Automated detection of chronic kidney disease using higher-order features and elongated quinary patterns from B-mode ultrasound images

Chronic kidney disease (CKD) is a continuing loss of kidney function, and early detection of this disease is fundamental to halting its progression to end-stage disease. Numerous methods have been proposed to detect CKD, mainly focusing on classification based upon peripheral clinical parameters and quantitative ultrasound parameters that must be manually calculated, or on shear wave elastography. No studies have been found that detect the presence or absence of CKD based solely from one B-mode ultrasound image. In this work, we propose an automated system to detect chronic kidney disease utilizing only the automatic extraction of features from a B-mode ultrasound image of the kidney, with a database of 405 images. Higher-order bispectrum and cumulants, and elongated quinary patterns, are extracted from each image to provide a final total of 24,480 features per image. These features were subjected to a locality sensitive discriminant analysis (LSDA) technique, which provides 30 LSDA coefficients. The coefficients were arranged according to their t value and inserted into various classifiers, to yield the best diagnostic accuracy using the least number of features. The best performance was obtained using a support vector machine and a radial basis function, utilizing only five features, resulting in an accuracy of 99.75%, a sensitivity of 100%, and a specificity of 99.57%. Based upon these findings, it is evident that the technique accurately and automatically identifies subjects with and without CKD from B-mode ultrasound images.

[1]  Varshika Pandey,et al.  MRI Image Segmentation Using Shannon and Non Shannon Entropy Measures , 2014 .

[2]  Y. Skaik.  Understanding and using sensitivity, specificity and predictive values , 2008, Indian journal of ophthalmology.

[3]  Satnam Singh Dlay,et al.  Multi-gradient features and elongated quinary pattern encoding for image-based facial expression recognition , 2017, Pattern Recognit..

[4]  D. Miron,et al.  Urinary tract infection: is there a need for routine renal ultrasonography? , 2004, Archives of Disease in Childhood.

[5]  Michelle Chen,et al.  A Model for Spheroid versus Monolayer Response of SK-N-SH Neuroblastoma Cells to Treatment with 15-Deoxy-PGJ 2 , 2016, Comput. Math. Methods Medicine.

[6]  Anjan Gudigar,et al.  Optimized multi-level elongated quinary patterns for the assessment of thyroid nodules in ultrasound images , 2018, Comput. Biol. Medicine.

[7]  Jing Gao,et al.  Multiparametric Quantitative Ultrasound Imaging to Assess Chronic Kidney Disease , 2017 .

[8]  Anjan Gudigar,et al.  Automated system for the detection of thoracolumbar fractures using a CNN architecture , 2018, Future Gener. Comput. Syst..

[9]  Abhay Bansal,et al.  Chronic Kidney Disease analysis using data mining classification techniques , 2016, 2016 6th International Conference - Cloud System and Big Data Engineering (Confluence).

[10]  Wangxin Yu,et al.  Characterization of Surface EMG Signal Based on Fuzzy Entropy , 2007, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[11]  Valquiria Aparecida Rosa Duarte,et al.  A multiagent player system composed by expert agents in specific game stages operating in high performance environment , 2017, Applied Intelligence.

[12]  Josef Coresh,et al.  Chronic kidney disease , 2012, The Lancet.

[13]  G. Crooks.  On Measures of Entropy and Information , 2015 .

[14]  John D. Austin,et al.  Adaptive histogram equalization and its variations , 1987 .

[15]  Anjan Gudigar,et al.  Automated characterization of fatty liver disease and cirrhosis using curvelet transform and entropy features extracted from ultrasound images , 2016, Comput. Biol. Medicine.

[16]  Daren Yu,et al.  Entropies Of Fuzzy Indiscernibility Relation And Its Operations , 2005, Int. J. Uncertain. Fuzziness Knowl. Based Syst..

[17]  Hojjat Adeli,et al.  A novel machine learning‐based algorithm to detect damage in high‐rise building structures , 2017 .

[18]  Ferran Torres,et al.  Are prediction equations for glomerular filtration rate useful for the long-term monitoring of type 2 diabetic patients? , 2006, Nephrology, dialysis, transplantation : official publication of the European Dialysis and Transplant Association - European Renal Association.

[19]  Kun Zhou,et al.  Locality Sensitive Discriminant Analysis , 2007, IJCAI.

[20]  David G. Stork,et al.  Pattern Classification , 1973 .

[21]  Chandan Chakraborty,et al.  Application of Higher Order cumulant Features for Cardiac Health Diagnosis using ECG signals , 2013, Int. J. Neural Syst..

[22]  L. Barozzi,et al.  The role of ultrasonography in the study of medical nephropathy. , 2007, Journal of ultrasound.

[23]  Sang Joon Kim,et al.  A Mathematical Theory of Communication , 2006 .

[24]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[25]  M.R. Raghuveer,et al.  Bispectrum estimation: A digital signal processing framework , 1987, Proceedings of the IEEE.

[26]  U. Rajendra Acharya,et al.  Automated EEG-based screening of depression using deep convolutional neural network , 2018, Comput. Methods Programs Biomed..

[27]  Leonid Churilov,et al.  Estimating glomerular filtration rate: Performance of the CKD-EPI equation over time in patients with type 2 diabetes. , 2016, Journal of diabetes and its complications.

[28]  Andrew K. C. Wong,et al.  A new method for gray-level picture thresholding using the entropy of the histogram , 1985, Comput. Vis. Graph. Image Process..

[29]  Sang Won Han,et al.  The efficacy of ultrasound and dimercaptosuccinic acid scan in predicting vesicoureteral reflux in children below the age of 2 years with their first febrile urinary tract infection , 2009, Pediatric Nephrology.

[30]  Anushya Vijayananthan,et al.  Shear wave elastography in the evaluation of renal parenchymal stiffness in patients with chronic kidney disease. , 2018, The British journal of radiology.

[31]  Poonam Sinha,et al.  Comparative Study of Chronic Kidney Disease Prediction using KNN and SVM , 2015 .

[32]  U. Raghavendra,et al.  Age-related Macular Degeneration detection using deep convolutional neural network , 2018, Future Gener. Comput. Syst..

[33]  Pawel Plawiak,et al.  Novel genetic ensembles of classifiers applied to myocardium dysfunction recognition based on ECG signals , 2017, Swarm Evol. Comput..

[34]  Shigeo Abe DrEng.  Pattern Classification , 2001, Springer London.

[35]  Mitra Mahdavi-Mazdeh,et al.  Predicting Renal Failure Progression in Chronic Kidney Disease Using Integrated Intelligent Fuzzy Expert System , 2016, Comput. Math. Methods Medicine.

[36]  Lambodar Jena,et al.  Distributed Data Mining Classification Algorithms for Prediction of Chronic- Kidney-Disease , 2015 .

[37]  U. Rajendra Acharya,et al.  Application of stacked convolutional and long short-term memory network for accurate identification of CAD ECG signals , 2018, Comput. Biol. Medicine.

[38]  Dr. S. Vijayarani,et al.  KIDNEY DISEASE PREDICTION USING SVM AND ANN ALGORITHMS , 2015 .

[39]  E. Porrini,et al.  An Overview of Errors and Flaws of Estimated GFR versus True GFR in Patients with Diabetes Mellitus , 2016, Nephron.

[40]  June-Goo Lee,et al.  Deep Learning in Medical Imaging: General Overview , 2017, Korean journal of radiology.

[41]  U. Rajendra Acharya,et al.  Deep convolutional neural network for the automated diagnosis of congestive heart failure using ECG signals , 2018, Applied Intelligence.

[42]  Aytekin Oto,et al.  ACR Appropriateness Criteria(®) on renal failure. , 2014, The American journal of medicine.

[43]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[44]  J. Radon.  On the determination of functions from their integral values along certain manifolds , 1986, IEEE Transactions on Medical Imaging.

[45]  Chandan Chakraborty,et al.  Cardiac decision making using higher order spectra , 2013, Biomed. Signal Process. Control..

[46]  Krzysztof Rzecki,et al.  Approximation of Phenol Concentration Using Computational Intelligence Methods Based on Signals From the Metal-Oxide Sensor Array , 2015, IEEE Sensors Journal.

[47]  Claude E. Shannon,et al.  The mathematical theory of communication , 1950 .

[48]  Anthony E. Samir,et al.  Shear wave elastography in chronic kidney disease: a pilot experience in native kidneys , 2015, BMC Nephrology.

[49]  L. Kennedy,et al.  Monitoring Kidney Function in Type 2 Diabetic Patients With Incipient and Overt Diabetic NephropathyRossing P, Pedersen O, Rossing K, et al (Steno Diabetes Ctr, Gentofte, Denmark; Univ of Aarhus, Denmark) Diabetes Care 29:1024–1030, 2006§ , 2007 .

[50]  U. Rajendra Acharya,et al.  Deep learning for healthcare applications based on physiological signals: A review , 2018, Comput. Methods Programs Biomed..