Automated total kidney volume measurements in pre-clinical magnetic resonance imaging for resourcing imaging data, annotations, and source code

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

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.

Test Retest Reproducibility of Organ Volume Measurements in ADPKD Using 3D Multimodality Deep Learning

RATIONALE AND OBJECTIVES

Following autosomal dominant polycystic kidney disease (ADPKD) progression by measuring organ volumes requires low measurement variability. The objective of this study is to reduce organ volume measurement variability on MRI of ADPKD patients by utilizing all pulse sequences to obtain multiple measurements which allows outlier analysis to find errors and averaging to reduce variability.

MATERIALS AND METHODS

In order to make measurements on multiple pulse sequences practical, a 3D multi-modality multi-class segmentation model based on nnU-net was trained/validated using T1, T2, SSFP, DWI and CT from 413 subjects. Reproducibility was assessed with test-re-test methodology on ADPKD subjects (n = 19) scanned twice within a 3-week interval correcting outliers and averaging the measurements across all sequences. Absolute percent differences in organ volumes were compared to paired students t-test.

RESULTS

Dice similarlity coefficient > 97%, Jaccard Index > 0.94, mean surface distance < 1 mm and mean Hausdorff Distance < 2 cm for all three organs and all five sequences were found on internal (n = 25), external (n = 37) and test-re-test reproducibility assessment (38 scans in 19 subjects). When averaging volumes measured from five MRI sequences, the model automatically segmented kidneys with test-re-test reproducibility (percent absolute difference between exam 1 and exam 2) of 1.3% which was better than all five expert observers. It reliably stratified ADPKD into Mayo Imaging Classification (area under the curve=100%) compared to radiologist.

CONCLUSION

3D deep learning measures organ volumes on five MRI sequences leveraging the power of outlier analysis and averaging to achieve 1.3% total kidney test-re-test reproducibility.

Non-contrast low-dose CT can be used for volumetry of ADPKD

BACKGROUND

Kidney volume provides important information for the diagnosis and prognosis of autosomal dominant polycystic kidney disease (ADPKD), as well as for the evaluation of the effects of drugs such as tolvaptan. Non-contrast computed tomography (CT) is commonly used for volumetry, and this study examined the correspondence and correlation of kidney volume measured by standard-dose or low-dose CT.

METHODS

Axial standard-dose and low-dose CT images with 1-mm slices were obtained from 24 ADPKD patients. The kidney was segmented in the Synapse 3D software and the kidney volume was calculated using stereology. The kidney volume was compared between the two sets of images using R2, Bland-Altman plots, coefficient of variation, and intra-class correlation coefficients (ICCs).

RESULTS

The mean age of the 24 patients was 48.4 ± 10.9 years, and 45.8% were men (n = 11). The mean total kidney volume on standard-dose CT was 1501 ± 838.2 mL. The R2 of volume between standard-dose and low-dose CT was 0.995. In the Bland-Altman plot, except for one case with a large kidney volume, the two measurements were consistent, and the coefficient of variation and ICC were also good (0.02, 0.998). The CT radiation dose (dose-length product) was 229 ± 68 mGy·cm for standard-dose CT and 50 ± 19 mGy·cm for low-dose CT. A comparable volume was obtained with 20% of the radiation dose of standard-dose CT.

CONCLUSIONS

Standard-dose and low-dose CT showed comparable kidney volume in ADPKD. Therefore, low-dose CT can substitute for ADPKD volumetry while minimizing radiation exposure.

Clinical Implementation of an Artificial Intelligence Algorithm for Magnetic Resonance-Derived Measurement of Total Kidney Volume

OBJECTIVE

To evaluate the performance of an internally developed and previously validated artificial intelligence (AI) algorithm for magnetic resonance (MR)-derived total kidney volume (TKV) in autosomal dominant polycystic kidney disease (ADPKD) when implemented in clinical practice.

PATIENTS AND METHODS

The study included adult patients with ADPKD seen by a nephrologist at our institution between November 2019 and January 2021 and undergoing an MR imaging examination as part of standard clinical care. Thirty-three nephrologists ordered MR imaging, requesting AI-based TKV calculation for 170 cases in these 161 unique patients. We tracked implementation and performance of the algorithm over 1 year. A radiologist and a radiology technologist reviewed all cases (N=170) for quality and accuracy. Manual editing of algorithm output occurred at radiology or radiology technologist discretion. Performance was assessed by comparing AI-based and manually edited segmentations via measures of similarity and dissimilarity to ensure expected performance. We analyzed ADPKD severity class assignment of algorithm-derived vs manually edited TKV to assess impact.

RESULTS

Clinical implementation was successful. Artificial intelligence algorithm-based segmentation showed high levels of agreement and was noninferior to interobserver variability and other methods for determining TKV. Of manually edited cases (n=84), the AI-algorithm TKV output showed a small mean volume difference of -3.3%. Agreement for disease class between AI-based and manually edited segmentation was high (five cases differed).

CONCLUSION

Performance of an AI algorithm in real-life clinical practice can be preserved if there is careful development and validation and if the implementation environment closely matches the development conditions.

Protein Kinase A Downregulation Delays the Development and Progression of Polycystic Kidney Disease

Background: Upregulation of cAMP-dependent and -independent PKA signaling is thought to promote cystogenesis in polycystic kidney disease (PKD). PKA-I regulatory subunit RIα is increased in kidneys of orthologous mouse models. Kidney-specific knockout of RIα upregulates PKA activity, induces cystic disease in wild-type mice, and aggravates it in Pkd1 ^RC/RC mice. Methods: PKA-I activation or inhibition was compared to EPAC activation or PKA-II inhibition using Pkd1 ^RC/RC metanephric organ cultures. The effect of constitutive PKA (preferentially PKA-I) downregulation in vivo was ascertained by kidney-specific expression of a dominant negative RIαB allele in Pkd1 ^RC/RC mice obtained by crossing Prkar1α ^R1αB/WT, Pkd1 ^RC/RC, and Pkhd1-Cre mice (C57BL/6 background). The effect of pharmacologic PKA inhibition using a novel, selective PRKACA inhibitor (BLU2864) was tested in mIMCD3 3D cultures, metanephric organ cultures, and Pkd1 ^RC/RC mice on a C57BL/6 x 129S6/Sv F1 background. Mice were sacrificed at 16 weeks of age. Results: PKA-I activation promoted and inhibition prevented ex vivo P-Ser133 CREB expression and cystogenesis. EPAC activation or PKA-II inhibition had no or only minor effects. BLU2864 inhibited in vitro mIMCD3 cystogenesis and ex vivo P-Ser133 CREB expression and cystogenesis. Genetic downregulation of PKA activity and BLU2864 directly and/or indirectly inhibited many pro-proliferative pathways and were both protective in vivo BLU2864 had no detectable on- or off-target adverse effects. Conclusions: PKA-I is the main PKA isozyme promoting cystogenesis. Direct PKA inhibition may be an effective strategy to treat PKD and other conditions where PKA signaling is upregulated. By acting directly on PKA, the inhibition may be more effective than or substantially increase the efficacy of treatments that only affect PKA activity by lowering cAMP.

Reliable kidney size determination by magnetic resonance imaging in pathophysiological settings

AIM

Kidney diseases constitute a major health challenge, which requires noninvasive imaging to complement conventional approaches to diagnosis and monitoring. Several renal pathologies are associated with changes in kidney size, offering an opportunity for magnetic resonance imaging (MRI) biomarkers of disease. This work uses dynamic MRI and an automated bean-shaped model (ABSM) for longitudinal quantification of pathophysiologically relevant changes in kidney size.

METHODS

A geometry-based ABSM was developed for kidney size measurements in rats using parametric MRI (T₂ , T₂ * mapping). The ABSM approach was applied to longitudinal renal size quantification using occlusion of the (a) suprarenal aorta or (b) the renal vein, (c) increase in renal pelvis and intratubular pressure and (d) injection of an X-ray contrast medium into the thoracic aorta to induce pathophysiologically relevant changes in kidney size.

RESULTS

The ABSM yielded renal size measurements with accuracy and precision equivalent to the manual segmentation, with >70-fold time savings. The automated method could detect a ~7% reduction (aortic occlusion) and a ~5%, a ~2% and a ~6% increase in kidney size (venous occlusion, pelvis and intratubular pressure increase and injection of X-ray contrast medium, respectively). These measurements were not affected by reduced image quality following administration of ferumoxytol.

CONCLUSION

Dynamic MRI in conjunction with renal segmentation using an ABSM supports longitudinal quantification of changes in kidney size in pathophysiologically relevant experimental setups mimicking realistic clinical scenarios. This can potentially be instrumental for developing MRI-based diagnostic tools for various kidney disorders and for gaining new insight into mechanisms of renal pathophysiology.

The genetic background significantly impacts the severity of kidney cystic disease in the Pkd1RC/RC mouse model of autosomal dominant polycystic kidney disease

Autosomal dominant polycystic kidney disease (ADPKD), primarily due to PKD1 or PKD2 mutations, causes progressive kidney cyst development and kidney failure. There is significant intrafamilial variability likely due to the genetic background and environmental/lifestyle factors; variability that can be modeled in PKD mice. Here, we characterized mice homozygous for the PKD1 hypomorphic allele, p.Arg3277Cys (Pkd1^RC/RC), inbred into the BALB/cJ (BC) or the 129S6/SvEvTac (129) strains, plus F1 progeny bred with the previously characterized C57BL/6J (B6) model; F1(BC/B6) or F1(129/B6). By one-month cystic disease in both the BC and 129 Pkd1^RC/RC mice was more severe than in B6 and continued with more rapid progression to six to nine months. Thereafter, the expansive disease stage plateaued/declined, coinciding with increased fibrosis and a clear decline in kidney function. Greater severity correlated with more inter-animal and inter-kidney disease variability, especially in the 129-line. Both F1 combinations had intermediate disease severity, more similar to B6 but progressive from one-month of age. Mild biliary dysgenesis, and an early switch from proximal tubule to collecting duct cysts, was seen in all backgrounds. Preclinical testing with a positive control, tolvaptan, employed the F1(129/B6)-Pkd1^RC/RC line, which has moderately progressive disease and limited isogenic variability. Magnetic resonance imaging was utilized to randomize animals and provide total kidney volume endpoints; complementing more traditional data. Thus, we show how genetic background can tailor the Pkd1^RC/RC model to address different aspects of pathogenesis and disease modification, and describe a possible standardized protocol for preclinical testing.