Computer-Aided Diagnostic System for Early Detection of Acute Renal Transplant Rejection Using Diffusion-Weighted MRI

<italic>Objective:</italic> Early diagnosis of acute renal transplant rejection (ARTR) is critical for accurate treatment. Although the current gold standard, diagnostic technique is renal biopsy, it is not preferred due to its invasiveness, long recovery time (1–2 weeks), and potential for complications, e.g., bleeding and/or infection. <italic>Methods:</italic> This paper presents a computer-aided diagnostic (CAD) system for early ARTR detection using (3D + <inline-formula><tex-math notation="LaTeX">$b$</tex-math></inline-formula>-value) diffusion-weighted (DW) magnetic resonance imaging (MRI) data. The CAD process starts from kidney tissue segmentation with an evolving geometric (level-set-based) deformable model. The evolution is guided by a voxel-wise stochastic speed function, which follows from a joint kidney-background Markov–Gibbs random field model accounting for an adaptive kidney shape prior and on-going kidney-background visual appearances. A B-spline-based three-dimensional data alignment is employed to handle local deviations due to breathing and heart beating. Then, empirical cumulative distribution functions of apparent diffusion coefficients of the segmented DW-MRI at different <inline-formula><tex-math notation="LaTeX">$b$</tex-math></inline-formula>-values are collected as discriminatory transplant status features. Finally, a deep-learning-based classifier with stacked nonnegative constrained autoencoders is employed to distinguish between rejected and nonrejected renal transplants. <italic>Results:</italic> In our initial “leave-one-subject-out” experiment on 100 subjects, <inline-formula><tex-math notation="LaTeX">$\text{97.0}\%$</tex-math></inline-formula> of the subjects were correctly classified. The subsequent four-fold and ten-fold cross-validations gave the average accuracy of <inline-formula><tex-math notation="LaTeX">$\text{96.0}\%$</tex-math></inline-formula> and <inline-formula><tex-math notation="LaTeX">$\text{94.0}\%$</tex-math></inline-formula>, respectively. <italic>Conclusion:</italic> These results demonstrate the promise of this new CAD system to reliably diagnose renal transplant rejection. <italic>Significance:</italic> The technology presented here can significantly impact the quality of care of renal transplant patients since it has the potential to replace the gold standard in kidney diagnosis, biopsy.

[1]  Sarah Jane Delany.  k-Nearest Neighbour Classifiers , 2007 .

[2]  Jacek Jakubowski,et al.  Kidney Segmentation in CT Data Using Hybrid Level-Set Method with Ellipsoidal Shape Constraints , 2017 .

[3]  W. Clem Karl,et al.  Coupled Shape Distribution-Based Segmentation of Multiple Objects , 2005, IPMI.

[4]  P. Foti,et al.  Magnetic resonance with diffusion-weighted imaging in the evaluation of transplanted kidneys: updating results in 35 patients. , 2012, Transplantation proceedings.

[5]  Erlend Hodneland,et al.  In vivo estimation of glomerular filtration in the kidney using DCE-MRI , 2011, 2011 7th International Symposium on Image and Signal Processing and Analysis (ISPA).

[6]  Klaus D. Tönnies,et al.  Prior Shape Level Set Segmentation on Multistep Generated Probability Maps of MR Datasets for Fully Automatic Kidney Parenchyma Volumetry , 2012, IEEE Transactions on Medical Imaging.

[7]  Dinggang Shen,et al.  Brain Tissue Segmentation Based on Diffusion MRI Using ℓ0 Sparse-Group Representation Classification , 2015, MICCAI.

[8]  Boleslaw K. Szymanski,et al.  Synergy Landscapes: A Multilayer Network for Collaboration in Biological Research , 2016, NetSci-X.

[9]  Arvid Lundervold,et al.  ssessment of 3 D DCE-MRI of the kidneys using non-rigid image registration nd segmentation of voxel time courses rank , 2009 .

[10]  Aly A. Farag,et al.  A kidney segmentation approach from DCE-MRI using level sets , 2008, 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops.

[11]  Abhinav Vishnu,et al.  Deep learning for computational chemistry , 2017, J. Comput. Chem..

[12]  Peter Glöckner,et al.  Why Does Unsupervised Pre-training Help Deep Learning? , 2013 .

[13]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[14]  T. El-Diasty,et al.  Role of diffusion-weighted MRI in diagnosis of acute renal allograft dysfunction: a prospective preliminary study. , 2012, The British journal of radiology.

[15]  Mads Nielsen,et al.  Locally Orderless Registration for Diffusion Weighted Images , 2015, MICCAI.

[16]  Jing-jing Xu,et al.  [Value of diffusion-weighted MR imaging in diagnosis of acute rejection after renal transplantation]. , 2010, Zhejiang da xue xue bao. Yi xue ban = Journal of Zhejiang University. Medical sciences.

[17]  C. Boesch,et al.  Evaluation of renal allograft function early after transplantation with diffusion-weighted MR imaging , 2010, European Radiology.

[18]  Aly A. Farag,et al.  Curve/Surface Representation and Evolution Using Vector Level Sets with Application to the Shape-Based Segmentation Problem , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[19]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[20]  Guido Gerig,et al.  Valmet: A New Validation Tool for Assessing and Improving 3D Object Segmentation , 2001, MICCAI.

[21]  Narayan Prasad,et al.  Assessment of allograft function using diffusion-weighted magnetic resonance imaging in kidney transplant patients. , 2014, Saudi journal of kidney diseases and transplantation : an official publication of the Saudi Center for Organ Transplantation, Saudi Arabia.

[22]  Mubarak Shah,et al.  Modeling Interaction for Segmentation of Neighboring Structures , 2009, IEEE Transactions on Information Technology in Biomedicine.

[23]  Henry Rusinek,et al.  Dynamic three-dimensional MR renography for the measurement of single kidney function: initial experience. , 2003, Radiology.

[24]  Guangyi Liu,et al.  Detection of renal allograft rejection using blood oxygen level-dependent and diffusion weighted magnetic resonance imaging: a retrospective study , 2014, BMC Nephrology.

[25]  Bram van Ginneken,et al.  A survey on deep learning in medical image analysis , 2017, Medical Image Anal..

[26]  W Greg Miller,et al.  Recommendations for improving serum creatinine measurement: a report from the Laboratory Working Group of the National Kidney Disease Education Program. , 2006, Clinical chemistry.

[27]  Ayman El-Baz,et al.  A novel framework for automatic segmentation of kidney from DW-MRI , 2015, 2015 IEEE 12th International Symposium on Biomedical Imaging (ISBI).

[28]  Jacek M. Zurada,et al.  Deep Learning of Part-Based Representation of Data Using Sparse Autoencoders With Nonnegativity Constraints , 2016, IEEE Transactions on Neural Networks and Learning Systems.

[29]  Gemma C. Garriga,et al.  Permutation Tests for Studying Classifier Performance , 2009, 2009 Ninth IEEE International Conference on Data Mining.

[30]  A. El-Baz,et al.  Towards non-invasive diagnostic techniques for early detection of acute renal transplant rejection: A review , 2017 .

[31]  Syed Muhammad Anwar,et al.  Deep Learning in Medical Image Analysis , 2017 .

[32]  M. Buonocore,et al.  Functional, dynamic, and anatomic MR urography: feasibility and preliminary findings. , 2001, Academic radiology.

[33]  Geoffrey E. Hinton,et al.  Reducing the Dimensionality of Data with Neural Networks , 2006, Science.

[34]  G Giuffrida,et al.  Magnetic resonance with diffusion-weighted imaging in the evaluation of transplanted kidneys: preliminary findings. , 2011, Transplantation proceedings.

[35]  Ayman El-Baz,et al.  Dynamic Contrast-Enhanced MRI-Based Early Detection of Acute Renal Transplant Rejection , 2013, IEEE Transactions on Medical Imaging.

[36]  N. Komodakis,et al.  Non-rigid Registration using Discrete MRFs: Application to Thoracic CT Images , 2010 .

[37]  Trevor Hastie,et al.  An Introduction to Statistical Learning , 2013, Springer Texts in Statistics.

[38]  Amy C. Dwyer,et al.  Models and methods for analyzing DCE-MRI: a review. , 2014, Medical physics.

[39]  Ayman El-Baz,et al.  A level set-based framework for 3D kidney segmentation from diffusion MR images , 2015, 2015 IEEE International Conference on Image Processing (ICIP).

[40]  Gábor Székely,et al.  Simultaneous Denoising and Registration for Accurate Cardiac Diffusion Tensor Reconstruction from MRI , 2015, MICCAI.

[41]  Ronald Fedkiw,et al.  Level set methods and dynamic implicit surfaces , 2002, Applied mathematical sciences.

[42]  Henry Rusinek,et al.  New magnetic resonance imaging methods in nephrology , 2013, Kidney international.

[43]  Leo Breiman,et al.  Classification and Regression Trees , 1984 .

[44]  Denis Le Bihan,et al.  Imagerie de diffusion in-vivo par résonance magnétique nucléaire , 1985 .

[45]  Ian H. Witten,et al.  The WEKA data mining software: an update , 2009, SKDD.

[46]  Thomas Hofmann,et al.  Greedy Layer-Wise Training of Deep Networks , 2007 .

[47]  Ayman El-Baz,et al.  Precise Segmentation of 3-D Magnetic Resonance Angiography , 2012, IEEE Transactions on Biomedical Engineering.

[48]  Hyun Ah Song,et al.  Hierarchical Representation Using NMF , 2013, ICONIP.

[49]  Aly A. Farag,et al.  Precise segmentation of multimodal images , 2006, IEEE Transactions on Image Processing.

[50]  Brian B. Avants,et al.  N4ITK: Improved N3 Bias Correction , 2010, IEEE Transactions on Medical Imaging.

[51]  Pascal Vincent,et al.  Representation Learning: A Review and New Perspectives , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[52]  Tony F. Chan,et al.  Active contours without edges , 2001, IEEE Trans. Image Process..

[53]  Yoshua. Bengio,et al.  Learning Deep Architectures for AI , 2007, Found. Trends Mach. Learn..

[54]  O. Faugeras,et al.  Statistical shape influence in geodesic active contours , 2002, 5th IEEE EMBS International Summer School on Biomedical Imaging, 2002..

[55]  Yadong Wang,et al.  Shape–intensity prior level set combining probabilistic atlas and probability map constrains for automatic liver segmentation from abdominal CT images , 2016, International Journal of Computer Assisted Radiology and Surgery.

[56]  L. R. Dice.  Measures of the Amount of Ecologic Association Between Species , 1945 .