Automatic Segmentation of Kidneys using Deep Learning for Total Kidney Volume Quantification in Autosomal Dominant Polycystic Kidney Disease

Autosomal Dominant Polycystic Kidney Disease (ADPKD) is the most common inherited disorder of the kidneys. It is characterized by enlargement of the kidneys caused by progressive development of renal cysts, and thus assessment of total kidney volume (TKV) is crucial for studying disease progression in ADPKD. However, automatic segmentation of polycystic kidneys is a challenging task due to severe alteration in the morphology caused by non-uniform cyst formation and presence of adjacent liver cysts. In this study, an automated segmentation method based on deep learning has been proposed for TKV computation on computed tomography (CT) dataset of ADPKD patients exhibiting mild to moderate or severe renal insufficiency. The proposed method has been trained (n = 165) and tested (n = 79) on a wide range of TKV (321.2-14,670.7 mL) achieving an overall mean Dice Similarity Coefficient of 0.86 ± 0.07 (mean ± SD) between automated and manual segmentations from clinical experts and a mean correlation coefficient (ρ) of 0.98 (p < 0.001) for segmented kidney volume measurements in the entire test set. Our method facilitates fast and reproducible measurements of kidney volumes in agreement with manual segmentations from clinical experts.

Effect of Sirolimus on Disease Progression in Patients with Autosomal Dominant Polycystic Kidney Disease and CKD Stages 3b-4

BACKGROUND AND OBJECTIVES

The effect of mammalian target of rapamycin (mTOR) inhibitors has never been tested in patients with autosomal dominant polycystic kidney disease (ADPKD) and severe renal insufficiency.

DESIGN, SETTING, PARTICIPANTS, & MEASUREMENTS

In this academic, prospective, randomized, open label, blinded end point, parallel group trial (ClinicalTrials.gov no. NCT01223755), 41 adults with ADPKD, CKD stage 3b or 4, and proteinuria ≤0.5 g/24 h were randomized between September of 2010 and March of 2012 to sirolimus (3 mg/d; serum target levels of 5-10 ng/ml) added on to conventional therapy (n=21) or conventional treatment alone (n=20). Primary outcome was GFR (iohexol plasma clearance) change at 1 and 3 years versus baseline.

RESULTS

At the 1-year preplanned interim analysis, GFR fell from 26.7±5.8 to 21.3±6.3 ml/min per 1.73 m(2) (P<0.001) and from 29.6±5.6 to 24.9±6.2 ml/min per 1.73 m(2) (P<0.001) in the sirolimus and conventional treatment groups, respectively. Albuminuria (73.8±81.8 versus 154.9±152.9 μg/min; P=0.02) and proteinuria (0.3±0.2 versus 06±0.4 g/24 h; P<0.01) increased with sirolimus. Seven patients on sirolimus versus one control had de novo proteinuria (P=0.04), ten versus three patients doubled proteinuria (P=0.02), 18 versus 11 patients had peripheral edema (P=0.04), and 14 versus six patients had upper respiratory tract infections (P=0.03). Three patients on sirolimus had angioedema, 14 patients had aphthous stomatitis, and seven patients had acne (P<0.01 for both versus controls). Two patients progressed to ESRD, and two patients withdrew because of worsening of proteinuria. These events were not observed in controls. Thus, the independent data and safety monitoring board recommend early trial termination for safety reasons. At 1 year, total kidney volume (assessed by contrast-enhanced computed tomography imaging) increased by 9.0% from 2857.7±1447.3 to 3094.6±1519.5 ml on sirolimus and 4.3% from 3123.4±1695.3 to 3222.6±1651.4 ml on conventional therapy (P=0.12). On follow-up, 37% and 7% of serum sirolimus levels fell below or exceeded the therapeutic range, respectively.

CONCLUSIONS

Finding that sirolimus was unsafe and ineffective in patients with ADPKD and renal insufficiency suggests that mTOR inhibitor therapy may be contraindicated in this context.