Login Register Cart 0
Generic placeholder image

Current Medical Imaging

Editor-in-Chief

ISSN (Print): 1573-4056
ISSN (Online): 1875-6603

Back
Journal Home About Journal Editorial Board Journal Insight Current Issue Volumes/Issues
Subscribe
Research Article

Diagnosis of Renal Diseases Based on Machine Learning Methods Using Ultrasound Images

Author(s): Guanghan Li, Jian Liu, Jingping Wu, Yan Tian, Liyong Ma, Yuejun Liu, Bo Zhang, Shan Mou and Min Zheng*

Volume 17, Issue 3, 2021

Published on: 18 September, 2020

Page: [425 - 432] Pages: 8

DOI: 10.2174/1573405616999200918150259

Price: $65

Abstract

Background: The incidence rate of renal disease is high, which can cause end-stage renal disease. Ultrasound is a commonly used imaging method, including conventional ultrasound, color ultrasound, elastography, etc. Machine learning is a potential method which has been widely used in clinical practices.

Objective: To compare the diagnostic performance of different ultrasonic image measurement parameters for kidney diseases, and to compare different machine learning methods with the human- reading method.

Methods: Ninety-four patients with pathologically diagnosed renal diseases and 109 normal controls were included in this study. The patients were examined by conventional ultrasound, color ultrasound and shear wave elasticity, respectively. Ultrasonic data were analyzed by Support vector machine (SVM), random forest (RF), K-nearest neighbor (KNN) and artificial neural network (ANN), respectively, and compared with the human-reading method.

Results: Only ultrasound elastography data have a diagnostic value for renal diseases. The accuracy of SVM, RF, KNN and ANN methods is 80.98%, 80.32%, 78.03% and 79.67%, respectively, while the accuracy of human-reading is 78.33%. In the data of machine learning ultrasound elastography, the elastic hardness parameters of the renal cortex are most important.

Conclusion: Ultrasound elastography is of the highest diagnostic value in machine learning for nephropathy, the diagnostic efficiency of the machine learning method is slightly higher than that of the human-reading method, and the diagnostic ability of the SVM method is higher than other methods.

Keywords: Renal disease, ultrasound image, diagnosis, machine learning, elastography, support vector machine.

Graphical Abstract

[1]
Bowe Benjamin, Xie Yan, Li Tingting, et al. Particulate Matter Air Pollution and the Risk of Incident CKD and Progression to ESRD J AM SOC NEPHROL 2018; 29(1): 218-30.
[2]
Li D, Zhang L, Zuo L, Jin CG, Li WG, Chen JB. Association of CKD-MBD Markers with All-Cause Mortality in Prevalent Hemodialysis Patients: A Cohort Study in Beijing. PLoS One 2017; 12(1): e0168537.
[http://dx.doi.org/10.1371/journal.pone.0168537] [PMID: 28045985]
[3]
Okuno S. [Kidney and bone update: the 5-year history and future of CKD-MBD. Bone metabolic marker in hemodialysis patients update]. CliCa 2012; 22(7): 1009-17.
[4]
Wang S, Larin KV. Optical coherence elastography for tissue characterization: a review. J Biophotonics 2015; 8(4): 279-302.
[http://dx.doi.org/10.1002/jbio.201400108] [PMID: 25412100]
[5]
Dudea SM, Botar-Jid C. Ultrasound elastography in thyroid disease. Med Ultrason 2015; 17(1): 74-96.
[http://dx.doi.org/10.11152/mu.2013.2066.171.smd] [PMID: 25745661]
[6]
Deo RC. Machine learning in medicine. Circulation 2015; 132(20): 1920-30.
[http://dx.doi.org/10.1161/CIRCULATIONAHA.115.001593] [PMID: 26572668]
[7]
Baştanlar Y, Ozuysal M. Introduction to machine learning. Methods Mol Biol 2014; 1107(1107): 105-28.
[http://dx.doi.org/10.1007/978-1-62703-748-8_7] [PMID: 24272434]
[8]
Goertz RS, Amann K, Heide R, Bernatik T, Neurath MF, Strobel D. An abdominal and thyroid status with Acoustic Radiation Force Impulse Elastometry--a feasibility study: Acoustic Radiation Force Impulse Elastometry of human organs. Eur J Radiol 2011; 80(3): e226-30.
[http://dx.doi.org/10.1016/j.ejrad.2010.09.025] [PMID: 20971591]
[9]
Peride I, Rădulescu D, Niculae A, Ene V, Bratu OG, Checheriță IA. Value of ultrasound elastography in the diagnosis of native kidney fibrosis. Med Ultrason 2016; 18(3): 362-9.
[http://dx.doi.org/10.11152/mu.2013.2066.183.per] [PMID: 27622414]
[10]
Kashani KB, Mao SA, Safadi S, et al. Association between kidney intracapsular pressure and ultrasound elastography. Crit Care 2017; 21(1): 251.
[http://dx.doi.org/10.1186/s13054-017-1847-2] [PMID: 29047410]
[11]
Kourou K, Exarchos TP, Exarchos KP, Karamouzis MV, Fotiadis DI. Machine learning applications in cancer prognosis and prediction. Comput Struct Biotechnol J 2014; 13: 8-17.
[http://dx.doi.org/10.1016/j.csbj.2014.11.005] [PMID: 25750696]
[12]
Bi XA, Shu Q, Sun Q, Xu Q. Random support vector machine cluster analysis of resting-state fMRI in Alzheimer’s disease. PLoS One 2018; 13(3): e0194479.
[http://dx.doi.org/10.1371/journal.pone.0194479] [PMID: 29570705]
[13]
Mativo JM, Huang S. Prediction of students’ academic performance: Adapt a methodology of predictive modeling for a small sample size. Proc of 44th Annual Frontiers in Education Conference,madrid. 1-3.
[http://dx.doi.org/10.1109/FIE.2014.7044287]
[14]
Yuan X, Yang Z. SVM-based Texture Classification and Application to Early Melanoma Detection Proceedings of Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference. 2006; pp. 1: 4775-8.
[15]
Temko A, Thomas E, Boylan G, et al. An SVM-Based System and Its Performance for Detection of Seizures in Neonates Proceedings of Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference. 2009; pp. 2643-6.

Rights & Permissions Print Cite
Article Metrics
41
3
© 2024 Bentham Science Publishers | Privacy Policy