Automated renal segmentation in healthy and chronic kidney disease subjects using a convolutional neural network

Daniel, Alexander; Buchanan, Charlotte; Allcock, Thomas; Scerri, Daniel; Cox, Eleanor; Prestwich, Benjamin; Francis, Susan

Abstract

Purpose: Total Kidney Volume (TKV) is an important measure in renal disease detection and monitoring. We developed a fully automated method to segment the kidneys from T2-weighted magnetic resonance images (MRI) to calculate TKV of healthy control (HC) and chronic kidney disease (CKD) patients.
Methods: This automated method uses machine learning, specifically a 2-dimensional (2D) convolutional neural network (CNN), to accurately segment the left and right kidneys from T2-weighted MRI data. The dataset consisted of 30 HC subjects and 30 CKD patients. The model was trained on 50 manually defined HC and CKD kidney segmentations. The model was subsequently evaluated on 50 test data sets, comprising data from five HCs and five CKD patients each scanned five times in a scan session to enable comparison of the precision of the CNN and manual segmentation of kidneys.
Results: The unseen test data processed by the 2D CNN had a mean Dice score of 0.93 ± 0.01. The difference between manual and automatically computed TKV was 1.2 ± 16.2 ml with a mean surface distance of 0.65 ± 0.21 mm. The variance in TKV measurements from repeat acquisitions on the same subject was significantly lower using the automated method compared to manual segmentation of the kidneys.
Conclusion: The 2D CNN method provides fully automated segmentation of the left and right kidney and calculation of TKV in under ten seconds on a standard office computer, allowing high data throughput and is a freely available executable.

Citation

Daniel, A., Buchanan, C., Allcock, T., Scerri, D., Cox, E., Prestwich, B., & Francis, S. (2021). Automated renal segmentation in healthy and chronic kidney disease subjects using a convolutional neural network. Magnetic Resonance in Medicine, 86(2), 1125-1136. https://doi.org/10.1002/mrm.28768

• Journal Article Type: Article
• Acceptance Date: Feb 16, 2021
• Online Publication Date: Mar 23, 2021
• Publication Date: Aug 1, 2021
• Deposit Date: Feb 19, 2021
• Publicly Available Date: Mar 24, 2022
• Journal: Magnetic Resonance in Medicine
• Print ISSN: 0740-3194
• Electronic ISSN: 1522-2594
• Publisher: Wiley
• Peer Reviewed: Peer Reviewed
• Volume: 86
• Issue: 2
• Pages: 1125-1136
• DOI: https://doi.org/10.1002/mrm.28768
• Public URL: https://nottingham-repository.worktribe.com/output/5334698
• Publisher URL: https://onlinelibrary.wiley.com/doi/full/10.1002/mrm.28768