Premium
Performance of an automated segmentation algorithm for 3D MR renography
Author(s) -
Rusinek Henry,
Boykov Yuri,
Kaur Manmeen,
Wong Samson,
Bokacheva Louisa,
Sajous Jan B.,
Huang Ambrose J.,
Heller Samantha,
Lee Vivian S.
Publication year - 2007
Publication title -
magnetic resonance in medicine
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.696
H-Index - 225
eISSN - 1522-2594
pISSN - 0740-3194
DOI - 10.1002/mrm.21240
Subject(s) - segmentation , renal function , kidney , computer science , renal cortex , renal medulla , algorithm , nuclear medicine , medicine , artificial intelligence
The accuracy and precision of an automated graph‐cuts (GC) segmentation technique for dynamic contrast‐enhanced (DCE) 3D MR renography (MRR) was analyzed using 18 simulated and 22 clinical datasets. For clinical data, the error was 7.2 ± 6.1 cm 3 for the cortex and 6.5 ± 4.6 cm 3 for the medulla. The precision of segmentation was 7.1 ± 4.2 cm 3 for the cortex and 7.2 ± 2.4 cm 3 for the medulla. Compartmental modeling of kidney function in 22 kidneys yielded a renal plasma flow (RPF) error of 7.5% ± 4.5% and single‐kidney GFR error of 13.5% ± 8.8%. The precision was 9.7% ± 6.4% for RPF and 14.8% ± 11.9% for GFR. It took 21 min to segment one kidney using GC, compared to 2.5 hr for manual segmentation. The accuracy and precision in RPF and GFR appear acceptable for clinical use. With expedited image processing, DCE 3D MRR has the potential to expand our knowledge of renal function in individual kidneys and to help diagnose renal insufficiency in a safe and noninvasive manner. Magn Reson Med 57:1159–1167, 2007. © 2007 Wiley‐Liss, Inc.