Early detection of the autosomal dominant polycystic kidney disease (ADPKD) is crucial as it is one of the most common causes of end-stage renal disease (ESRD) and kidney failure. The total kidney volume (TKV) can be used as a biomarker to quantify disease progression. The TKV calculation requires accurate delineation of kidney volumes, which is usually performed manually by an expert physician. However, this is time-consuming and automated segmentation is warranted. Furthermore, the scarcity of large annotated datasets hinders the development of deep learning solutions. In this work, we address this problem by implementing three attention mechanisms into the U-Net to improve TKV estimation. Additionally, we implement a cosine loss function that works well on image classification tasks with small datasets. Lastly, we apply a technique called sharpness aware minimization (SAM) that helps improve the generalizability of networks. Our results show significant improvements (p-value < 0.05) over the reference kidney segmentation U-Net. We show that the attention mechanisms and/or the cosine loss with SAM can achieve a dice score (DSC) of 0.918, a mean symmetric surface distance (MSSD) of 1.20 mm with the mean TKV difference of −1.72%, and R2 of 0.96 while using only 100 MRI datasets for training and testing. Furthermore, we tested four ensembles and obtained improvements over the best individual network, achieving a DSC and MSSD of 0.922 and 1.09 mm, respectively.

No abstract

The prognosis of renal function decline in Autosomal Dominant Polycystic Kidney Disease (ADPKD) is vital for early intervention. Currently, the accepted biomarkers are height-adjusted total kidney volume (HtTKV) with estimated glomerular filtration rate (eGFR) and patient age. However, kidney volume delineation is time-consuming and prone to observer variability. Furthermore, improvement in prognosis can be achieved by incorporating automatically generated features of kidney MRI images in addition to the conventional biomarkers. Hence, to improve prediction we develop two deep learning algorithms. At first, we create an automated kidney volume segmentation model that can accurately calculate HtTKV. Secondly, we use the segmented kidney volumes with the predicted HtTKV, age, and eGFR at the baseline visit. Here, we use a combination of convolutional neural network (CNN) and multi-layer perceptron (MLP) for the prediction of chronic kidney disease (CKD) stages >=3A, >=3B, and a 30% decline in eGFR after 8 years from the baseline visit. We obtain AUC scores of 0.96, 0.96, and 0.95 for CKD stages >=3A, >=3B, and 30% decline in eGFR, respectively. Moreover, our algorithm achieves a Pearson correlation coefficient of 0.81 between predicted and measured eGFR decline. We further extend our approach to predict distinct CKD stages after eight years with high accuracy. The proposed approach might improve monitoring and support the prognosis of ADPKD patients from the earliest disease stages.