired at different TEs.…”

Section: Methodsmentioning

confidence: 99%

In vivo monitoring of renal tubule volume fraction using dynamic parametric MRI

Tasbihi,

Gladytz,

Millward

et al. 2024

Magnetic Resonance in Med

View full text Add to dashboard Cite

PurposeThe increasing incidence of kidney diseases is a global concern, and current biomarkers and treatments are inadequate. Changes in renal tubule luminal volume fraction (TVF) serve as a rapid biomarker for kidney disease and improve understanding of renal (patho)physiology. This study uses the amplitude of the long T2 component as a surrogate for TVF in rats, by applying multiexponential analysis of the T2‐driven signal decay to examine micromorphological changes in renal tissue.MethodsSimulations were conducted to identify a low mean absolute error (MAE) protocol and an accelerated protocol customized for the in vivo study of T2 mapping of the rat kidney at 9.4 T. We then validated our bi‐exponential approach in a phantom mimicking the relaxation properties of renal tissue. This was followed by a proof‐of‐principle demonstration using in vivo data obtained during a transient increase of renal pelvis and tubular pressure.ResultsUsing the low MAE protocol, our approach achieved an accuracy of MAE < 1% on the mechanical phantom. The T2 mapping protocol customized for in vivo study achieved an accuracy of MAE < 3%. Transiently increasing pressure in the renal pelvis and tubules led to significant changes in TVF in renal compartments: ΔTVFcortex = 4.9%, ΔTVFouter_medulla = 4.5%, and ΔTVFinner_medulla = −14.6%.ConclusionThese results demonstrate that our approach is promising for research into quantitative assessment of renal TVF in in vivo applications. Ultimately, these investigations have the potential to help reveal mechanism in acute renal injury that may lead to chronic kidney disease, which will support research into renal disorders.

show abstract

Subsegmentation of the Kidney in Experimental MR Images Using Morphology-Based Regions-of-Interest or Multiple-Layer Concentric Objects

Cited by 3 publications

References 14 publications

Monitoring kidney size to interpret MRI‐based assessment of renal oxygenation in acute pathophysiological scenarios

Monitoring kidney size to interpret MRI‐based assessment of renal oxygenation in acute pathophysiological scenarios

Dynamic parametric MRI and deep learning: Unveiling renal pathophysiology through accurate kidney size quantification

In vivo monitoring of renal tubule volume fraction using dynamic parametric MRI

Contact Info

Product

Resources

About