2020 Vol.3 Apr. No.2

• Title: Study on classification learning method of medical device ultrasonic imaging based on partial differential equation
• Name: Lishan Kuang
• Company: The Rizhao City People's Hospital, Rizhao
• Abstract:

  Traditional medical image classification methods are mostly based on the change of image gray features, extract edge and contour feature information, or perform conversion between medical image coordinate sets. However, the algorithms are complicated, real-time performance is poor, classification speed is slow, and accuracy is low. This paper proposes a classification study of medical images based on partial differential equations combined with deep learning algorithms, and uses the advantages of partial differential equations in medical image processing to extract the texture features of medical images. And according to the texture features of the medical image contrast modulation, filtering out the image noise interference. Based on the depth learning algorithm, the image distance stratification, the target object size, fit and other information, to achieve accurate classification of medical images. Simulation data experimental results show that the proposed classification method has high efficiency, low error rate, good real-time performance and robustness.

• Keyword: Partial differential equations; Medical imaging; Medical images; Texture features; Contrast modulation.
• DOI: 10.12250/jpciams2020020222
• Citation form: Lishan Kuang.Study on classification learning method of medical device ultrasonic imaging based on partial differential equation[J]. Computer Informatization and Mechanical System, 2020, vol. 3, pp. 88-97.

[1] Fang C, Zhao Z, Zhou P, et al. Feature learning via partial differential equation with applications to face recognition[J]. Pattern Recognition, 2017, 69(C):14-25.
[2] Li S, Yang X. Novel image inpainting algorithm based on adaptive fourth-order partial differential equation[J]. Iet Image Processing, 2017, 11(10):870-879.
[3] Nnolim U A. Improved partial differential equation-based enhancement for underwater images using local–global contrast operators and fuzzy homomorphic processes[J]. Iet Image Processing, 2017, 11(11):1059-1067.
[4] Aziz I, Siraj-ul-Islam, Asif M. Haar wavelet collocation method for three-dimensional elliptic partial differential equations[J]. Computers & Mathematics with Applications, 2017.
[5]Li M, Tian Z L, Hon Y C, et al. Improved finite integration method for partial differential equations[J]. Engineering Analysis with Boundary Elements, 2016, 64:230-236.
[6] Yang J, Hu H, Yao K, et al. Taylor meshless method for solving non-linear partial differential equations[J]. Journal of Computational Physics, 2017, 348.
[7] Yi-Fei P U, Siarry P, Chatterjee A, et al. A Fractional-Order Variational Framework for Retinex: Fractional-Order Partial Differential Equation Based Formulation for Multi-scale Nonlocal Contrast Enhancement with Texture Preserving[J]. IEEE Transactions on Image Processing, 2017, PP(99):1-5.
[8] Guo R, Xia Y, Xu Y. Semi-implicit spectral deferred correction methods for highly nonlinear partial differential equations[J]. Journal of Computational Physics, 2017, 338:269-284.
[9] King N D, Ruuth S J. Solving variational problems and partial differential equations that map between manifolds via the closest point method[J]. Journal of Computational Physics, 2017, 336:330-346.
[10] Raissi M, Karniadakis G E. Hidden physics models: Machine learning of nonlinear partial differential equations[J]. Journal of Computational Physics, 2017, 357:125–141.
[11] Luo W H, Huang T Z, Gu X M, et al. Barycentric rational collocation methods for a class of nonlinear parabolic partial differential equations [J]. Applied Mathematics Letters, 2017, 68:13-19.
[12] Ahmad I, Siraj-ul-Islam, Khaliq A Q M. Local RBF method for multi-dimensional partial differential equations[J]. Computers & Mathematics with Applications, 2017.
[13] Boiger R, Kaltenbacher B. An online parameter identification method for time dependent partial differential equations[J]. Inverse Problems, 2016, 32(4):4-9.
[14] Hattaf K, Yousfi N. A numerical method for delayed partial differential equations describing infectious diseases[J]. Computers & Mathematics with Applications, 2016, 72(11):16-21.
[15] Lee K, Elman H C. A Preconditioned Low-Rank Projection Method with a Rank-Reduction Scheme for Stochastic Partial Differential Equations[J]. Siam Journal on Scientific Computing, 2016, 39(5):12-16.
[16] Guzik S M, Gao X, Olschanowsky C. A high-performance finite-volume algorithm for solving partial differential equations governing compressible viscous flows on structured grids[J]. Computers & Mathematics with Applications, 2016, 72(9):2098-2118.
[17] Mao Z, Shen J. Efficient spectral–Galerkin methods for fractional partial differential equations with variable coefficients[J]. Journal of Computational Physics, 2016, 307:243-261.
[18] Liu Y, Yan Y, Khan M. Discontinuous Galerkin time stepping method for solving linear space fractional partial differential equations[J]. Applied Numerical Mathematics, 2017, 115:200-213.
[19] Liu T. A wavelet multiscale-homotopy method for the parameter identification problem of partial differential equations[J]. Computers & Mathematics with Applications, 2016, 71(7):1519-1523.
[20] Galán-García J L, Aguilera-Venegas G. Partial differential equations based simulations in multiple space dimensions[J]. Computers & Mathematics with Applications, 2017, 74(1):1-5.
[21] Yang D. Non-iterative parallel Schwarz algorithms based on overlapping domain decomposition for parabolic partial differential equations[J]. Mathematics of Computation, 2017, 86:1-6.