Image texture features predict renal function decline in patients with autosomal dominant polycystic kidney disease

Novel splice site and nonsense variants in PKHD1 cause autosomal recessive polycystic kidney disease in a Chinese Zhuang ethnic family

BACKGROUND

This study aims to report the clinical characteristics of a child with autosomal recessive polycystic kidney disease (ARPKD) within a Chinese Zhuang ethnic family.

METHODS

We used whole exome sequencing (WES) in the family to examine the genetic cause of the disease. Candidate pathogenic variants were validated by Sanger sequencing.

RESULTS

We identified previously unreported mutations in the PKHD1 gene of the proband with ARPKD through WES: a splice site mutation c.6809-2A > T, a nonsense mutation c.4192C > T(p.Gln1398Ter), and a missense mutation c.2181T > G(p.Asn727Lys). Her mother is a heterozygous carrier of c.2181T > G(p.Asn727Lys) mutation. Her father is a carrier of c.6809-2A > T mutation and c.4192C > T(p.Gln1398Ter) mutation.

CONCLUSIONS

The identification of novel mutations in the PKHD1 gene through WES not only expands the spectrum of known variants but also potentially enhances genetic counseling and prenatal diagnostic approaches for families affected by ARPKD.

Evaluation of split renal dysfunction using radiomics based on magnetic resonance diffusion-weighted imaging

BACKGROUND

Accurate and noninvasive assessment of split renal dysfunction is crucial, while there is lack of corresponding method clinically.

PURPOSE

To investigate the feasibility of using diffusion-weighted imaging (DWI)-based radiomics models to evaluate split renal dysfunction.

METHODS

We enrolled patients with impaired and normal renal function undergoing renal DWI examination. Glomerular filtration rate (GFR, mL/min) was measured using 99mTc-DTPA scintigraphy, which is reference standard of GFR measurement. The kidneys were classified into normal (GFR ≥40), mildly impaired (20≤ GFR < 40), moderately impaired (10≤ GFR < 20), and severely impaired (GFR < 10) renal function groups. Optimized subsets of radiomics features were selected from renal DWI images and radiomics scores (Rad-score) calculated to discriminate groups with different renal function. The radiomics model (Rad-score based) was developed in a training cohort and validated in a test cohort. Evaluations were conducted on the discrimination, calibration, and clinical application of the method.

RESULTS

The final analysis included 330 kidneys. Logistic regression was used to develop three radiomics models, model A, B, and C, which were used to distinguish normal from impaired, mild from moderate, and moderate from severe renal function, respectively. The area under the curve of the three models were 0.822, 0.704, and 0.887 in the training cohort and 0.843, 0.717, and 0.897 in the test cohort, respectively, indicating efficient discrimination performance.

CONCLUSIONS

DWI-based radiomics models have potential for evaluating split renal dysfunction and discriminating between normal and impaired renal function groups and their subgroups.

Non-contrast-enhanced magnetic resonance urography for measuring split kidney function in pediatric patients with hydronephrosis: comparison with renal scintigraphy

BACKGROUND

Split kidney function (SKF) is critical for treatment decision in pediatric patients with hydronephrosis and is commonly measured using renal scintigraphy (RS). Non-contrast-enhanced magnetic resonance urography (NCE-MRU) is increasingly used in clinical practice. This study aimed to investigate the feasibility of using NCE-MRU as an alternative to estimate SKF in pediatric patients with hydronephrosis, compared to RS.

METHODS

Seventy-five pediatric patients with hydronephrosis were included in this retrospective study. All patients underwent NCE-MRU and RS within 2 weeks. Kidney parenchyma volume (KPV) and texture analysis parameters were obtained from T2-weighted (T2WI) in NCE-MRU. The calculated split KPV (SKPV) percent and texture analysis parameters percent of left kidney were compared with the RS-determined SKF.

RESULTS

SKPV showed a significant positive correlation with SKF (r = 0.88, p < 0.001), while inhomogeneity was negatively correlated with SKF (r =  - 0.68, p < 0.001). The uncorrected and corrected prediction models of SKF were established using simple and multiple linear regression. Bland-Altman plots demonstrated good agreement of both predictive models. The residual sum of squares of the corrected prediction model was lower than that of the uncorrected model (0.283 vs. 0.314) but not statistically significant (p = 0.662). Subgroup analysis based on different MR machines showed correlation coefficients of 0.85, 0.95, and 0.94 between SKF and SKPV for three different scanners, respectively (p < 0.05 for all).

CONCLUSIONS

NCE-MRU can be used as an alternative method for estimating SKF in pediatric patients with hydronephrosis when comparing with RS. Specifically, SKPV proves to be a simple and universally applicable indicator for predicting SKF.

Automated prognosis of renal function decline in ADPKD patients using deep learning

An accurate prognosis of renal function decline in Autosomal Dominant Polycystic Kidney Disease (ADPKD) is crucial for early intervention. Current biomarkers used are height-adjusted total kidney volume (HtTKV), estimated glomerular filtration rate (eGFR), and patient age. However, manually measuring kidney volume is time-consuming and subject to observer variability. Additionally, incorporating automatically generated features from kidney MRI images, along with conventional biomarkers, can enhance prognostic improvement. To address these issues, we developed two deep-learning algorithms. Firstly, an automated kidney volume segmentation model accurately calculates HtTKV. Secondly, we utilize segmented kidney volumes, predicted HtTKV, age, and baseline eGFR to predict chronic kidney disease (CKD) stages >=3A, >=3B, and a 30% decline in eGFR after 8 years from the baseline visit. Our approach combines a convolutional neural network (CNN) and a multi-layer perceptron (MLP). Our study included 135 subjects and the AUC scores obtained were 0.96, 0.96, and 0.95 for CKD stages >=3A, >=3B, and a 30% decline in eGFR, respectively. Furthermore, our algorithm achieved a Pearson correlation coefficient of 0.81 between predicted and measured eGFR decline. We extended our approach to predict distinct CKD stages after eight years with an AUC of 0.97. The proposed approach has the potential to enhance monitoring and facilitate prognosis in ADPKD patients, even in the early disease stages.

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.

Ultrasound-Based Radiomics for the Classification of Henoch-Schönlein Purpura Nephritis in Children

Henoch-Schönlein purpura nephritis (HSPN) is one of the most common kidney diseases in children. The current diagnosis and classification of HSPN depend on pathological biopsy, which is seriously limited by its invasive and high-risk nature. The aim of the study was to explore the potential of radiomics model for evaluating the histopathological classification of HSPN based on the ultrasound (US) images. A total of 440 patients with Henoch-Schönlein purpura nephritis proved by biopsy were analyzed retrospectively. They were grouped according to two histopathological categories: those without glomerular crescent formation (ISKDC grades I-II) and those with glomerular crescent formation (ISKDC grades III-V). The patients were randomly assigned to either a training cohort (n = 308) or a validation cohort (n = 132) with a ratio of 7:3. The sonologist manually drew the regions of interest (ROI) on the ultrasound images of the right kidney including the cortex and medulla. Then, the ultrasound radiomics features were extracted using the Pyradiomics package. The dimensions of radiomics features were reduced by Spearman correlation coefficients and least absolute shrinkage and selection operator (LASSO) method. Finally, three radiomics models using k-nearest neighbor (KNN), logistic regression (LR), and support vector machine (SVM) were established, respectively. The predictive performance of such classifiers was assessed with receiver operating characteristic (ROC) curve. 105 radiomics features were extracted from derived US images of each patient and 14 features were ultimately selected for the machine learning analysis. Three machine learning models including k-nearest neighbor (KNN), logistic regression (LR), and support vector machine (SVM) were established for HSPN classification. Of the three classifiers, the SVM classifier performed the best in the validation cohort [area under the curve (AUC) =0.870 (95% CI, 0.795-0.944), sensitivity = 0.706, specificity = 0.950]. The US-based radiomics had good predictive value for HSPN classification, which can be served as a noninvasive tool to evaluate the severity of renal pathology and crescentic formation in children with HSPN.

Magnetic resonance imaging preprocessing and radiomic features for classification of autosomal dominant polycystic kidney disease genotype

Purpose

Our study aims to investigate the impact of preprocessing on magnetic resonance imaging (MRI) radiomic features extracted from the noncystic kidney parenchyma of patients with autosomal dominant polycystic kidney disease (ADPKD) in the task of classifying PKD1 versus PKD2 genotypes, which differ with regard to cyst burden and disease outcome.

Approach

The effect of preprocessing on radiomic features was investigated using a single T2-weighted fat saturated (T2W-FS) MRI scan from PKD1 and PKD2 subjects (29 kidneys in total) from the Consortium for Radiologic Imaging Studies of Polycystic Kidney Disease study. Radiomic feature reproducibility using the intraclass correlation coefficient (ICC) was computed across MRI normalizations (z -score, reference-tissue, and original image), gray-level discretization, and upsampling and downsampling pixel schemes. A second dataset for genotype classification from 136 subjects T2W-FS MRI images previously enrolled in the HALT Progression of Polycystic Kidney Disease study was matched for age, gender, and Mayo imaging classification class. Genotype classification was performed using a logistic regression classifier and radiomic features extracted from (1) the noncystic kidney parenchyma and (2) the entire kidney. The area under the receiver operating characteristic curve (AUC) was used to evaluate the classification performance across preprocessing methods.

Results

Radiomic features extracted from the noncystic kidney parenchyma were sensitive to preprocessing parameters, with varying reproducibility depending on the parameter. The percentage of features with good-to-excellent ICC scores ranged from 14% to 58%. AUC values ranged between 0.47 to 0.68 and 0.56 to 0.73 for the noncystic kidney parenchyma and entire kidney, respectively.

Conclusions

Reproducibility of radiomic features extracted from the noncystic kidney parenchyma was dependent on the preprocessing parameters used, and the effect on genotype classification was sensitive to preprocessing parameters. The results suggest that texture features may be indicative of genotype expression in ADPKD.

Evaluation of advanced imaging biomarkers at kidney failure in patients with ADPKD: a pilot study

Background

Autosomal dominant polycystic kidney disease (ADPKD) presents with variable disease severity and progression. Advanced imaging biomarkers may provide insights into cystic and non-cystic processes leading to kidney failure in different age groups.

Methods

This pilot study included 39 ADPKD patients with kidney failure, stratified into three age groups (<46, 46-56, >56 years old). Advanced imaging biomarkers were assessed using an automated instance cyst segmentation tool. The biomarkers were compared with an age- and sex-matched ADPKD cohort in early chronic kidney disease (CKD).

Results

Ht-total parenchymal volume correlated negatively with age at kidney failure. The median Ht-total parenchymal volume was significantly lower in patients older than 56 years. Cystic burden was significantly higher at time of kidney failure, especially in patients who reached it before age 46 years. The cyst index at kidney failure was comparable across age groups and Mayo Imaging Classes. Advanced imaging biomarkers showed higher correlation with Ht-total kidney volume in early CKD than at kidney failure. Cyst index and parenchymal index were relatively stable over 5 years prior to kidney failure, whereas Ht-total cyst volume and cyst parenchymal surface area increased significantly.

Conclusion

Age-related differences in advanced imaging biomarkers suggest variable pathophysiological mechanisms in ADPKD patients with kidney failure. Further studies are needed to validate the utility of these biomarkers in predicting disease progression and guiding treatment strategies.

Size Matters: How to Characterize ADPKD Severity by Measuring Total Kidney Volume

Following patients with Autosomal Dominant Polycystic Kidney Disease (ADPKD) has been challenging because serum biomarkers such as creatinine often remain normal until relatively late in the disease [...].

Assessing the Risk of Progression to Kidney Failure in Patients With Autosomal Dominant Polycystic Kidney Disease

While autosomal dominant polycystic kidney disease (ADPKD) is a dichotomous diagnosis, substantial variability in disease severity exists. Identification of inherited risk through family history, genetic testing, and environmental risk factors through clinical assessment are important components of risk assessment for optimal management of patients with ADPKD. Genetic testing is especially helpful in cases with diagnostic uncertainty, particularly in cases with no apparent family history, in young cases (age less than 25 years) where a definitive diagnosis is sought, or in atypical presentations with early, severe, or discordant findings. Currently, risk assessment in ADPKD may be performed with the use of age-adjusted estimated glomerular filtration rate thresholds, evidence of rapid estimated glomerular filtration rate decline on serial measurements, age- and height-adjusted total kidney volume by Mayo Clinic Imaging Classification, or evidence of early hypertension and urological complications combined with PKD1 or PKD2 mutation class; however, caveats exist with each of these approaches. Fine-tuning of risk stratification with advanced imaging features and biomarkers is the subject of research but is not yet ready for general clinical practice. While conservative treatment strategies will be advised for all patients, those with the greatest rate of disease progression will have the most benefit from aggressive disease-modifying therapy. In this narrative review, we will summarize the evidence behind the clinical assessment and risk stratification of patients with ADPKD.

Diffusion magnetic resonance imaging for kidney cyst volume quantification and non-cystic tissue characterisation in ADPKD

OBJECTIVES

Beyond total kidney and cyst volume (TCV), non-cystic tissue plays an important role in autosomal dominant polycystic kidney disease (ADPKD) progression. This study aims at presenting and preliminarily validating a diffusion MRI (DWI)-based TCV quantification method and providing evidence of DWI potential in characterising non-cystic tissue microstructure.

METHODS

T2-weighted MRI and DWI scans (b = 0, 15, 50, 100, 200, 350, 500, 700, 1000; 3 directions) were acquired from 35 ADPKD patients with CKD stage 1 to 3a and 15 healthy volunteers on a 1.5 T scanner. ADPKD classification was performed using the Mayo model. DWI scans were processed by mono- and segmented bi-exponential models. TCV was quantified on T2-weighted MRI by the reference semi-automatic method and automatically computed by thresholding the pure diffusivity (D) histogram. The agreement between reference and DWI-based TCV values and the differences in DWI-based parameters between healthy and ADPKD tissue components were assessed.

RESULTS

There was strong correlation between DWI-based and reference TCV (rho = 0.994, p < 0.001). Non-cystic ADPKD tissue had significantly higher D, and lower pseudo-diffusion and flowing fraction than healthy tissue (p < 0.001). Moreover, apparent diffusion coefficient and D values significantly differed by Mayo imaging class, both in the whole kidney (Wilcoxon p = 0.007 and p = 0.004) and non-cystic tissue (p = 0.024 and p = 0.007).

CONCLUSIONS

DWI shows potential in ADPKD to quantify TCV and characterise non-cystic kidney tissue microstructure, indicating the presence of microcysts and peritubular interstitial fibrosis. DWI could complement existing biomarkers for non-invasively staging, monitoring, and predicting ADPKD progression and evaluating the impact of novel therapies, possibly targeting damaged non-cystic tissue besides cyst expansion.

CLINICAL RELEVANCE STATEMENT

This study shows diffusion-weighted MRI (DWI) potential to quantify total cyst volume and characterise non-cystic kidney tissue microstructure in ADPKD. DWI could complement existing biomarkers for non-invasively staging, monitoring, and predicting ADPKD progression and evaluating the impact of novel therapies, possibly targeting damaged non-cystic tissue besides cyst expansion.

KEY POINTS

• Diffusion magnetic resonance imaging shows potential to quantify total cyst volume in ADPKD. • Diffusion magnetic resonance imaging might allow to non-invasively characterise non-cystic kidney tissue microstructure. • Diffusion magnetic resonance imaging-based biomarkers significantly differ by Mayo imaging class, suggesting their possible prognostic value.

Abdominal Imaging in ADPKD: Beyond Total Kidney Volume

In the context of autosomal dominant polycystic kidney disease (ADPKD), measurement of the total kidney volume (TKV) is crucial. It acts as a marker for tracking disease progression, and evaluating the effectiveness of treatment strategies. The TKV has also been recognized as an enrichment biomarker and a possible surrogate endpoint in clinical trials. Several imaging modalities and methods are available to calculate the TKV, and the choice depends on the purpose of use. Technological advancements have made it possible to accurately assess the cyst burden, which can be crucial to assessing the disease state and helping to identify rapid progressors. Moreover, the development of automated algorithms has increased the efficiency of total kidney and cyst volume measurements. Beyond these measurements, the quantification and characterization of non-cystic kidney tissue shows potential for stratifying ADPKD patients early on, monitoring disease progression, and possibly predicting renal function loss. A broad spectrum of radiological imaging techniques are available to characterize the kidney tissue, showing promise when it comes to non-invasively picking up the early signs of ADPKD progression. Radiomics have been used to extract textural features from ADPKD images, providing valuable information about the heterogeneity of the cystic and non-cystic components. This review provides an overview of ADPKD imaging biomarkers, focusing on the quantification methods, potential, and necessary steps toward a successful translation to clinical practice.

Utility of new image-derived biomarkers for autosomal dominant polycystic kidney disease prognosis using automated instance cyst segmentation

New image-derived biomarkers for patients affected by autosomal dominant polycystic kidney disease are needed to improve current clinical management. The measurement of total kidney volume (TKV) provides critical information for clinicians to drive care decisions. However, patients with similar TKV may present with very different phenotypes, often requiring subjective decisions based on other factors (e.g., appearance of healthy kidney parenchyma, a few cysts contributing significantly to overall TKV, etc.). In this study, we describe a new technique to individually segment cysts and quantify biometric parameters including cyst volume, cyst number, parenchyma volume, and cyst parenchyma surface area. Using data from the Consortium for Radiologic Imaging Studies of Polycystic Kidney Disease (CRISP) study the utility of these new parameters was explored, both quantitatively as well as visually. Total cyst number and cyst parenchyma surface area showed superior prediction of the slope of estimated glomerular filtration rate decline, kidney failure and chronic kidney disease stages 3A, 3B, and 4, compared to TKV. In addition, presentations such as a few large cysts contributing significantly to overall kidney volume were shown to be much better stratified in terms of outcome predictions. Thus, these new image biomarkers, which can be obtained automatically, will have great utility in future studies and clinical care for patients affected by autosomal dominant polycystic kidney disease.

Current progress in artificial intelligence-assisted medical image analysis for chronic kidney disease: A literature review

Chronic kidney disease (CKD) causes irreversible damage to kidney structure and function. Arising from various etiologies, risk factors for CKD include hypertension and diabetes. With a progressively increasing global prevalence, CKD is an important public health problem worldwide. Medical imaging has become an important diagnostic tool for CKD through the non-invasive identification of macroscopic renal structural abnormalities. Artificial intelligence (AI)-assisted medical imaging techniques aid clinicians in the analysis of characteristics that cannot be easily discriminated by the naked eye, providing valuable information for the identification and management of CKD. Recent studies have demonstrated the effectiveness of AI-assisted medical image analysis as a clinical support tool using radiomics- and deep learning-based AI algorithms for improving the early detection, pathological assessment, and prognostic evaluation of various forms of CKD, including autosomal dominant polycystic kidney disease. Herein, we provide an overview of the potential roles of AI-assisted medical image analysis for the diagnosis and management of CKD.

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.

RtNet: a deep hybrid neural network for the identification of acute rejection and chronic allograft nephropathy after renal transplantation using multiparametric MRI

BACKGROUND

Reliable diagnosis of the cause of renal allograft dysfunction is of clinical importance. The aim of this study is to develop a hybrid deep-learning approach for determining acute rejection (AR), chronic allograft nephropathy (CAN) and renal function in kidney-allografted patients by multimodality integration.

METHODS

Clinical and magnetic resonance imaging (MRI) data of 252 kidney-allografted patients who underwent post-transplantation MRI between December 2014 and November 2019 were retrospectively collected. An end-to-end convolutional neural network, namely RtNet, was designed to discriminate between AR, CAN and stable renal allograft recipient (SR), and secondarily, to predict the impaired renal graft function [estimated glomerular filtration rate (eGFR) ≤50 mL/min/1.73 m2]. Specially, clinical variables and MRI radiomics features were integrated into the RtNet, resulting in a hybrid network (RtNet+). The performance of the conventional radiomics model RtRad, RtNet and RtNet+ was compared to test the effect of multimodality interaction.

RESULTS

Out of 252 patients, AR, CAN and SR was diagnosed in 20/252 (7.9%), 92/252 (36.5%) and 140/252 (55.6%) patients, respectively. Of all MRI sequences, T2-weighted imaging and diffusion-weighted imaging with stretched exponential analysis showed better performance than other sequences. On pairwise comparison of resulting prediction models, RtNet+ produced significantly higher macro-area-under-curve (macro-AUC) (0.733 versus 0.745; P = 0.047) than RtNet in discriminating between AR, CAN and SR. RtNet+ performed similarly to the RtNet (macro-AUC, 0.762 versus 0.756; P > 0.05) in discriminating between eGFR ≤50 mL/min/1.73 m2 and >50 mL/min/1.73 m2. With decision curve analysis, adding RtRad and RtNet to clinical variables resulted in more net benefits in diagnostic performance.

CONCLUSIONS

Our study revealed that the proposed RtNet+ model owned a stable performance in revealing the cause of renal allograft dysfunction, and thus might offer important references for individualized diagnostics and treatment strategy.

A Systematic Review of Reported Outcomes in ADPKD Studies

Introduction

Methods

Results

Conclusion

The utility of texture analysis of kidney MRI for evaluating renal dysfunction with multiclass classification model

We evaluated a multiclass classification model to predict estimated glomerular filtration rate (eGFR) groups in chronic kidney disease (CKD) patients using magnetic resonance imaging (MRI) texture analysis (TA). We identified 166 CKD patients who underwent MRI comprising Dixon-based T1-weighted in-phase (IP)/opposed-phase (OP)/water-only (WO) images, apparent diffusion coefficient (ADC) maps, and T2* maps. The patients were divided into severe, moderate, and control groups based on eGFR borderlines of 30 and 60 mL/min/1.73 m². After extracting 93 texture features (TFs), dimension reduction was performed using inter-observer reproducibility analysis and sequential feature selection (SFS) algorithm. Models were created using linear discriminant analysis (LDA); support vector machine (SVM) with linear, rbf, and sigmoid kernels; decision tree (DT); and random forest (RF) classifiers, with synthetic minority oversampling technique (SMOTE). Models underwent 100-time repeat nested cross-validation. Overall performances of our classification models were modest, and TA based on T1-weighted IP/OP/WO images provided better performance than those based on ADC and T2* maps. The most favorable result was observed in the T1-weighted WO image using RF classifier and the combination model was derived from all T1-weighted images using SVM classifier with rbf kernel. Among the selected TFs, total energy and energy had weak correlations with eGFR.

The predictive value of renal parenchymal information for renal function impairment in patients with ADPKD: a multicenter prospective study

OBJECTIVE

Although the guideline indicates that total kidney volume (TKV) is an important detection indicator in patients with autosomal dominant polycystic kidney disease (ADPKD), this study attempted to demonstrate that renal parenchymal information, combined with parenchymal volume and radiomics features, may have more valuable clinical guiding significance.

METHODS

A totals of 340 ADPKD patients with normal renal function were prospectively collected and followed-up for five years, with renal function tests and non-contrast computed tomography (CT) performed every six months. The relationship between renal function impairment and renal parenchymal volume (RPV) as along with radiomics features was explored using a multiple linear regression model and multiple logistic regression. Then, a combined model of RPV with radiomics features was constructed to comprehensively evaluate its predictive value.

RESULTS

Compared with TKV, decreased RPV presented a closer relationship with renal function impairment, namely, with the impairment rate (RPV: 82.3% vs. TVK: 67.1%) and eGFR (RPV: r = 0.614, p < 0.001 vs. TKV: r = -0.452, p < 0.001), and showed higher predictive power (RPV: AUC = 0.752 [95%CI 0.692-0.805], p < 0.001 vs. TKV: AUC = 0.711 [95%CI 0.649-0.768], p < 0.001). Correspondingly, the radiomics analysis that was derived from the renal parenchyma also showed a satisfactory result (AUC = 0.849 [95%Cl 0.797-0.892], p < 0.001). Importantly, the predictive power for renal function impairment was further improved in the combined model of RPV and radiomics features (AUC = 0.902 [95%Cl 0.857-0.937], p < 0.001).

CONCLUSION

Renal parenchyma information may be a sensitive biomarker of renal function impairment in ADPKD, which can provide a new approach for clinically monitoring renal function, and may greatly improve the pre-hospital prevention and treatment effects.

MRI-based kidney radiomic analysis during chronic lithium treatment

BACKGROUND

Lithium therapy during bipolar disorder is associated with an increased risk of chronic kidney disease (CKD) that is slowly progressive and undetectable at early stages. We aimed at identifying kidney image texture features as possible imaging biomarkers of decreased measured glomerular filtration rate (mGFR) using radiomics of T2-weighted magnetic resonance imaging (MRI).

METHODS

One hundred and eight patients treated with lithium were evaluated including mGFR and kidney MRI, with T2-weighted sequence single-shot fast spin-echo. Computed radiomic analysis was performed after kidney segmentation. Significant features were selected to build a radiomic signature using multivariable Cox analysis to detect an mGFR <60 ml/min/1.73 m². The texture index was validated using a training and a validation cohort.

RESULTS

Texture analysis index was able to detect an mGFR decrease, with an AUC of 0.85 in the training cohort and 0.71 in the validation cohort. Patients with a texture index below the median were older (59 [42-66] vs. 46 [34-54] years, p = .001), with longer treatment duration (10 [3-22] vs. 6 [2-10] years, p = .02) and a lower mGFR (66 [46-84] vs. 83 [71-94] ml/min/1.73m², p < .001). Texture analysis index was independently and negatively associated with age (β = -.004 ± 0.001, p < .001), serum vasopressin (-0.005 ± 0.002, p = .02) and lithium treatment duration (-0.01 ± 0.003, p = .001), with a significant interaction between lithium treatment duration and mGFR (p = .02).

CONCLUSIONS

A renal texture index was developed among patients treated with lithium associated with a decreased mGFR. This index might be relevant in the diagnosis of lithium-induced renal toxicity.

Effect of Matrix Size Reduction on Textural Information in Clinical Magnetic Resonance Imaging

The selection of the matrix size is an important element of the magnetic resonance imaging (MRI) process, and has a significant impact on the acquired image quality. Signal to noise ratio, often used to assess MR image quality, has its limitations. Thus, for this purpose we propose a novel approach: the use of texture analysis as an index of the image quality that is sensitive for the change of matrix size. Image texture in biomedical images represents tissue and organ structures visualized via medical imaging modalities such as MRI. The correlation between texture parameters determined for the same tissues visualized in images acquired with different matrix sizes is analyzed to aid in the assessment of the selection of the optimal matrix size. T2-weighted coronal images of shoulders were acquired using five different matrix sizes while maintaining the same field of view; three regions of interest (bone, fat, and muscle) were considered. Lin’s correlation coefficients were calculated for all possible pairs of the 310-element texture feature vectors evaluated for each matrix. The obtained results are discussed considering the image noise and blurring effect visible in images acquired with smaller matrices. Taking these phenomena into account, recommendations for the selection of the matrix size used for the MRI imaging were proposed.

A MRI-based radiomics nomogram for evaluation of renal function in ADPKD

OBJECTIVES

This study is aimed to establish a fusion model of radiomics-based nomogram to predict the renal function of autosomal dominant polycystic kidney disease (ADPKD).

METHODS

One hundred patients with ADPKD were randomly divided into training group (n = 69) and test group (n = 31). The radiomics features were extracted from T1-weighted fat suppression images (FS-T1WI) and T2-weighted fat suppression images (FS-T2WI). Decision tree algorithm was employed to build radiomics model to get radiomics signature. Then multivariate logistic regression analysis was used to establish the radiomics nomogram based on independent clinical factors, conventional MR imaging variables and radiomics signature. The receiver operating characteristic (ROC) analysis and Delong test were used to compare the performance of radiomics model and radiomics nomogram model, and the decision curve to evaluate the clinical application value of radiomics nomogram model in the evaluation of renal function in patients with ADPKD.

RESULTS

Fourteen radiomics features were selected to establish radiomics model. Based on FS-T1WI and FS-T2WI sequences, the radiomics model showed good discrimination ability in training group and test group [training group: (AUC) = 0.7542, test group (AUC) = 0.7417]. The performance of radiomics nomogram model was significantly better than that of radiomics model in all data sets [radiomics model (AUC) = 0.7505, radiomics nomogram model (AUC) = 0.8435, p value = 0.005]. The analysis of calibration curve and decision curve showed that radiomics nomogram model had more clinical application value.

CONCLUSION

radiomics analysis of MRI can be used for the preliminary evaluation and prediction of renal function in patients with ADPKD. The radiomics nomogram model shows better prediction effect in renal function evaluation, and can be used as a non-invasive renal function prediction tool to assist clinical decision-making. Trial registration ChiCTR, ChiCTR2100046739. Registered 27 May 2021-retrospectively registered, http://www.ChiCTR.org.cn/showproj.aspx?proj=125955.

Application of MR Imaging Features in Differentiation of Renal Changes in Patients With Stage III Type 2 Diabetic Nephropathy and Normal Subjects

OBJECTIVE

The objective of the study was to explore the value of MRI texture features based on T1WI, T2-FS and diffusion-weighted imaging (DWI) in differentiation of renal changes in patients with stage III type 2 diabetic nephropathy (DN) and normal subjects.

MATERIALS AND METHODS

A retrospective analysis was performed to analyze 44 healthy volunteers (group A) and 40 patients with stage III type 2 diabetic nephropathy (group B) with microalbuminuria. Urinary albumin to creatinine ratio (ACR) <30 mg/g, estimated glomerular filtration rate (eGFR) in the range of 60-120 ml/(min 1.73 m²), and randomly divided into primary cohort and test cohort. Conventional MRI and DWI of kidney were performed using 1.5 T magnetic resonance imaging (MRI). The outline of the renal parenchyma was manually labeled in fat-suppressed T2-weighted imaging (FS-T2WI), and PyRadiomics was used to extract radiomics features. The radiomics features were then selected by the least absolute shrinkage and selection operator (LASSO) method.

RESULTS

There was a significant difference in sex and body mass index (BMI) (P <0.05) in the primary cohort, with no significant difference in age. In the final results, the wavelet and Laplacian-Gaussian filtering are used to extract 1,892 image features from the original T1WI image, and the LASSO algorithm is used for selection. One first-order feature and six texture features are selected through 10 cross-validations. In the mass, 1,638 imaging extracts features from the original T2WI image.1 first-order feature and 5 texture features were selected. A total of 1,241 imaging features were extracted from the original ADC images, and 5 texture features were selected. Using LASSO-Logistic regression analysis, 10 features were selected for modeling, and a combined diagnosis model of diabetic nephropathy based on texture features was established. The average unit cost in the logistic regression model was 0.98, the 95% confidence interval for the predictive efficacy was 0.9486-1.0, specificity 0.97 and precision 0.93, particularly. ROC curves also revealed that the model could distinguish with high sensitivity of at least 92%.

CONCLUSION

In consequence, the texture features based on MR have broad application prospects in the early detection of DN as a relatively simple and noninvasive tool without contrast media administration.

Ultrasound-Based Renal Parenchymal Area and Kidney Function Decline in Infants With Congenital Anomalies of the Kidney and Urinary Tract

Congenital anomalies of the kidney and urinary tract are the leading cause of chronic kidney disease in children. Noninvasive imaging biomarkers that predict chronic kidney disease progression in early infancy are needed. We performed a pilot study nested in the prospective Chronic Kidney Disease in Children cohort study to determine the association between renal parenchymal area (RPA) on first post-natal renal ultrasound and change in estimated glomerular filtration rate (eGFR) in children with congenital anomalies of the kidney and urinary tract. Among 14 participants, 78.6% were males, the median age at the time of the ultrasound was 3.4 months (interquartile range, 1.3-7.9 mo), and the median total RPA z-score at baseline was -1.01 (interquartile range, -2.39 to 0.52). After a median follow-up period of 7.4 years (interquartile range, 6.8-8.2 y), the eGFR decreased from a median of 49.4 mL/min per 1.73 m² at baseline to 29.4 mL/min per 1.73 m², an annual eGFR percentage decrease of -4.68%. Lower RPA z-scores were correlated weakly with a higher annual decrease in eGFR (Spearman correlation, 0.35; 95% confidence interval, -0.25 to 0.76). This pilot study shows the feasibility of obtaining RPA from a routine ultrasound and suggests that a lower baseline RPA may be associated with a greater decrease in eGFR over time. Further studies with larger patient cohorts are needed to confirm this association.

Limited Performance of Estimated Total Kidney Volume for Follow-up of ADPKD

Introduction

Total kidney volume (TKV) is a qualified biomarker for disease progression in autosomal dominant polycystic kidney disease (ADPKD). Recent studies suggest that TKV estimated using ellipsoid formula correlates well with TKV measured by manual planimetry (gold standard). We investigated whether the ellipsoid formula could replace manual planimetry for follow-up of ADPKD patients.

Methods

Abdominal magnetic resonance images of patients with ADPKD performed between January 1, 2013, and June 31, 2019, in Saint-Luc Hospital, Brussels, were used. Two radiologists independently performed manual TKV (mTKV) measures and kidney axial measures necessary for estimating TKV (eTKV) using ellipsoid equation. Repeatability and reproducibility of axial measures, mTKV and eTKV, and agreement between mTKV and eTKV were assessed (Bland-Altman). Intraclass correlation coefficient (ICC) was used to assess agreement on Mayo Clinic Imaging Classification (MCIC) scores.

Results

140 patients were included with mean age 45±13 years, estimated glomerular filtration rate (eGFR) 71±31 ml/min per 1.73 m², and mTKV 1697±1538 ml. Repeatability and reproducibility were superior for mTKV versus eTKV (repeatability coefficient 2.4% vs. 14% in senior reader, and reproducibility coefficient 6.7% vs. 15%). Intertechnique reproducibility coefficient (95% confidence interval [CI]) was 19% (17%, 21%) in senior reader. Intertechnique agreement on derived MCIC scores was very good (ICC = 0.924 [0.884, 0.949]).

Conclusion

TKV estimated using ellipsoid equation demonstrates poor repeatability and reproducibility compared with that of mTKV. Intertechnique agreement is also limited, even when measurements are performed by an experienced radiologist. Estimated TKV, however, accurately determines MCIC score.

An update on the use of tolvaptan for ADPKD: Consensus statement on behalf of the ERA Working Group on Inherited Kidney Disorders (WGIKD), the European Rare Kidney Disease Reference Network (ERKNet) and Polycystic Kidney Disease International (PKD-International)

Approval of the vasopressin V2 receptor antagonist tolvaptan—based on the landmark TEMPO 3:4 trial—marked a transformation in the management of autosomal dominant polycystic kidney disease (ADPKD). This development has advanced patient care in ADPKD from general measures to prevent progression of chronic kidney disease to targeting disease-specific mechanisms. However, considering the long-term nature of this treatment, as well as potential side effects, evidence-based approaches to initiate treatment only in patients with rapidly progressing disease are crucial. In 2016, the position statement issued by the European Renal Association (ERA) was the first society-based recommendation on the use of tolvaptan and has served as a widely used decision-making tool for nephrologists. Since then, considerable practical experience regarding the use of tolvaptan in ADPKD has accumulated. More importantly, additional data from REPRISE, a second randomized clinical trial (RCT) examining the use of tolvaptan in later-stage disease, have added important evidence to the field, as have post hoc studies of these RCTs. To incorporate this new knowledge, we provide an updated algorithm to guide patient selection for treatment with tolvaptan and add practical advice for its use.

Predictors of progression in autosomal dominant and autosomal recessive polycystic kidney disease

Autosomal dominant polycystic kidney disease (ADPKD) and autosomal recessive polycystic kidney disease (ARPKD) are characterized by bilateral cystic kidney disease leading to progressive kidney function decline. These diseases also have distinct liver manifestations. The range of clinical presentation and severity of both ADPKD and ARPKD is much wider than was once recognized. Pediatric and adult nephrologists are likely to care for individuals with both diseases in their lifetimes. This article will review genetic, clinical, and imaging predictors of kidney and liver disease progression in ADPKD and ARPKD and will briefly summarize pharmacologic therapies to prevent progression.

Texture analysis based on quantitative magnetic resonance imaging to assess kidney function: a preliminary study

Background

Magnetic resonance imaging (MRI) has demonstrated its potential in the evaluation of renal function. Texture analysis (TA) is a novel technique to quantify tissue heterogeneity. We aim to investigate the feasibility of using TA based on the apparent diffusion coefficient (ADC), as well as T1 and T2 maps to evaluate renal function.

Methods

Patients with impaired renal function and subjects with a normal renal function who underwent renal diffusion weighted imaging (DWI), as well as T1 and T2 mapping at 3T, were prospectively enrolled. The participants were classified into four groups according to the estimated glomerular filtration rate (eGFR, mL/min/1.73 m²): normal (eGFR ≥90), mildly impaired (60≤ eGFR <90), moderately impaired (30≤ eGFR <60), and severely impaired (eGFR <30) renal function groups. Texture features quantified from the renal cortex or medulla were selected to build classifiers to discriminate different renal function groups by plotting receiver operating characteristic (ROC) curves and calculating the area under the curve (AUC), sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV).

Results

In total, 116 candidates were included (94 patients and 22 healthy volunteers, mean age 37.9±14.9 years). There were 46 participants in the normal renal function group, 14 in the mildly impaired renal function group, 27 in the moderately impaired renal function group, and 29 in the severely impaired renal function group. Texture features from the ADC and T1 maps exhibited a good correlation to eGFR. The AUC, sensitivity, specificity, PPV, and NPV to differentiate between the normal and impaired renal function groups were 0.835, 0.792, 0.867, 0.905, and 0.722, respectively; to differentiate between the mildly impaired and moderately impaired groups were 0.937, 0.889, 0.857, 0.923, and 0.800, respectively; and to differentiate between the moderately impaired and severely impaired groups was 0.940, 0.759, 0.889, 0.880, and 0.774, respectively.

Conclusions

TA based on ADC and T1 maps is feasible for evaluating renal function with relatively good accuracy.

Assessing Risk of Rapid Progression in Autosomal Dominant Polycystic Kidney Disease and Special Considerations for Disease-Modifying Therapy

Autosomal dominant polycystic kidney disease (ADPKD) is the most common inherited cause of kidney failure, accounting for 5%-10% of cases. Predicting which patients with ADPKD will progress rapidly to kidney failure is critical to assess the risk-benefit ratio of any intervention and to consider early initiation of long-term kidney protective measures that will maximize the cumulative benefit of slowing disease progression. Surrogate prognostic biomarkers are required to predict future decline in kidney function. Clinical, genetic, environmental, epigenetic, and radiologic factors have been studied as predictors of progression to kidney failure in ADPKD. A complex interaction of these prognostic factors determines the number of kidney cysts and their growth rates, which affect total kidney volume (TKV). Age-adjusted TKV, represented by the Mayo imaging classification, estimates each patient's unique rate of kidney growth and provides the most individualized approach available clinically so far. Tolvaptan has been approved to slow disease progression in patients at risk of rapidly progressive disease. Several other disease-modifying treatments are being studied in clinical trials. Selection criteria for patients at risk of rapid progression vary widely among countries and are based on a combination of age, baseline glomerular filtration rate (GFR), GFR slope, baseline TKV, and TKV rate of growth. This review details the approach in assessing the risk of disease progression in ADPKD and identifying patients who would benefit from long-term therapy with disease-modifying agents.

Automatic semantic segmentation of kidney cysts in MR images of patients affected by autosomal-dominant polycystic kidney disease

PURPOSE

For patients affected by autosomal-dominant polycystic kidney disease (ADPKD), successful differentiation of cysts is useful for automatic classification of patient phenotypes, clinical decision-making, and disease progression. The objective was to develop and evaluate a fully automated semantic segmentation method to differentiate and analyze renal cysts in patients with ADPKD.

METHODS

An automated deep learning approach using a convolutional neural network was trained, validated, and tested on a set of 60 MR T2-weighted images. A three-fold cross-validation approach was used to train three models on distinct training and validation sets (n = 40). An ensemble model was then built and tested on the hold out cases (n = 20), with each of the cases compared to manual segmentations performed by two readers. Segmentation agreement between readers and the automated method was assessed.

RESULTS

The automated approach was found to perform at the level of interobserver variability. The automated approach had a Dice coefficient (mean ± standard deviation) of 0.86 ± 0.10 vs Reader-1 and 0.84 ± 0.11 vs. Reader-2. Interobserver Dice was 0.86 ± 0.08. In terms of total cyst volume (TCV), the automated approach had a percent difference of 3.9 ± 19.1% vs Reader-1 and 8.0 ± 24.1% vs Reader-2, whereas interobserver variability was - 2.0 ± 16.4%.

CONCLUSION

This study developed and validated a fully automated approach for performing semantic segmentation of kidney cysts in MR images of patients affected by ADPKD. This approach will be useful for exploring additional imaging biomarkers of ADPKD and automatically classifying phenotypes.

Susceptibility weighted imaging (SWI) for evaluating renal dysfunction in type 2 diabetes mellitus: a preliminary study using SWI parameters and SWI-based texture features

Background

Susceptibility weighted imaging (SWI) could reflect tissue blood oxygen levels, and then whether it could be used to evaluate renal injury remains to be further studied. This study aimed to examine the performance of SWI parameters and SWI-based texture features in evaluating renal dysfunction of type 2 diabetes mellitus (T2DM).

Methods

Forty-five patients with T2DM were included. With the estimated glomerular filtration rate (eGFR), the patients were divided into non-moderate-severe renal injured group (non-msRI, eGFR >60 mL/min/1.73 m²) and moderate-severe renal injured group (msRI, eGFR ≤60 mL/min/1.73 m²). The 3 SWI parameters and 16 SWI-based texture features between non-msRI and msRI were compared. The correlation between the parameters and BUN, Scr was analyzed.

Results

The signal intensity ratio of the medulla to psoas muscle (MPswi) was significantly lower than the signal intensity ratio of the cortex to psoas muscle (CPswi) in non-msRI and msRI group (t=8.619, 3.483, respectively, P<0.05). MPswi was higher, and the signal intensity ratio of the cortex to the medulla (CMswi), Skewness, Correlation were lower in msRI than in non-msRI (P<0.05). These parameters showed similar diagnostic efficacies for msRI (P>0.05), and AUCs were 0.703–0.854. CMswi was an independent protective factor for msRI (OR =0.026, P=0.003). MPswi and CMswi were correlated with BUN (r=0.416, −0.545, P<0.05). CMswi and Correlation were correlated with Scr (r=−0.645, −0.411, P<0.05).

Conclusions

SWI was valuable for assessing renal dysfunction, which may be helpful for the evaluation of moderate-severe renal injured patients with T2DM.

Magnetic Resonance Kidney Parenchyma-T2 as a Novel Imaging Biomarker for Autosomal Dominant Polycystic Kidney Disease

OBJECTIVE

Autosomal dominant polycystic kidney disease (ADPKD) is a chronic progressive disorder with a significant disease burden leading to end-stage renal disease in more than 75% of the affected individuals. Although prediction of disease progression is highly important, all currently available biomarkers-including height-adjusted total kidney volume (htTKV)-have important drawbacks in the everyday clinical setting. Thus, the purpose of this study was to evaluate T2 mapping as a source of easily obtainable and accurate biomarkers, which are needed for improved patient counseling and selection of targeted treatment options.

MATERIALS AND METHODS

A total of 139 ADPKD patients from The German ADPKD Tolvaptan Treatment Registry and 10 healthy controls underwent magnetic resonance imaging on a clinical 1.5-T system including acquisition of a Gradient-Echo-Spin-Echo T2 mapping sequence. The ADPKD patients were divided into 3 groups according to kidney cyst fraction (0%-35%, 36%-70%, >70%) as a surrogate marker for disease severity. The htTKV was calculated based on standard T2-weighted imaging. Mean T2 relaxation times of both kidneys (kidney-T2) as well as T2 relaxation times of the residual kidney parenchyma (parenchyma-T2) were measured on the T2 maps.

RESULTS

Calculation of parenchyma-T2 was 6- to 10-fold faster than determination of htTKV and kidney-T2 (0.78 ± 0.14 vs 4.78 ± 1.17 minutes, P < 0.001; 0.78 ± 0.14 vs 7.59 ± 1.57 minutes, P < 0.001). Parenchyma-T2 showed a similarly strong correlation to cyst fraction (r = 0.77, P < 0.001) as kidney-T2 (r = 0.76, P < 0.001), the strongest correlation to the serum-derived biomarker copeptin (r = 0.37, P < 0.001), and allowed for the most distinct separation of patient groups divided according to cyst fraction. In contrast, htTKV showed an only moderate correlation to cyst fraction (r = 0.48, P < 0.001). These observations were even more evident when considering only patients with preserved kidney function.

CONCLUSIONS

The rapidly assessable parenchyma-T2 shows a strong association with disease severity early in disease and is superior to htTKV when it comes to correlation with renal cyst fraction.

RIL-Contour: a Medical Imaging Dataset Annotation Tool for and with Deep Learning

Deep-learning algorithms typically fall within the domain of supervised artificial intelligence and are designed to “learn” from annotated data. Deep-learning models require large, diverse training datasets for optimal model convergence. The effort to curate these datasets is widely regarded as a barrier to the development of deep-learning systems. We developed RIL-Contour to accelerate medical image annotation for and with deep-learning. A major goal driving the development of the software was to create an environment which enables clinically oriented users to utilize deep-learning models to rapidly annotate medical imaging. RIL-Contour supports using fully automated deep-learning methods, semi-automated methods, and manual methods to annotate medical imaging with voxel and/or text annotations. To reduce annotation error, RIL-Contour promotes the standardization of image annotations across a dataset. RIL-Contour accelerates medical imaging annotation through the process of annotation by iterative deep learning (AID). The underlying concept of AID is to iteratively annotate, train, and utilize deep-learning models during the process of dataset annotation and model development. To enable this, RIL-Contour supports workflows in which multiple-image analysts annotate medical images, radiologists approve the annotations, and data scientists utilize these annotations to train deep-learning models. To automate the feedback loop between data scientists and image analysts, RIL-Contour provides mechanisms to enable data scientists to push deep newly trained deep-learning models to other users of the software. RIL-Contour and the AID methodology accelerate dataset annotation and model development by facilitating rapid collaboration between analysts, radiologists, and engineers.

DTI-based radiomics signature for the detection of early diabetic kidney damage

OBJECTIVE

To explore whether a radiomics signature based on diffusion tensor imaging (DTI) can detect early kidney damage in diabetic patients.

MATERIALS AND METHODS

Twenty-eight healthy volunteers (group A) and thirty type 2 diabetic patients (group B) with micro-normoalbuminuria, a urinary albumin-to-creatinine ratio (ACR) < 30 mg/g and an estimated glomerular filtration rate (eGFR) of 60-120 mL/(min 1.73 m²) were recruited. Kidney DTI was performed using 1.5T magnetic resonance imaging (MRI).The radiologist manually drew regions of interest (ROI) on the fractional anisotropy (FA) map of the right kidney ROI including the cortex and medulla. The texture features of the ROIs were extracted using MaZda software. The Fisher coefficient, mutual information (MI), and probability of classification error and average correlation coefficient (POE + ACC) methods were used to select the texture features. The most valuable texture features were further selected by the least absolute shrinkage and selection operator (LASSO) algorithm. A LASSO regression model based on the radiomics signature was established. The diagnostic performance of the model for detecting early diabetic kidney changes was evaluated by the area under the receiver operating characteristic (ROC) curve (AUC). Empower (R), R, and MedCalc15.8 software were used for statistical analysis RESULTS: A total of 279 texture features were extracted from ROI of the kidney, and 30 most valuable texture features were selected from groups A and B using MaZda software. After LASSO-logistic regression, a diagnostic model of diabetic kidney damage based on texture features was established. Model discrimination evaluation: AUC = 0.882 (0.770 ± 0.952). Model calibration evaluation: Hosmer-Lemeshow X2 = 5.3611, P = 0.7184, P > 0.05, the model has good calibration.

CONCLUSION

The texture features based on DTI could play a promising role in detecting early diabetic kidney damage.

Computation of the Texture Features on T2-Weighted Images as a Novel Method to Assess the Function of the Transplanted Kidney: Primary Research

Texture in medical images describes the internal structure of human tissues or organs. We hypothesize that textural analysis (TA) could be applied to assess renal function after kidney transplantation (KTx). This preliminary study aims to find a statistical difference between texture features in transplanted kidneys with different placement of region of interest (ROI). Also, we aimed at comparing results of TA with transplanted kidney function. For analysis, we used 9 retrospective examinations in patients with a transplanted kidney. All patients underwent a diagnostic magnetic resonance imaging (MRI) scan, including T2-weighted images. All MRI acquisition was performed using a 1.5T MRI (MAGNETOM Aera, Siemens Healthineers AG, Erlangen, Germany). Examinations were performed from indications other than KTx and in various times after KTx. We found an association between the texture parameters and the estimated glomerular filtration rate (4p estimate formula: Chronic Kidney Disease Epidemiology Collaboration [CKD-EPI]) and between texture parameters and creatinine in ROI location in the cortex. Our findings make TA a promising tool for the assessment of the function of the transplanted kidney. However, the effect of binning, ROI size, and placement of ROI in the organ are yet to be determined and need further study.

MRI-derived markers for predicting a decline in renal function in patients with autosomal dominant polycystic kidney disease

Autosomal dominant polycystic kidney disease (ADPKD) constitutes the fourth cause of end-stage renal disease in Europe. The course of the disease varies widely among patients with ADPKD. Due to the emergence of new possibilities of pharmacotherapy, it has become crucial to identify the group of patients with the fastest rate and risk of disease progression. This particular group of patients will benefit most from the therapy and they are the best candidates for clinical trials. At the early stages of ADPKD typical markers of severity and progression of the disease remain unchanged in contrast to the kidney volume, which increases continuously in an exponential way. Therefore, the use of height-adjusted total kidney volume as a biomarker should become a mandatory diagnostic option. Also, quantitative MRI techniques are promising biomarkers for the evaluation of disease severity and could provide additional insights into its course.

Prognostic Performance of Kidney Volume Measurement for Polycystic Kidney Disease: A Comparative Study of Ellipsoid vs. Manual Segmentation

Total kidney volume (TKV) is a validated prognostic biomarker for risk assessment in autosomal dominant polycystic kidney disease (ADPKD). TKV by manual segmentation (MS) is the “gold standard” but is time-consuming and requires expertise. The purpose of this study was to compare TKV-based prognostic performance by ellipsoid (EL) vs. MS in a large cohort of patients. Cross-sectional study of 308 patients seen at a tertiary referral center; all had a standardized MRI with typical imaging of ADPKD. An experienced radiologist blinded to patient clinical results performed all TKV measurements by EL and MS. We assessed the agreement of TKV measurements by intraclass correlation(ICC) and Bland-Altman plot and also how the disagreement of the two methods impact the prognostic performance of the Mayo Clinic Imaging Classification (MCIC). We found a high ICC of TKV measurements (0.991, p < 0.001) between EL vs. MS; however, 5.5% of the cases displayed disagreement of TKV measurements >20%. We also found a high degree of agreement of the individual MCIC risk classes (i.e. 1A to 1E) with a Cohen’s weighted-kappa of 0.89; but 42 cases (13.6%) were misclassified by EL with no misclassification spanning more than one risk class. The sensitivity and specificity of EL in distinguishing low-risk (1A-B) from high-risk (1C-E) MCIC prognostic grouping were 96.6% and 96.1%, respectively. Overall, we found an excellent agreement of TKV-based risk assessment between EL and MS. However, caution is warranted for patients with MCIC 1B and 1C, as misclassification can have therapeutic consequence.

Computer-aided diagnosis of congenital abnormalities of the kidney and urinary tract in children based on ultrasound imaging data by integrating texture image features and deep transfer learning image features

INTRODUCTION

Anatomic characteristics of kidneys derived from ultrasound images are potential biomarkers of children with congenital abnormalities of the kidney and urinary tract (CAKUT), but current methods are limited by the lack of automated processes that accurately classify diseased and normal kidneys.

OBJECTIVE

The objective of the study was to evaluate the diagnostic performance of deep transfer learning techniques to classify kidneys of normal children and those with CAKUT.

STUDY DESIGN

A transfer learning method was developed to extract features of kidneys from ultrasound images obtained during routine clinical care of 50 children with CAKUT and 50 controls. To classify diseased and normal kidneys, support vector machine classifiers were built on the extracted features using (1) transfer learning imaging features from a pretrained deep learning model, (2) conventional imaging features, and (3) their combination. These classifiers were compared, and their diagnosis performance was measured using area under the receiver operating characteristic curve (AUC), accuracy, specificity, and sensitivity.

RESULTS

The AUC for classifiers built on the combination features were 0.92, 0.88, and 0.92 for discriminating the left, right, and bilateral abnormal kidney scans from controls with classification rates of 84%, 81%, and 87%; specificity of 84%, 74%, and 88%; and sensitivity of 85%, 88%, and 86%, respectively. These classifiers performed better than classifiers built on either the transfer learning features or the conventional features alone (p < 0.001).

DISCUSSION

The present study validated transfer learning techniques for imaging feature extraction of ultrasound images to build classifiers for distinguishing children with CAKUT from controls. The experiments have demonstrated that the classifiers built on the transfer learning features and conventional image features could distinguish abnormal kidney images from controls with AUCs greater than 0.88, indicating that classification of ultrasound kidney scans has a great potential to aid kidney disease diagnosis. A limitation of the present study is the moderate number of patients that contributed data to the transfer learning approach.

CONCLUSIONS

The combination of transfer learning and conventional imaging features yielded the best classification performance for distinguishing children with CAKUT from controls based on ultrasound images of kidneys.

Polycystic kidney disease

Cystic kidneys are common causes of end-stage renal disease, both in children and in adults. Autosomal dominant polycystic kidney disease (ADPKD) and autosomal recessive polycystic kidney disease (ARPKD) are cilia-related disorders and the two main forms of monogenic cystic kidney diseases. ADPKD is a common disease that mostly presents in adults, whereas ARPKD is a rarer and often more severe form of polycystic kidney disease (PKD) that usually presents perinatally or in early childhood. Cell biological and clinical research approaches have expanded our knowledge of the pathogenesis of ADPKD and ARPKD and revealed some mechanistic overlap between them. A reduced 'dosage' of PKD proteins is thought to disturb cell homeostasis and converging signalling pathways, such as Ca²⁺, cAMP, mechanistic target of rapamycin, WNT, vascular endothelial growth factor and Hippo signalling, and could explain the more severe clinical course in some patients with PKD. Genetic diagnosis might benefit families and improve the clinical management of patients, which might be enhanced even further with emerging therapeutic options. However, many important questions about the pathogenesis of PKD remain. In this Primer, we provide an overview of the current knowledge of PKD and its treatment.

Recent Advances in the Management of Autosomal Dominant Polycystic Kidney Disease

Autosomal dominant polycystic kidney disease (ADPKD), the most common monogenic cause of ESKD, is characterized by relentless development of kidney cysts, hypertension, and destruction of the kidney parenchyma. Over the past few years, major advancements in diagnosing, prognosticating, and understanding the pathogenesis and natural course of the disease have been made. Currently, no kidney disease is more suitable for nephron-protective strategies. Early nephrology referral and implementation of these strategies may have a substantial effect. Total kidney volume is a good prognostication marker and allows stratification of patients into slow or rapid progressing disease, with implications for their management. Measurement of total kidney volume, disease stratification, and prognostication are possible using readily available tools. Although some patients require only monitoring and basic optimized kidney protective measures, such as rigorous BP control and various lifestyle and dietary changes, others will benefit from disease-modifying treatments. Vasopressin V2 receptor antagonists, a likely disease-modifying treatment, has been approved in several countries and recently by the US Food and Drug Administration; other therapies, such as somatostatin analogs and other novel agents, are currently in clinical trials. The purpose of this article is to present our views on the optimal management to delay kidney disease progression in ADPKD.

Standardizing total kidney volume measurements for clinical trials of autosomal dominant polycystic kidney disease

Background

The ability of unstandardized methods to track kidney growth in clinical trials for autosomal dominant polycystic kidney disease (ADPKD) has not been critically evaluated.

Methods

The Tolvaptan Efficacy and Safety Management of ADPKD and its Outcomes (TEMPO) 3:4 study involved baseline and annual magnetic resonance follow-up imaging yearly for 3 years. Total kidney volume (TKV) measurements were performed on these four time points in addition to the baseline imaging in TEMPO 4:4, initially by Perceptive Informatics (Waltham, MA, USA) using planimetry (original dataset) and for this study by the Mayo Translational PKD Center using semiautomated and complementary automated methods (sequential dataset). In the original dataset, the same reader was assigned to all scans of individual patients in TEMPO 3:4, but readers were reassigned in TEMPO 4:4. Two placebo-treated cohorts were included. In the first (n = 158), intervals between the end of TEMPO 3:4 and the start of TEMPO 4:4 scan visits ranged from 12 to 403 days; in the second (n = 95), the same scan (measured twice) visit was used for both.

Results

Growth rates in TEMPO 3:4 were similar in the original and sequential datasets (5.5 and 5.9%/year). Growth rates during the TEMPO 3:4 to TEMPO 4:4 interval were higher in the original (13.7%/year) but were not different in the sequential dataset (4.0%/year). Comparing volumes from the same images, TKVs showed a bias of 2.2% [95% confidence interval (CI) −5.2–9.7] in the original and −0.16% (95% CI −1.91–1.58) in the sequential dataset.

Conclusions

Despite using the same software, TKV and growth rate changes were present, likely due to reader differences in the transition from TEMPO 3:4 to TEMPO 4:4 in the original but not in the sequential dataset. Robust, standardized methods are essential in ADPKD trials to minimize errors in serial TKV measurements.

TRANSFER LEARNING FOR DIAGNOSIS OF CONGENITAL ABNORMALITIES OF THE KIDNEY AND URINARY TRACT IN CHILDREN BASED ON ULTRASOUND IMAGING DATA

Classification of ultrasound (US) kidney images for diagnosis of congenital abnormalities of the kidney and urinary tract (CAKUT) in children is a challenging task. It is desirable to improve existing pattern classification models that are built upon conventional image features. In this study, we propose a transfer learning-based method to extract imaging features from US kidney images in order to improve the CAKUT diagnosis in children. Particularly, a pre-trained deep learning model (imagenet-caffe-alex) is adopted for transfer learning-based feature extraction from 3-channel feature maps computed from US images, including original images, gradient features, and distanced transform features. Support vector machine classifiers are then built upon different sets of features, including the transfer learning features, conventional imaging features, and their combination. Experimental results have demonstrated that the combination of transfer learning features and conventional imaging features yielded the best classification performance for distinguishing CAKUT patients from normal controls based on their US kidney images.

Performance of an Artificial Multi-observer Deep Neural Network for Fully Automated Segmentation of Polycystic Kidneys

Deep learning techniques are being rapidly applied to medical imaging tasks—from organ and lesion segmentation to tissue and tumor classification. These techniques are becoming the leading algorithmic approaches to solve inherently difficult image processing tasks. Currently, the most critical requirement for successful implementation lies in the need for relatively large datasets that can be used for training the deep learning networks. Based on our initial studies of MR imaging examinations of the kidneys of patients affected by polycystic kidney disease (PKD), we have generated a unique database of imaging data and corresponding reference standard segmentations of polycystic kidneys. In the study of PKD, segmentation of the kidneys is needed in order to measure total kidney volume (TKV). Automated methods to segment the kidneys and measure TKV are needed to increase measurement throughput and alleviate the inherent variability of human-derived measurements. We hypothesize that deep learning techniques can be leveraged to perform fast, accurate, reproducible, and fully automated segmentation of polycystic kidneys. Here, we describe a fully automated approach for segmenting PKD kidneys within MR images that simulates a multi-observer approach in order to create an accurate and robust method for the task of segmentation and computation of TKV for PKD patients. A total of 2000 cases were used for training and validation, and 400 cases were used for testing. The multi-observer ensemble method had mean ± SD percent volume difference of 0.68 ± 2.2% compared with the reference standard segmentations. The complete framework performs fully automated segmentation at a level comparable with interobserver variability and could be considered as a replacement for the task of segmentation of PKD kidneys by a human.

Tolvaptan in the treatment of autosomal dominant polycystic kidney disease: patient selection and special considerations

Standard of care therapies for autosomal dominant polycystic kidney disease (ADPKD) may limit morbidity and mortality due to disease-related complications, but they do not delay disease progression. Tolvaptan, a selective vasopressin V2 receptor antagonist, delays the increase in kidney volume (a surrogate marker for disease progression), slows the decline in renal function, and reduces pain in ADPKD patients with relatively preserved renal function. The most common adverse events of tolvaptan are linked to its aquaretic effect, and rare cases of idiosyncratic hepatitis were observed. Additional ongoing studies will determine whether the benefits are sustained over time, whether they can be observed in patients with advanced kidney disease, and whether they can be translated in terms of quality of life and cost/effectiveness parameters. Tolvaptan is currently approved in Europe and several countries throughout the world. In real-life conditions, selection of patients that would be good theoretical candidates to tolvaptan is a key but complex question. Eligibility criteria slightly differ from one country to another, and several models (based on conventional data, genetics, renal volume) were recently proposed to identify patients with evidence or risk of rapid disease progression. Eligible patients will ultimately make the decision to start tolvaptan, after complete information, consideration, and balancing of benefits, adverse events, and risks.