Automated Segmentation of Kidney Cortex and Medulla in CT Images: A Multisite Evaluation Study.
Adult
Algorithms
Contrast Media
Deep Learning
Donor Selection
/ methods
Female
Humans
Image Processing, Computer-Assisted
/ methods
Kidney Cortex
/ diagnostic imaging
Kidney Medulla
/ diagnostic imaging
Kidney Transplantation
Living Donors
Male
Middle Aged
Neural Networks, Computer
Observer Variation
Tomography, X-Ray Computed
/ methods
computed tomography
deep learning
kidney cortex
kidney medulla
kidney volume
machine learning collection
segmentation
Journal
Journal of the American Society of Nephrology : JASN
ISSN: 1533-3450
Titre abrégé: J Am Soc Nephrol
Pays: United States
ID NLM: 9013836
Informations de publication
Date de publication:
02 2022
02 2022
Historique:
received:
27
03
2021
accepted:
21
11
2021
pubmed:
9
12
2021
medline:
5
3
2022
entrez:
8
12
2021
Statut:
ppublish
Résumé
In kidney transplantation, a contrast CT scan is obtained in the donor candidate to detect subclinical pathology in the kidney. Recent work from the Aging Kidney Anatomy study has characterized kidney, cortex, and medulla volumes using a manual image-processing tool. However, this technique is time consuming and impractical for clinical care, and thus, these measurements are not obtained during donor evaluations. This study proposes a fully automated segmentation approach for measuring kidney, cortex, and medulla volumes. A total of 1930 contrast-enhanced CT exams with reference standard manual segmentations from one institution were used to develop the algorithm. A convolutional neural network model was trained ( The automated model was found to perform on par with manual segmentation, with errors similar to interobserver variability with manual segmentation. Compared with the reference standard, the automated approach achieved a Dice similarity metric of 0.94 (right cortex), 0.90 (right medulla), 0.94 (left cortex), and 0.90 (left medulla) in the test set. Similar performance was observed when the algorithm was applied on the two external datasets. A fully automated approach for measuring cortex and medullary volumes in CT images of the kidneys has been established. This method may prove useful for a wide range of clinical applications.
Sections du résumé
BACKGROUND
In kidney transplantation, a contrast CT scan is obtained in the donor candidate to detect subclinical pathology in the kidney. Recent work from the Aging Kidney Anatomy study has characterized kidney, cortex, and medulla volumes using a manual image-processing tool. However, this technique is time consuming and impractical for clinical care, and thus, these measurements are not obtained during donor evaluations. This study proposes a fully automated segmentation approach for measuring kidney, cortex, and medulla volumes.
METHODS
A total of 1930 contrast-enhanced CT exams with reference standard manual segmentations from one institution were used to develop the algorithm. A convolutional neural network model was trained (
RESULTS
The automated model was found to perform on par with manual segmentation, with errors similar to interobserver variability with manual segmentation. Compared with the reference standard, the automated approach achieved a Dice similarity metric of 0.94 (right cortex), 0.90 (right medulla), 0.94 (left cortex), and 0.90 (left medulla) in the test set. Similar performance was observed when the algorithm was applied on the two external datasets.
CONCLUSIONS
A fully automated approach for measuring cortex and medullary volumes in CT images of the kidneys has been established. This method may prove useful for a wide range of clinical applications.
Identifiants
pubmed: 34876489
pii: 00001751-202202000-00014
doi: 10.1681/ASN.2021030404
pmc: PMC8819990
doi:
Substances chimiques
Contrast Media
0
Types de publication
Evaluation Study
Journal Article
Multicenter Study
Research Support, N.I.H., Extramural
Langues
eng
Sous-ensembles de citation
IM
Pagination
420-430Subventions
Organisme : NIDDK NIH HHS
ID : K01 DK110136
Pays : United States
Organisme : NIDDK NIH HHS
ID : R01 DK090358
Pays : United States
Organisme : NIDDK NIH HHS
ID : R03 DK125632
Pays : United States
Informations de copyright
Copyright © 2022 by the American Society of Nephrology.
Références
Chapman AB, Wei W: Imaging approaches to patients with polycystic kidney disease. Semin Nephrol 31: 237–244, 2011
Liebau MC, Serra AL: Looking at the (w)hole: Magnet resonance imaging in polycystic kidney disease. Pediatr Nephrol 28: 1771–1783, 2013
Fick-Brosnahan GM: Endothelial dysfunction and angiogenesis in autosomal dominant polycystic kidney disease. Curr Hypertens Rev 9: 32–36, 2013
Grantham JJ, Torres VE, Chapman AB, Guay-Woodford LM, Bae KT, King BF Jr, et al.; CRISP Investigators: Volume progression in polycystic kidney disease. N Engl J Med 354: 2122–2130, 2006
Dias J, Malheiro J, Almeida M, Dias L, Silva-Ramos M, Martins LS, et al.: CT-based renal volume and graft function after living-donor kidney transplantation: Is there a volume threshold to avoid? Int Urol Nephrol 47: 851–859, 2015
Fananapazir G, Benzl R, Corwin MT, Chen LX, Sageshima J, Stewart SL, et al.: Predonation volume of future remnant cortical kidney helps predict postdonation renal function in live kidney donors. Radiology 288: 153–157, 2018
Wang X, Vrtiska TJ, Avula RT, Walters LR, Chakkera HA, Kremers WK, et al.: Age, kidney function, and risk factors associate differently with cortical and medullary volumes of the kidney. Kidney Int 85: 677–685, 2014
Yu ASL, Shen C, Landsittel DP, Harris PC, Torres VE, Mrug M, et al.; Consortium for Radiologic Imaging Studies of Polycystic Kidney Disease (CRISP): Baseline total kidney volume and the rate of kidney growth are associated with chronic kidney disease progression in autosomal dominant polycystic kidney disease. Kidney Int 93: 691–699, 2018
Yamashita SR, von Atzingen AC, Iared W, Bezerra AS, Ammirati AL, Canziani ME, et al.: Value of renal cortical thickness as a predictor of renal function impairment in chronic renal disease patients. Radiol Bras 48: 12–16, 2015
Snoek R, de Heus R, de Mooij KJ, Pistorius LR, Lilien MR, Lely AT, et al.: Assessing nephron hyperplasia in fetal congenital solitary functioning kidneys by measuring renal papilla number. Am J Kidney Dis 72: 465–467, 2018
Yushkevich PA, Piven J, Hazlett HC, Smith RG, Ho S, Gee JC, et al.: User-guided 3D active contour segmentation of anatomical structures: significantly improved efficiency and reliability. Neuroimage 31: 1116–1128, 2006
Denic A, Alexander MP, Kaushik V, Lerman LO, Lieske JC, Stegall MD, et al.: Detection and clinical patterns of nephron hypertrophy and nephrosclerosis among apparently healthy adults. Am J Kidney Dis 68: 58–67, 2016
Merzkani MA, Denic A, Narasimhan R, Lopez CL, Larson JJ, Kremers WK, et al.: Kidney microstructural features at the time of donation predict long-term risk of chronic kidney disease in living kidney donors. Mayo Clin Proc 96: 40–51, 2021
Issa N, Lopez CL, Denic A, Taler SJ, Larson JJ, Kremers WK, et al.: Kidney structural features from living donors predict graft failure in the recipient. J Am Soc Nephrol 31: 415–423, 2020
Thong W, Kadoury S, Piché N, Pal CJ: Convolutional networks for kidney segmentation in contrast-enhanced CT scans. Comput Methods Biomech Biomed Eng Imaging Vis 6: 277–282, 2018
Sharma K, Rupprecht C, Caroli A, Aparicio MC, Remuzzi A, Baust M, et al.: Automatic segmentation of kidneys using deep learning for total kidney volume quantification in autosomal dominant polycystic kidney disease. Sci Rep 7: 2049, 2017
Duan X, Rule AD, Elsherbiny H, Vrtiska TJ, Avula RT, Alexander MP, et al.: Automated assessment of renal cortical surface roughness from computerized tomography images and its association with age. Acad Radiol 21: 1441–1445, 2014
Rule AD, Sasiwimonphan K, Lieske JC, Keddis MT, Torres VE, Vrtiska TJ: Characteristics of renal cystic and solid lesions based on contrast-enhanced computed tomography of potential kidney donors. Am J Kidney Dis 59: 611–618, 2012
Cai Q, Geng P, Li H, Sun H, Kang Y: Semi-automatic segmentation of renal cortex and medulla based on dynamic magnetic resonance images. 2010 3rd International Conference on Biomedical Engineering and Informatics. IEEE, 2010 pp 555–559
Will S, Martirosian P, Würslin C, Schick F: Automated segmentation and volumetric analysis of renal cortex, medulla, and pelvis based on non-contrast-enhanced T1- and T2-weighted MR images. MAGMA 27: 445–454, 2014
Huang W, Li H, Wang R, Zhang X, Wang X, Zhang J: A self-supervised strategy for fully automatic segmentation of renal dynamic contrast-enhanced magnetic resonance images. Med Phys 46: 4417–4430, 2019
Xiang D, Bagci U, Jin C, Shi F, Zhu W, Yao J, et al.: CorteXpert: A model-based method for automatic renal cortex segmentation. Med Image Anal 42: 257–273, 2017
Chen X, Summers RM, Cho M, Bagci U, Yao J: An automatic method for renal cortex segmentation on CT images: Evaluation on kidney donors. Acad Radiol 19: 562–570, 2012
Greenspan H, Ginneken BV, Summers RM: Guest editorial deep learning in medical imaging: Overview and future promise of an exciting new technique. IEEE Trans Med Imaging 35: 1153–1159, 2016
van Gastel MDA, Edwards ME, Torres VE, Erickson BJ, Gansevoort RT, Kline TL: Automatic measurement of kidney and liver volumes from MR images of patients affected by autosomal dominant polycystic kidney disease. J Am Soc Nephrol 30: 1514–1522, 2019
Yasaka K, Abe O: Deep learning and artificial intelligence in radiology: Current applications and future directions. PLoS Med 15: e1002707, 2018
Weston AD, Korfiatis P, Philbrick KA, Conte GM, Kostandy P, Sakinis T, et al.: Complete abdomen and pelvis segmentation using U-net variant architecture. Med Phys 47: 5609–5618, 2020
Jin C, Shi F, Xiang D, Zhang L, Chen X: Fast segmentation of kidney components using random forests and ferns. Med Phys 44: 6353–6363, 2017
Davenport MS, Khalatbari S, Cohan RH, Dillman JR, Myles JD, Ellis JH: Contrast material-induced nephrotoxicity and intravenous low-osmolality iodinated contrast material: Risk stratification by using estimated glomerular filtration rate. Radiology 268: 719–728, 2013