Convolutional neural network with group theory and random selection particle swarm optimizer for enhancing cancer image classification

Kun Lan; Gloria Li; Yang Jie; Rui Tang; Liansheng Liu; Simon Fong; Kun Lan; Gloria Li; Yang Jie; Rui Tang; Liansheng Liu; Simon Fong

doi:10.3934/mbe.2021281

Mathematical Biosciences and Engineering

2021, Volume 18, Issue 5: 5573-5591. doi: 10.3934/mbe.2021281

Previous Article Next Article

Research article Special Issues

Convolutional neural network with group theory and random selection particle swarm optimizer for enhancing cancer image classification

1.
Department of Computer and Information Science, Faculty of Science and Technology, University of Macau, Macau 999078, China
2.
DACC Laboratory, Zhuhai Institutes of Advanced Technology of the Chinese Academy of Sciences, Zhuhai 519080, China
3.
Department of Management and Science and Information System, Faculty of Management and Economics, Kunming University of Science and Technology, Kunming 650093, China
4.
Department of Medical Imaging, First Affiliated Hospital of Guangzhou University of Chinese Medicine, Guangzhou 510405, China

Academic Editor: Kelvin K.L. Wong

Received: 19 April 2021 Accepted: 15 June 2021 Published: 21 June 2021

As an epitome of deep learning, convolutional neural network (CNN) has shown its advantages in solving many real-world problems. Successful CNN applications on medical prognosis and diagnosis have been achieved in recent years. Their common goal is to recognize the insights from the subtle details from medical images by building a suitable CNN model with maximum accuracy and minimum error. The CNN performance is extremely sensitive to the parameter tuning for any given network structure. To approach this concern, a novel self-tuning CNN model is proposed with a significant characteristic of having a metaheuristic-based optimizer. The most optimal set of parameters is often found via our proposed method, namely group theory and random selection-based particle swarm optimization (GTRS-PSO). The insights of symmetric essentials of model structure and parameter correlation are extracted, followed by the hierarchical partitioning of parameter space, and four operators on those partitions are designed for moving neighborhoods and formulating the swarm topology accordingly. The parameters are updated by a random selection strategy at each interval of partitions during the search process. Preliminary experiments over two radiology image datasets: breast cancer and lung cancer, are conducted for a comprehensive comparison of GTRS-PSO versus other optimization algorithms. The results show that CNN with GTRS-PSO optimizer can achieve the best performance for cancer image classifications, especially when there are symmetric components inside the data properties and model structures.
- convolutional neural network,
- metaheuristic,
- particle swarm optimization,
- group theory,
- random selection,
- symmetry,
- breast and lung cancer,
- image classification
Citation: Kun Lan, Gloria Li, Yang Jie, Rui Tang, Liansheng Liu, Simon Fong. Convolutional neural network with group theory and random selection particle swarm optimizer for enhancing cancer image classification[J]. Mathematical Biosciences and Engineering, 2021, 18(5): 5573-5591. doi: 10.3934/mbe.2021281

Related Papers:

Abstract

As an epitome of deep learning, convolutional neural network (CNN) has shown its advantages in solving many real-world problems. Successful CNN applications on medical prognosis and diagnosis have been achieved in recent years. Their common goal is to recognize the insights from the subtle details from medical images by building a suitable CNN model with maximum accuracy and minimum error. The CNN performance is extremely sensitive to the parameter tuning for any given network structure. To approach this concern, a novel self-tuning CNN model is proposed with a significant characteristic of having a metaheuristic-based optimizer. The most optimal set of parameters is often found via our proposed method, namely group theory and random selection-based particle swarm optimization (GTRS-PSO). The insights of symmetric essentials of model structure and parameter correlation are extracted, followed by the hierarchical partitioning of parameter space, and four operators on those partitions are designed for moving neighborhoods and formulating the swarm topology accordingly. The parameters are updated by a random selection strategy at each interval of partitions during the search process. Preliminary experiments over two radiology image datasets: breast cancer and lung cancer, are conducted for a comprehensive comparison of GTRS-PSO versus other optimization algorithms. The results show that CNN with GTRS-PSO optimizer can achieve the best performance for cancer image classifications, especially when there are symmetric components inside the data properties and model structures.

References

[1]	World Health Organization, World health statistics 2020: monitoring health for the SDGs, sustainable development goals, 2020.
[2]	J. D. Li, G. Chen, M. Wu, Y. Huang, W. Tang, Downregulation of CDC14B in 5218 breast cancer patients: A novel prognosticator for triple-negative breast cancer, Math. Biosci. Eng., 17 (2020), 8152-8181. doi: 10.3934/mbe.2020414
[3]	Y. Ouyang, Z. Zhou, W. Wu, J. Tian, F. Xu, S. Wu, et al., A review of ultrasound detection methods for breast microcalcification, Math. Biosci. Eng., 16 (2019), 1761-1785.
[4]	M. Zhang, Y. Zhou, Y. Zhang, High expression of TLR2 in the serum of patients with tuberculosis and lung cancer, and can promote the progression of lung cancer, Math. Biosci. Eng., 17 (2020), 1959-1972.
[5]	G. Sun, T. Zhao, Lung adenocarcinoma pathology stages related gene identification, Math. Biosci. Eng., 17 (2020), 737-746. doi: 10.3934/mbe.2020038
[6]	J. Gao, Q. Jiang, B. Zhou, D. Chen, Convolutional neural networks for computer-aided detection or diagnosis in medical image analysis: an overview, Math. Biosci. Eng., 16 (2019), 6536-6561. doi: 10.3934/mbe.2019326
[7]	B. Sahiner, H. P. Chan, N. Petrick, D. Wei, M. A. Helvie, D. D. Adler, et al., Classification of mass and normal breast tissue: a convolution neural network classifier with spatial domain and texture images, IEEE T. Med. Imaging, 15 (1996), 598-610.
[8]	Q. Li, W. Cai, X. Wang, Y. Zhou, D. D. Feng, M. Chen, Medical image classification with convolutional neural network, in 2014 13th international conference on control automation robotics & vision (ICARCV), IEEE, (2014), 844-848.
[9]	T. Kooi, G. Litjens, B. Van Ginneken, A. Gubern-Mérida, C. I. Sánchez, R. Mann, et al., Large scale deep learning for computer aided detection of mammographic lesions, Med. Image. Anal., 35 (2017), 303-312.
[10]	J. Snoek, O. Rippel, K. Swersky, R. Kiros, N. Satish, N. Sundaram, et al., Scalable bayesian optimization using deep neural networks, in International conference on machine learning, PMLR, (2015), 2171-2180.
[11]	M. Z. Alom, T. M. Taha, C. Yakopcic, S. Westberg, P. Sidike, M. S. Nasrin, et al., A state-of-the-art survey on deep learning theory and architectures, Electronics, 8 (2019), 292.
[12]	X. He, K. Zhao, X. Chu, AutoML: A Survey of the State-of-the-Art, Knowl-Based. Syst., 212 (2021), 106622.
[13]	L. Li, A. Talwalkar, Random search and reproducibility for neural architecture search, in Uncertainty in Artificial Intelligence, PMLR, (2020), 367-377.
[14]	P. Liu, M. D. El Basha, Y. Li, Y. Xiao, P. C. Sanelli, R. Fang, Deep evolutionary networks with expedited genetic algorithms for medical image denoising, Med. Image. Anal., 54 (2019), 306-315. doi: 10.1016/j.media.2019.03.004
[15]	P. Esfahanian, M. Akhavan, Gacnn: Training deep convolutional neural networks with genetic algorithm, preprint, arXiv: 1909.13354.
[16]	K. Pawełczyk, M. Kawulok, J. Nalepa, Genetically-trained deep neural networks, in Proceedings of the Genetic and Evolutionary Computation Conference Companion (GECCO), ACM, (2018), 63-64.
[17]	G. L. F. da Silva, T. L. A. Valente, A. C. Silva, A. C. de Paiva, M. Gattass, Convolutional neural network-based PSO for lung nodule false positive reduction on CT images, Comput. Meth. Prog. Bio., 162 (2018), 109-118.
[18]	P. R. Lorenzo, J. Nalepa, M. Kawulok, L. S. Ramos, J. R. Pastor, Particle swarm optimization for hyper-parameter selection in deep neural networks, in Proceedings of the genetic and evolutionary computation conference (GECCO), ACM, (2017), 481-488.
[19]	K. Lan, D. T. Wang, S. Fong, L. S. Liu, K. K. Wong, N. Dey, A survey of data mining and deep learning in bioinformatics, J. Med. Syst., 42 (2018), 1-20. doi: 10.1007/s10916-017-0844-y
[20]	T. Serizawa, H. Fujita, Optimization of convolutional neural network using the linearly decreasing weight particle swarm optimization, preprint, arXiv: 2001.05670.
[21]	J. Tóth, H. Toman, A. Hajdu, Efficient sampling-based energy function evaluation for ensemble optimization using simulated annealing, Pattern. Recogn, 107 (2020), 107510.
[22]	L. R. Rere, B. A. Wardijono, Y. I. Chandra, A comparison study of three single-solution based metaheuristic optimisation for stacked auto encoder, in Journal of Physics: Conference Series, IOP Publishing, (2019), 012066.
[23]	G. Rosa, J. Papa, A. Marana, W. Scheirer, D. Cox, Fine-tuning convolutional neural networks using harmony search, in Iberoamerican Congress on Pattern Recognition, (2015), 683-690.
[24]	R. Gens, P. M. Domingos, Deep symmetry networks, Adv. Neur. Inf., 27 (2014), 2537-2545.
[25]	V. Badrinarayanan, B. Mishra, R. Cipolla, Understanding symmetries in deep networks, preprint, arXiv: 1511.01029.
[26]	K. Lan, L. Liu, T. Li, Y. Chen, S. Fong, J. A. L. Marques, et al., Multi-view convolutional neural network with leader and long-tail particle swarm optimizer for enhancing heart disease and breast cancer detection, Neural. Comput. Appl., 32 (2020), 15469-15488.

mbe-18-05-281- supplementary.pdf

Reader Comments

Your name:*

Email:*
© 2021 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)