Automatic Renal Segmentation in DCE-MRI using Convolutional Neural Networks

TL;DR

This paper introduces a fast, fully automated 3D CNN-based method for renal segmentation in DCE-MRI images, achieving high accuracy and efficiency for both normal and hydronephrotic kidneys in children.

Contribution

It presents a novel cascaded 3D CNN approach that effectively combines spatial and temporal information for kidney localization and segmentation.

Findings

Achieved mean dice coefficient of 91.4 for normal kidneys.

Achieved mean dice coefficient of 83.6 for abnormal kidneys.

Segmentation runs in seconds, demonstrating high efficiency.

Abstract

Kidney function evaluation using dynamic contrast-enhanced MRI (DCE-MRI) images could help in diagnosis and treatment of kidney diseases of children. Automatic segmentation of renal parenchyma is an important step in this process. In this paper, we propose a time and memory efficient fully automated segmentation method which achieves high segmentation accuracy with running time in the order of seconds in both normal kidneys and kidneys with hydronephrosis. The proposed method is based on a cascaded application of two 3D convolutional neural networks that employs spatial and temporal information at the same time in order to learn the tasks of localization and segmentation of kidneys, respectively. Segmentation performance is evaluated on both normal and abnormal kidneys with varying levels of hydronephrosis. We achieved a mean dice coefficient of 91.4 and 83.6 for normal and abnormal kidneys of pediatric patients, respectively.