改进的PSO优化SVM的病理图像分类算法

doi:10.3969/j.issn.1000-1565.2020.05.013

摘要/Abstract

摘要： 为了提高医学病理图像分类的准确率,提出了一种带有粒子位置权重和粒子之间相关度函数的PSO(particle swarm optimization)参数寻优算法.首先,在经典PSO算法的基础上提出了一种基于适应性原则的位置更新策略.然后,在粒子进行参数寻优的过程中,设计了一个增加粒子之间相关性的函数.该算法可以在不考虑速度影响的情况下进行参数最优解的搜索.最后,用经过PSO优化的支持向量机(SVM)算法分类检测病理图像.实验结果表明,该算法的分类准确率达到了98.5%,较高于另外几种算法.分类检测结果符合临床诊断结果,满足医学研究要求.

关键词: 支持向量机, 参数优化, 病理图像, 图像分类

Abstract: In order to improve the accuracy of medical pathological image classification, a PSO parameter optimization algorithm with adaptive iterative optimization function is proposed.First, a position updating strategy based on the adaptive principle is proposed on the basis of the classical PSO algorithm.Then, an adaptive iterative optimization function is designed in the process of particle parameter optimization.The algorithm can search for optimal solution without considering the influence of speed.Finally, the PSO optimized support vector machine algorithm is used to classify and detect pathological images.The experimental results show that the classification accuracy of the algorithm is 98.5%, which is higher than that of the other two algorithms.The results of classified detection are in accordance with the results of clinical diagnosis and meet the requirements of medical research.

Key words: support vector machine, parameter optimization, pathological image, image classification

中图分类号:

TP391

董斌,王云涛,贾立男,王娅南. 改进的PSO优化SVM的病理图像分类算法[J]. 河北大学学报(自然科学版), 2020, 40(5): 543-551.

DONG Bin,WANG Yuntao,JIA Linan,WANG Yanan. Pathological image classification algorithm by improved PSO-optimized SVM[J]. Journal of Hebei University (Natural Science Edition), 2020, 40(5): 543-551.

参考文献

[1] VERONIKA C, MARLEEN B, JOSIEN P W, et al. Not-so-supervised: A survey of semi-supervised, multi-instance, and transfer learning in medical image analysis[J]. Medical Image Analysis, 2019, 54: 280-296. DOI: 10.1016/j.media.2019.03.009.
[2] TAGHANAKI S A, KAWAHARA J,MILES B. Pareto-optimal multi-objective dimensionality reduction deep auto-encoder for mammography classification[J]. Computer Methods and Programs in Biomedicine, 2017, 145: 85-93. DOI: 10.1016/j.cmpb.2017.04.012.
[3] SWEETLIN J D,NEHEMIAH H K,KANNAN A. A Feature selection using ant colony optimization with tandem-run recruitment to diagnose bronchitis from CT scan images[J]. Computer Methods And Programs in Biomedicine, 2017, 145: 115-125. DOI: 10.1016/j.cmpb.2017.04.009.
[4] BHASKAR N, SUCHETHA M. PSO optimized 1-D CNN-SVM architecture for real-time detection and classification applications[J]. Computers In Biology and Medicine, 2018, 108: 85-92. DOI: 10.1016/j.compbiomed.2019.03.017.
[5] GIOVANNI L F, THALES L A V, ARISTOFANES C S, et al. Convolutional neural network-based PSO for lung nodule false positive reduction on CT images[J]. Computer Methods and Programs in Biomedicine, 2018, 162: 109-118. DOI: 10.1016/j.cmpb.2018.05.006.
[6] ZHANG Y D, ZHAO G H, SUN J D. Smart pathological brain detection by synthetic minority oversampling technique, extreme learning machine, and Jaya algorithm[J]. Multimedia Tools and Applications, 2018, 77(17): 22629-22648. DOI: 10.1007/s11042-017-5023-0.
[7] LEANDOR V P, CALINAE B B C, RAVAGANI M A S S. Heat exchanger network synthesis without stream splits using parallelized and simplified simulated annealing and particle swarm optimization[J]. Chemical Engineering Science, 2017, 158: 96-107. DOI: 10.1016/j.ces.2016.09.030.
[8] SAIED A, NIMA J N. Resource discovery in the peer to peer networks using an inverted ant colony optimization algorithm[J]. Peer-To-Peer Networking and Applications, 2019, 12(1): 129-142. DOI: 10.1007/s12083-018-0644-2.
[9] KARTHICK P A, GHOSH D M, RAMAKRISHNAN S S. Surface electromyography based muscle fatigue detection using high-resolution time-frequency methods and machine learning algorithms[J]. Computer Methods and Programs in Biomedicine, 2018, 154: 45-46. DOI: 10.1016/j.cmpb.2017.10.024.
[10] WANG D S, TAN D P, LIU L. Particle swarm optimization algorithm: an overview[J]. Soft Computing, 2018, 22(2): 387-408. DOI: 10.1007/s00500-016-2474-6.
[11] MOHAMMAD R B, ZBIGNEW M. Particle swarm optimization for single objective continuous space problems: A review[J]. Evolutionary Computation, 2017, 25(1): 1-54. DOI: 10.1162/EVCO_r_00180.
[12] CLERC M, KENNEDY J. The particle swarm-explosion,stability and convergence in a multidimensional complex space[J]. IEEE Trans Evol Comput, 2002, 6(2): 58-73. DOI: 10.1109/4235.985692.
[13] EBERHART R C, SHI Y. Comparing inertia weights and constriction factors in particle swarm optimization[C] // Congress on Evolutionary Computation,IEEE,2000. DOI: 10.1109/CEC.2000.870279.
[14] SUGANTHAN P N. Particle swarm optimiser with neighbourhood operator[C] // Congress on Evolutionary Computation, IEEE, 1999.DOI:10.1109/CEC.1999.785514.
[15] RATNAWEERA A, HALGAUMGE S K, WATSON H C. Self-organizing hierarchical particle swarm optimizer with time-varying acceleration coefficients[J]. IEEE Transactions on Evolutionary Computation, 2004, 8(3):240-255.DIO:10.1109/TEVC.2004.826071.
[16] 胡旺, 李志蜀. 一种更简化而高效的粒子群优化算法[J]. 软件学报,2007, 18(4): 861-868. DOI: 10. 1360/jos1 80861.
[17] SH Y A Modified particle swarm optimizer[C] // Proc of IEEE Icec Conference,1998.DIO:10.1109/ICEC.1998.699146.
[18] TIAN D P, SHI Z Z. MPSO: Modified particle swarm optimization and its applications[J]. Swarm and Evolutionary Computation, 2018, 41: 49-68. DOI: 10.1016/j.swevo.2018.01.011.
[19] LIN W C, YIN Y Q, CHENG S K. Particle swarm optimization and opposite-based particle swarm optimization for two-agent multi-facility customer order scheduling with ready times[J]. Applied Soft Computing, 2017, 52: 877-884. DOI:10.1016/j.asoc.2016.09.038.
[20] HAN H G, LU W, HOU Y. An adaptive-PSO-based self-organizing RBF neural network[J]. IEEE Transactions On Neural Networks and Learning Systems, 2018, 29(1): 104-117. DOI:10.1109/TNNLS.2016.2616413.
[21] LIANG H B, ZOU D L, LI Z L. Dynamic evaluation of drilling leakage risk based on fuzzy theory and PSO-SVR algorithm[J]. Future Generation Computer Systems-the International Journal of Escience,2019, 95: 454-466. DOI:10.1016/j.future.2018.12.068.
[22] YANG Z, CE L, LIAN I. Electricity price forecasting by a hybrid model, combining wavelet transform, ARMA and kernel-based extreme learning machine methods[J]. Applied Energy, 2017, 190: 291-305. DOI:10.1016/j.apenergy.2016.12.130.
[23] DENG W, YAO R, ZHAO H M. A novel intelligent diagnosis method using optimal LS-SVM with improved PSO algorithm[J]. Soft Computing, 2019, 23(7): 2445-2462. DOI:10.1007/s00500-017-2940-9.
[24] FENG Z K, NIU W J, CHENG C T. Multi-objective quantum-behaved particle swarm optimization for economic environmental hydrothermal energy system scheduling[J]. Energy, 2017, 131: 165-178. DOI:10.1016/j.energy.2017.05.013.
[25] SANKHADEEP C, SARBARTHA S, SIRSHENDU H, et al. Particle swarm optimization trained neural network for structural failure prediction of multistoried RC buildings[J]. Neural Computing & Applications, 2017, 28(8): 2005-2016. DOI: 10.1007/s00521-016-2190-2.
[26] ZHOU J H, REN J X, YAO C F. Multi-objective optimization of multi-axis ball-end milling Inconel 718 via grey relational analysis coupled with RBF neural network and PSO algorithm[J]. Measurement, 2017, 102: 271-285. DOI: 10.1016/j.measurement.2017.01.057.
[27] MAROUR N, ABDELGHANI B, ABDEREZAK J,et al. An effective and distributed particle swarm optimization algorithm for flexible job-shop scheduling problem[J]. Journal of Intelligent Manufacturing, 2018, 29(3): 603-615. DOI: 10.1007/s10845-015-1039-3.
[28] TIEN BUI D, BUI Q T, NGUYEN Q P, et al. A hybrid artificial intelligence approach using GIS-based neural-fuzzy inference system and particle swarm optimization for forest fire susceptibility modeling at a tropical area[J]. Agricultural and Forest Meteorology, 2017, 233:32-44.
[29] RAMDAN B A, AHMED F Z. A novel MPPT algorithm based on particle swarm optimization for photovoltaic systems[J]. IEEE Transactions on Sustainable Energy, 2017, 8(2): 468-476. DOI: 10.1109/TSTE.2016.2606421.
[30] AGHAJANI G R, SHAYANFAR H A, SHAYEGHI H. Demand side management in a smart micro-grid in the presence of renewable generation and demand response[J]. Energy, 2017, 126: 622-637. DOI: 10.1016/j.energy.2017.03.051.
[31] KABOLI S, FALLAHPOUR A, SELVARAJ J. Long-term electrical energy consumption formulating and forecasting via optimized gene expression programming[J]. Energy, 2017, 126: 144-164. DOI: 10.1016/j.energy.2017.03.009.
[32] QI C C, FOURIE A, CHEN Q S. Neural network and particle swarm optimization for predicting the unconfined compressive strength of cemented paste backfill[J]. Construction and Building Materials, 2018, 159: 473-478. DOI: 10.1016/j.conbuildmat.2017.11.006.
[33] MURALITHARAM K, SAKTHIVEL R,VISHNUVARTHAN R. Neural network based optimization approach for energy demand prediction in smart grid[J]. Neurocomputing, 2018, 273: 199-208. DOI: 10.1016/j.neucom.2017.08.017.
[34] SELVARANI S,RAJENDRAN P. Detection of renal calculi in ultrasound Image using meta-heuristic support vector machine[J]. Journal of Medical Systems, 2019, 43: 300. DOI: 10.1007/s10916-019-1407-1.