Comparison of MRI segmentation techniques for measuring liver cyst volumes in autosomal dominant polycystic kidney disease

IRIS—Intelligent Rapid Interactive Segmentation for Measuring Liver Cyst Volumes in Autosomal Dominant Polycystic Kidney Disease

Purpose: To develop and integrate interactive features with automatic methods for accurate liver cyst segmentation in patients with autosomal dominant polycystic kidney and liver disease (ADPKD). Methods: SmartClick and antiSmartClick were developed using iterative region growth guided by spatial and intensity connections and were integrated with automated level set (LS) segmentation and graphical user interface, forming an intelligent rapid interactive segmentation (IRIS) tool. IRIS and LS segmentations of liver cysts on T2 weighted images of patients with ADPKD (n = 17) were compared with manual segmentation as ground truth (GT). Results: Compared to manual GT, IRIS reduced the segmentation time by more than 10-fold. Compared to automated LS, IRIS reduced the mean liver cyst volume error from 42.22% to 13.44% (p < 0.001). IRIS segmentation agreed well with manual GT (79% dice score and 99% intraclass correlation coefficient). Conclusion: IRIS is feasible for fast, accurate liver cyst segmentation in patients with ADPKD.

Prevalence of Inferior Vena Cava Compression in ADPKD

Introduction

Kidney and liver cysts in autosomal dominant polycystic kidney disease (ADPKD) can compress the inferior vena cava (IVC), but IVC compression prevalence and its risk factors are unknown.

Methods

Patients who have ADPKD (n = 216) with abdominal magnetic resonance imaging (MRI) studies and age-/sex-matched controls (n = 216) were evaluated for IVC compression as well as azygous vein diameter (a marker of collateral blood flow) and IVC aspect ratio (left-to-right dimension divided by anterior-to-posterior dimension with a value of 1 corresponding to a circular (high pressure) IVC caudal to compression.

Results

Severe IVC compression (≥70%) was observed in 33 (15%) ADPKD subjects and mild compression (≥50% to <70%) was observed in 33 (15%) subjects; whereas controls had no IVC compression (P < 0.001). Severe IVC compression was associated with larger azygous vein (4.0 ± 1.3 mm versus 2.3 ± 0.8 mm without IVC compression; P < 0.001) and a more circular IVC cross-section upstream (mean IVC aspect ratio: 1.16 ± 0.27 vs. 1.69 ± 0.67, P < 0.001), suggesting higher pressure upstream from the compression. IVC compression was associated with older age, lower estimated glomerular filtration rate (eGFR), greater height-adjusted total kidney volumes, greater height-adjusted liver volume (ht-LV), and greater liver and renal cyst fractions (P < 0.001). No subject younger than 30 years had IVC compression, but ADPKD subjects ≥40 years old had 12-fold higher risk of IVC compression (95% confidence interval [CI]: 4.2–42.4), with highest predicted probability for Mayo Clinic classes 1D (59%; 95% CI: 39%–76%) and 1E (74%; 95% CI: 49%–90%) after adjustment (P < 0.001). Women with ht-LV ≥ 2000 ml/m had 83% (95% CI: 59%–95%) prevalence of IVC compression. Complications of IVC compression included deep vein thrombosis (DVT) and symptomatic hypotension.

Conclusions

IVC compression is common in ADPKD patients >40 years old, with Mayo Clinic class 1D/E, and in females with ht-LV > 2000 ml/m.

Hemorrhagic Cysts and Other MR Biomarkers for Predicting Renal Dysfunction Progression in Autosomal Dominant Polycystic Kidney Disease

BACKGROUND

Screening for rapidly progressing autosomal dominant polycystic kidney disease (ADPKD) is necessary for assigning and monitoring therapies. Height-adjusted total kidney volume (ht-TKV) is an accepted biomarker for clinical prognostication, but represents only a small fraction of information on abdominal MRI.

PURPOSE

To investigate the utility of other MR features of ADPKD to predict progression.

STUDY TYPE

Single-center retrospective.

POPULATION

Longitudinal data from 186 ADPKD subjects with baseline serum creatinine, PKD gene testing, abdominal MRI measurements, and ≥2 follow-up serum creatinine were reviewed.

FIELD STRENGTH/SEQUENCE

1.5T, T₂ -weighted single-shot fast spin echo, T₁ -weighted 3D spoiled gradient echo (liver accelerated volume acquisition) and 2D cine velocity encoded gradient echo (phase contrast MRA).

ASSESSMENT

Ht-TKV, renal blood flow (RBF), number and fraction of renal and hepatic cysts, bright T₁ hemorrhagic renal cysts, and liver and spleen volumes were independently assessed by three observers blinded to estimated glomerular filtration rate (eGFR) data.

STATISTICAL TESTS

Linear mixed-effect models were applied to predict eGFR over time using MRI features at baseline adjusted for confounders. Validation was performed in 158 patients who had follow-up MRI using receiver operator characteristic, sensitivity, and specificity.

RESULTS

Hemorrhagic cysts, fraction of renal and hepatic cysts, height-adjusted liver and spleen volumes were significant independent predictors of future eGFR (final prediction model R² = 0.88 P < 0.05). The number of hemorrhagic cysts significantly improved the prediction compared to ht-TKV in predicting future eGFR (area under the curve [AUC] = 0.94, 95% confidence interval [CI]: 0.9-0.94 vs. R² = 0.9, 95% CI: 0.85-0.9, P = 0.045). For baseline eGFR ≥60 ml/min/1.73m² , sensitivity for predicting eGFR<45 ml/min/1.73m² by ht-TKV alone was 29%. Sensitivity increased to 72% with all MRI variables in the model (P < 0.05 = 0.019), whereas specificity was unchanged, 100% vs. 99%.

DATA CONCLUSION

Combining multiple MR features including hemorrhagic renal cysts, renal cyst fraction, liver and spleen volume, hepatic cyst fraction, and renal blood flow enhanced sensitivity for predicting eGFR decline in ADPKD compared to the standard model including only ht-TKV. Level of Evidence 2 Technical Efficacy Stage 2 J. MAGN. RESON. IMAGING 2021;53:564-576.

Adrenal tumor segmentation method for MR images

BACKGROUND AND OBJECTIVE

Adrenal tumors, which occur on adrenal glands, are incidentally determined. The liver, spleen, spinal cord, and kidney surround the adrenal glands. Therefore, tumors on the adrenal glands can be adherent to other organs. This is a problem in adrenal tumor segmentation. In addition, low contrast, non-standardized shape and size, homogeneity, and heterogeneity of the tumors are considered as problems in segmentation.

METHODS

This study proposes a computer-aided diagnosis (CAD) system to segment adrenal tumors by eliminating the above problems. The proposed hybrid method incorporates many image processing methods, which include active contour, adaptive thresholding, contrast limited adaptive histogram equalization (CLAHE), image erosion, and region growing.

RESULTS

The performance of the proposed method was assessed on 113 Magnetic Resonance (MR) images using seven metrics: sensitivity, specificity, accuracy, precision, Dice Coefficient, Jaccard Rate, and structural similarity index (SSIM). The proposed method eliminates some of the discussed problems with success rates of 74.84%, 99.99%, 99.84%, 93.49%, 82.09%, 71.24%, 99.48% for the metrics, respectively.

CONCLUSIONS

This study presents a new method for adrenal tumor segmentation, and avoids some of the problems preventing accurate segmentation, especially for cyst-based tumors.

Relationship of Seminal Megavesicles, Prostate Median Cysts, and Genotype in Autosomal Dominant Polycystic Kidney Disease

BACKGROUND

Autosomal dominant polycystic kidney disease (ADPKD) can involve prostate and seminal vesicles but the potential interrelationship of these findings and associations with PKD gene mutation locus and type is unknown.

PURPOSE

To determine the interrelationship of seminal megavesicles (seminal vesicles with lumen diameter > 10mm) and prostatic cysts in ADPKD and to determine whether there are associations with PKD gene mutations.

STUDY TYPE

Retrospective, case control.

POPULATION

Male ADPKD subjects (n = 92) with mutations in PKD1 (n = 71; 77%) or PKD2 (n = 21; 23%), and age/gender-matched controls without ADPKD (n = 92).

FIELD STRENGTH/SEQUENCE

1.5T, axial/coronal T₂ -weighted MR images.

ASSESSMENT

Reviewers blinded to genotype independently measured seminal vesicle lumen diameter and prevalence of cysts in prostate, kidney, and liver.

STATISTICAL TESTS

Nonparametric tests for group comparisons and univariate and multivariable logistic regression analyses to identify associations of megavesicles and prostate median cysts with mutations and renal/hepatic cyst burden.

RESULTS

Seminal megavesicles were found in 23 of 92 ADPKD (25%) subjects with PKD1 (22/71, 31%) or PKD2 (n = 1/21, 5%) mutations, but in only two control subjects (P < 0.0001). Prostate median cysts were found in 17/92 (18%) ADPKD subjects, compared with only 6/92 (7%) controls (P = 0.01), and were correlated with seminal vesicle diameters (ρ = 0.24, P = 0.02). Nonmedian prostate cyst prevalence was identical between ADPKD and controls (7/92, 8%). After adjusting for age, estimated glomerular filtration rate, and height-adjusted total kidney volume, ADPKD subjects with megavesicles were 10 times more likely to have a PKD1 than a PKD2 mutation. Among PKD1 subjects, seminal megavesicles occurred more frequently with nontruncating mutations with less severe kidney involvement.

DATA CONCLUSION

ADPKD is associated with prostate median cysts near ejaculatory ducts. These cysts correlate with seminal megavesicles (dilated to >10 mm) which predict a 10-fold greater likelihood of PKD1 vs. PKD2 mutation. Cysts elsewhere in the prostate are not related to ADPKD.

LEVEL OF EVIDENCE

2 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2019;49:894-903.