Kidney segmentation in neck-to-knee body MRI of 40,000 UK Biobank participants

The UK Biobank is collecting extensive data on health-related characteristics of over half a million volunteers. The biological samples of blood and urine can provide valuable insight on kidney function, with important links to cardiovascular and metabolic health. Further information on kidney anatomy could be obtained by medical imaging. In contrast to the brain, heart, liver, and pancreas, no dedicated Magnetic Resonance Imaging (MRI) is planned for the kidneys. An image-based assessment is nonetheless feasible in the neck-to-knee body MRI intended for abdominal body composition analysis, which also covers the kidneys. In this work, a pipeline for automated segmentation of parenchymal kidney volume in UK Biobank neck-to-knee body MRI is proposed. The underlying neural network reaches a relative error of 3.8%, with Dice score 0.956 in validation on 64 subjects, close to the 2.6% and Dice score 0.962 for repeated segmentation by one human operator. The released MRI of about 40,000 subjects can be processed within one day, yielding volume measurements of left and right kidney. Algorithmic quality ratings enabled the exclusion of outliers and potential failure cases. The resulting measurements can be studied and shared for large-scale investigation of associations and longitudinal changes in parenchymal kidney volume.

[1]  P. Elliott,et al.  UK Biobank: An Open Access Resource for Identifying the Causes of a Wide Range of Complex Diseases of Middle and Old Age , 2015, PLoS medicine.

[2]  Daw-Tung Lin,et al.  Computer-aided kidney segmentation on abdominal CT images , 2006, IEEE Transactions on Information Technology in Biomedicine.

[3]  Ben Glocker,et al.  Automated cardiovascular magnetic resonance image analysis with fully convolutional networks , 2017, Journal of Cardiovascular Magnetic Resonance.

[4]  Joel Kullberg,et al.  Large-scale biometry with interpretable neural network regression on UK Biobank body MRI , 2020, Scientific reports.

[5]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[6]  Andrea Remuzzi,et al.  Kidney volume measurement methods for clinical studies on autosomal dominant polycystic kidney disease , 2017, PloS one.

[7]  Nassir Navab,et al.  Automatic Segmentation of Kidneys using Deep Learning for Total Kidney Volume Quantification in Autosomal Dominant Polycystic Kidney Disease , 2017, Scientific Reports.

[8]  Michael Brady,et al.  Deep Quantitative Liver Segmentation and Vessel Exclusion to Assist in Liver Assessment , 2017, MIUA.

[9]  Nicholas Ayache,et al.  3-D Consistent and Robust Segmentation of Cardiac Images by Deep Learning With Spatial Propagation , 2018, IEEE Transactions on Medical Imaging.

[10]  Yi Liu,et al.  Automated Measurement of Pancreatic Fat and Iron Concentration Using Multi-Echo and T1-Weighted MRI Data , 2020, 2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI).

[11]  Walter K. Kremers,et al.  Age, kidney function, and risk factors associate differently with cortical and medullary volumes of the kidney , 2013, Kidney international.

[12]  Klaus H. Maier-Hein,et al.  An attempt at beating the 3D U-Net , 2019, Submissions to the 2019 Kidney Tumor Segmentation Challenge: KiTS19.

[13]  M. Hughson,et al.  Nephron number, glomerular volume, renal disease and hypertension , 2008, Current opinion in nephrology and hypertension.

[14]  Andreas Östling,et al.  Automated Kidney Segmentation in Magnetic Resonance Imaging using U-Net , 2019 .

[15]  Raja Muthupillai,et al.  Normal values for renal length and volume as measured by magnetic resonance imaging. , 2006, Clinical journal of the American Society of Nephrology : CJASN.

[16]  Hao Chen,et al.  The Liver Tumor Segmentation Benchmark (LiTS) , 2019, Medical Image Anal..

[17]  Huazhong Shu,et al.  Automatic kidney segmentation in CT images based on multi-atlas image registration , 2014, 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[18]  Caroline S. Fox,et al.  Clinical associations of total kidney volume: the Framingham Heart Study , 2016, Nephrology, dialysis, transplantation : official publication of the European Dialysis and Transplant Association - European Renal Association.

[19]  Alejandro F. Frangi,et al.  Quantitative CMR population imaging on 20, 000 subjects of the UK Biobank imaging study: LV/RV quantification pipeline and its evaluation , 2019, Medical Image Anal..

[20]  Alexey Shvets,et al.  TernausNet: U-Net with VGG11 Encoder Pre-Trained on ImageNet for Image Segmentation , 2018, Computer-Aided Analysis of Gastrointestinal Videos.

[21]  Yaozong Gao,et al.  The state of the art in kidney and kidney tumor segmentation in contrast-enhanced CT imaging: Results of the KiTS19 Challenge , 2019, Medical Image Anal..

[22]  Ralf Herwig,et al.  Kidney fusion anomalies revisited: clinical and radiological analysis of 209 cases of crossed fused ectopia and horseshoe kidney , 2009, BJU international.

[23]  J G Houston,et al.  A clinical MRI investigation of the relationship between kidney volume measurements and renal function in patients with renovascular disease. , 2007, The British journal of radiology.

[24]  Xiao Han,et al.  MR‐based synthetic CT generation using a deep convolutional neural network method , 2017, Medical physics.

[25]  Eshan Sharma,et al.  Analysis of drought-responsive signalling network in two contrasting rice cultivars using transcriptome-based approach , 2017, Scientific Reports.

[26]  Magnus Borga,et al.  Feasibility of MR-Based Body Composition Analysis in Large Scale Population Studies , 2016, PloS one.

[27]  Jef Vandemeulebroucke,et al.  Registration strategies for multi‐modal whole‐body MRI mosaicing , 2018, Magnetic resonance in medicine.

[28]  Aly A. Farag,et al.  Graph Cuts Framework for Kidney Segmentation with Prior Shape Constraints , 2007, MICCAI.

[29]  J F Pedersen,et al.  Kidney dimensions at sonography: correlation with age, sex, and habitus in 665 adult volunteers. , 1993, AJR. American journal of roentgenology.

[30]  Ayman El-Baz,et al.  3D kidney segmentation from abdominal diffusion MRI using an appearance-guided deformable boundary , 2018, PloS one.

[31]  E E de Lange,et al.  In vitro measurement of kidney size: comparison of ultrasonography and MRI. , 1998, Ultrasound in medicine & biology.

[32]  Ben Glocker,et al.  Automated quality control in image segmentation: application to the UK Biobank cardiovascular magnetic resonance imaging study , 2019, Journal of Cardiovascular Magnetic Resonance.

[33]  G. Pazour,et al.  Ror2 signaling regulates Golgi structure and transport through IFT20 for tumor invasiveness , 2017, Scientific Reports.

[34]  Filip Malmberg,et al.  SmartPaint: a tool for interactive segmentation of medical volume images , 2017, Comput. methods Biomech. Biomed. Eng. Imaging Vis..

[35]  H. Parving,et al.  Risk factors for development of incipient and overt diabetic nephropathy in type 1 diabetic patients: a 10-year prospective observational study. , 2002, Diabetes care.