Automatic renal segmentation for MR urography using 3D‐GrabCut and random forests

• Published in: Magnetic resonance in medicine Vol. 79; no. 3; pp. 1696 - 1707
• Main Authors: Yoruk, Umit, Hargreaves, Brian A., Vasanawala, Shreyas S.
• Format: Journal Article
• Language: English
• Published: United States Wiley Subscription Services, Inc 01.03.2018
• Subjects: Automation; Brain mapping; Children; dynamic contrast enhanced MRI; Glomerular filtration rate; Image processing; Image segmentation; Iterative methods; machine learning; Magnetic resonance imaging; Renal cortex; renal segmentation; Urography; renal segmentation; dynamic contrast enhanced MRI; machine learning; glomerular filtration rate
• DOI: 10.1002/mrm.26806
• ISSN: 0740-3194; 1522-2594

Purpose To introduce and evaluate a fully automated renal segmentation technique for glomerular filtration rate (GFR) assessment in children. Methods An image segmentation method based on iterative graph cuts (GrabCut) was modified to work on time‐resolved 3D dynamic contrast‐enhanced MRI data sets. A random forest classifier was trained to further segment the renal tissue into cortex, medulla, and the collecting system. The algorithm was tested on 26 subjects and the segmentation results were compared to the manually drawn segmentation maps using the F1‐score metric. A two‐compartment model was used to estimate the GFR of each subject using both automatically and manually generated segmentation maps. Results Segmentation maps generated automatically showed high similarity to the manually drawn maps for the whole‐kidney (F1 = 0.93) and renal cortex (F1 = 0.86). GFR estimations using whole‐kidney segmentation maps from the automatic method were highly correlated (Spearman's ρ = 0.99) to the GFR values obtained from manual maps. The mean GFR estimation error of the automatic method was 2.98 ± 0.66% with an average segmentation time of 45 s per patient. Conclusion The automatic segmentation method performs as well as the manual segmentation for GFR estimation and reduces the segmentation time from several hours to 45 s. Magn Reson Med 79:1696–1707, 2018. © 2017 International Society for Magnetic Resonance in Medicine.