Semantic Instance Segmentation of Kidney Cysts in MR Images: A Fully Automated 3D Approach Developed Through Active Learning

Deep Learning-Based Automated Imaging Classification of ADPKD

Introduction

The Mayo imaging classification model (MICM) requires a prestep qualitative assessment to determine whether a patient is in class 1 (typical) or class 2 (atypical), where patients assigned to class 2 are excluded from the MICM application.

Methods

We developed a deep learning-based method to automatically classify class 1 and 2 from magnetic resonance (MR) images and provide classification confidence utilizing abdominal T 2 -weighted MR images from 486 subjects, where transfer learning was applied. In addition, the explainable artificial intelligence (XAI) method was illustrated to enhance the explainability of the automated classification results. For performance evaluations, confusion matrices were generated, and receiver operating characteristic curves were drawn to measure the area under the curve.

Results

The proposed method showed excellent performance for the classification of class 1 (97.7%) and 2 (100%), where the combined test accuracy was 98.01%. The precision and recall for predicting class 1 were 1.00 and 0.98, respectively, with F 1 -score of 0.99; whereas those for predicting class 2 were 0.87 and 1.00, respectively, with F 1 -score of 0.93. The weighted averages of precision and recall were 0.98 and 0.98, respectively, showing the classification confidence scores whereas the XAI method well-highlighted contributing regions for the classification.

Conclusion

The proposed automated method can classify class 1 and 2 cases as accurately as the level of a human expert. This method may be a useful tool to facilitate clinical trials investigating different types of kidney morphology and for clinical management of patients with autosomal dominant polycystic kidney disease (ADPKD).

Kidney Energetics and Cyst Burden in Autosomal Dominant Polycystic Kidney Disease: A Pilot Study

RATIONALE & OBJECTIVE

In this pilot study, we hypothesized that autosomal dominant polycystic kidney disease (ADPKD) is characterized by impaired kidney oxidative metabolism that associates with kidney size and cyst burden.

STUDY DESIGN

Cross-sectional study.

SETTING & PARTICIPANTS

Twenty adults with ADPKD (age, 31±6 years; 65% women; body mass index [BMI], 26.8 [22.7-30.4] kg/m2; estimated glomerular filtration rate [eGFR, 2021 CKD-EPI creatinine], 103±18mL/min/1.73m2; height-adjusted total kidney volume [HTKV], 731±370mL/m; Mayo classifications 1B [5%], 1C [42%], 1D [21%], and 1E [32%]) and 11 controls in normal weight category (NWC) (age, 25±3 years; 45% women; BMI, 22.5 [21.7-24.2] kg/m2; eGFR, 113±15mL/min/1.73m2; HTKV, 159±31mL/m) at the University of Colorado Anschutz Medical Campus.

PREDICTORS

ADPKD status (yes/no) and severity (Mayo classifications).

OUTCOME

HTKV and cyst burden by magnetic resonance imaging, kidney oxidative metabolism, and perfusion by 11C-acetate positron emission tomography/computed tomography, insulin sensitivity by hyperinsulinemic-euglycemic clamps (presented as ratio of M-value of steady state insulin concentration [M/I]).

ANALYTICAL APPROACH

For categorical variables, χ2/Fisher's exact tests, and for continuous variables t tests/Mann-Whitney U tests. Pearson correlation was used to estimate the relationships between variables.

RESULTS

Compared with NWC individuals, the participants with ADPKD exhibited lower mean±SD M/I ratio (0.586±0.205 vs 0.424±0.171 [mg/kg lean/min]/(μIU/mL), P=0.04), lower median cortical perfusion (1.93 [IQR, 1.80-2.09] vs 0.68 [IQR, 0.47-1.04] mL/min/g, P<0.001) and lower median total kidney oxidative metabolism (0.17 [IQR, 0.16-0.19] vs. 0.14 [IQR, 0.12-0.15] min-1, P=0.001) in voxel-wise models excluding cysts. HTKV correlated inversely with cortical perfusion (r: -0.83, P < 0.001), total kidney oxidative metabolism (r: -0.61, P<0.001) and M/I (r: -0.41, P = 0.03).

LIMITATIONS

Small sample size and cross-sectional design.

CONCLUSIONS

Adults with ADPKD and preserved kidney function exhibited impaired renal perfusion and kidney oxidative metabolism across a wide range of cysts and kidney enlargements.

FUNDING

Grants from government (National Institutes of Health, Centers for Disease Control and Prevention) and not-for-profit (JDRF) entities.

TRIAL REGISTRATION

Registered at ClinicalTrials.gov with study numbers NCT04407481 and NCT04074668.

PLAIN-LANGUAGE SUMMARY

In our study, we explored how a common genetic kidney condition, autosomal dominant polycystic kidney disease (ADPKD), relates to kidney metabolism. ADPKD leads to the growth of numerous cysts in the kidneys, which can impact their ability to work properly. We wanted to understand the kidneys' ability to process oxygen and blood flow in ADPKD. Our approach involved using advanced imaging techniques to observe kidney metabolism and blood flow in people with ADPKD compared with healthy individuals. We discovered that those with ADPKD had significant changes in kidney oxygen metabolism even when their kidney function was still normal. These findings are crucial as they provide deeper insights into ADPKD, potentially guiding future treatments to target these changes.

AI models for automated segmentation of engineered polycystic kidney tubules

Autosomal dominant polycystic kidney disease (ADPKD) is a monogenic, rare disease, characterized by the formation of multiple cysts that grow out of the renal tubules. Despite intensive attempts to develop new drugs or repurpose existing ones, there is currently no definitive cure for ADPKD. This is primarily due to the complex and variable pathogenesis of the disease and the lack of models that can faithfully reproduce the human phenotype. Therefore, the development of models that allow automated detection of cysts' growth directly on human kidney tissue is a crucial step in the search for efficient therapeutic solutions. Artificial Intelligence methods, and deep learning algorithms in particular, can provide powerful and effective solutions to such tasks, and indeed various architectures have been proposed in the literature in recent years. Here, we comparatively review state-of-the-art deep learning segmentation models, using as a testbed a set of sequential RGB immunofluorescence images from 4 in vitro experiments with 32 engineered polycystic kidney tubules. To gain a deeper understanding of the detection process, we implemented both pixel-wise and cyst-wise performance metrics to evaluate the algorithms. Overall, two models stand out as the best performing, namely UNet++ and UACANet: the latter uses a self-attention mechanism introducing some explainability aspects that can be further exploited in future developments, thus making it the most promising algorithm to build upon towards a more refined cyst-detection platform. UACANet model achieves a cyst-wise Intersection over Union of 0.83, 0.91 for Recall, and 0.92 for Precision when applied to detect large-size cysts. On all-size cysts, UACANet averages at 0.624 pixel-wise Intersection over Union. The code to reproduce all results is freely available in a public GitHub repository.

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.

The Number and Size of Individual Kidney Medullary Pyramids is Associated with Clinical Characteristics, Kidney Biopsy Findings, and CKD Outcomes among Kidney Donors

SIGNIFICANCE STATEMENT

Segmentation of multiple structures in cross-sectional imaging is time-consuming and impractical to perform manually, especially if the end goal is clinical implementation. In this study, we developed, validated, and demonstrated the capability of a deep learning algorithm to segment individual medullary pyramids in a rapid, accurate, and reproducible manner. The results demonstrate that cortex volume, medullary volume, number of pyramids, and mean pyramid volume is associated with patient clinical characteristics and microstructural findings and provide insights into the mechanisms that may lead to CKD.

BACKGROUND

The kidney is a lobulated organ, but little is known regarding the clinical importance of the number and size of individual kidney lobes.

METHODS

After applying a previously validated algorithm to segment the cortex and medulla, a deep-learning algorithm was developed and validated to segment and count individual medullary pyramids on contrast-enhanced computed tomography images of living kidney donors before donation. The association of cortex volume, medullary volume, number of pyramids, and mean pyramid volume with concurrent clinical characteristics (kidney function and CKD risk factors), kidney biopsy morphology (nephron number, glomerular volume, and nephrosclerosis), and short- and long-term GFR <60 or <45 ml/min per 1.73 m 2 was assessed.

RESULTS

Among 2876 living kidney donors, 1132 had short-term follow-up at a median of 3.8 months and 638 had long-term follow-up at a median of 10.0 years. Larger cortex volume was associated with younger age, male sex, larger body size, higher GFR, albuminuria, more nephrons, larger glomeruli, less nephrosclerosis, and lower risk of low GFR at follow-up. Larger pyramids were associated with older age, female sex, larger body size, higher GFR, more nephrons, larger glomerular volume, more nephrosclerosis, and higher risk of low GFR at follow-up. More pyramids were associated with younger age, male sex, greater height, no hypertension, higher GFR, lower uric acid, more nephrons, less nephrosclerosis, and a lower risk of low GFR at follow-up.

CONCLUSIONS

Cortex volume and medullary pyramid volume and count reflect underlying variation in nephron number and nephron size as well as merging of pyramids because of age-related nephrosclerosis, with loss of detectable cortical columns separating pyramids.

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.

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.

A Deep Learning Approach for Automated Segmentation of Kidneys and Exophytic Cysts in Individuals with Autosomal Dominant Polycystic Kidney Disease

BACKGROUND

Total kidney volume (TKV) is an important imaging biomarker in autosomal dominant polycystic kidney disease (ADPKD). Manual computation of TKV, particularly with the exclusion of exophytic cysts, is laborious and time consuming.

METHODS

We developed a fully automated segmentation method for TKV using a deep learning network to selectively segment kidney regions while excluding exophytic cysts. We used abdominal T₂ -weighted magnetic resonance images from 210 individuals with ADPKD who were divided into two groups: one group of 157 to train the network and a second group of 53 to test it. With a 3D U-Net architecture using dataset fingerprints, the network was trained by K-fold cross-validation, in that 80% of 157 cases were for training and the remaining 20% were for validation. We used Dice similarity coefficient, intraclass correlation coefficient, and Bland-Altman analysis to assess the performance of the automated segmentation method compared with the manual method.

RESULTS

The automated and manual reference methods exhibited excellent geometric concordance (Dice similarity coefficient: mean±SD, 0.962±0.018) on the test datasets, with kidney volumes ranging from 178.9 to 2776.0 ml (mean±SD, 1058.5±706.8 ml) and exophytic cysts ranging from 113.4 to 2497.6 ml (mean±SD, 549.0±559.1 ml). The intraclass correlation coefficient was 0.9994 (95% confidence interval, 0.9991 to 0.9996; P<0.001) with a minimum bias of -2.424 ml (95% limits of agreement, -49.80 to 44.95).

CONCLUSIONS

We developed a fully automated segmentation method to measure TKV that excludes exophytic cysts and has an accuracy similar to that of a human expert. This technique may be useful in clinical studies that require automated computation of TKV to evaluate progression of ADPKD and response to treatment.

Automated measurement of total kidney volume from 3D ultrasound images of patients affected by polycystic kidney disease and comparison to MR measurements

PURPOSE

Total kidney volume (TKV) is the most important imaging biomarker for quantifying the severity of autosomal-dominant polycystic kidney disease (ADPKD). 3D ultrasound (US) can accurately measure kidney volume compared to 2D US; however, manual segmentation is tedious and requires expert annotators. We investigated a deep learning-based approach for automated segmentation of TKV from 3D US in ADPKD patients.

METHOD

We used axially acquired 3D US-kidney images in 22 ADPKD patients where each patient and each kidney were scanned three times, resulting in 132 scans that were manually segmented. We trained a convolutional neural network to segment the whole kidney and measure TKV. All patients were subsequently imaged with MRI for measurement comparison.

RESULTS

Our method automatically segmented polycystic kidneys in 3D US images obtaining an average Dice coefficient of 0.80 on the test dataset. The kidney volume measurement compared with linear regression coefficient and bias from human tracing were R² = 0.81, and - 4.42%, and between AI and reference standard were R² = 0.93, and - 4.12%, respectively. MRI and US measured kidney volumes had R² = 0.84 and a bias of 7.47%.

CONCLUSION

This is the first study applying deep learning to 3D US in ADPKD. Our method shows promising performance for auto-segmentation of kidneys using 3D US to measure TKV, close to human tracing and MRI measurement. This imaging and analysis method may be useful in a number of settings, including pediatric imaging, clinical studies, and longitudinal tracking of patient disease progression.