A novel stochastic resonance based closed-loop neural network method for image segmentation

Di Wang; Yang Wang; Chunxia Lu; Zonglian Wang; Jiandun Chen; Shanshan Xu; Di Wang; Yang Wang; Chunxia Lu; Zonglian Wang; Jiandun Chen; Shanshan Xu

doi:10.3934/era.2026062

Electronic Research Archive

2026, Volume 34, Issue 3: 1363-1385. doi: 10.3934/era.2026062

Previous Article Next Article

Research article Special Issues

A novel stochastic resonance based closed-loop neural network method for image segmentation

1.
Westlake Institute for Optoelectronics, Hangzhou 311400, China
2.
College of Information Engineering, Taizhou University, Taizhou 225300, China
3.
Dingjie Shuzhi Co., Ltd., Nanjing 210012, China
4.
College of Mechanical and Electrical Engineering, China Jiliang University, Hangzhou 310018, China

Received: 01 December 2025 Revised: 16 January 2026 Accepted: 28 January 2026 Published: 11 February 2026

Extracting multi-level information in colony images facilitates analysis and identification tasks of biomedical informatics. In order to achieve multi-level segmentation in colony images with multiple contrast levels, a closed-loop neural network model based on the stochastic resonance (SR) mechanism of neurons is proposed. First, this paper realizes the detection of transition pulses in sinusoidal, non-periodic bipolar binary signals, and one-dimensional strong and weak transition signals with multiple amplitude values. Then, through enhancement processing for the detection by the SR-based closed-loop neural network model, combined with the coati optimization algorithm, multi-target detection is achieved. Eventually, it can be applied to the segmentation of multi-level grayscale signals in two-dimensional images. Experimental results show that the proposed method can simultaneously detect strong and weak contrast edges, enrich image details, highlight image contours, and enhance the hierarchical sense of image edges, while exhibiting strong robustness against external noise. As a result, the proposed method provides a novel research framework for multi-contrast grayscale image segmentation under strong noise background.
- closed-loop neural network,
- stochastic resonance,
- coati optimization algorithm,
- image segmentation
Citation: Di Wang, Yang Wang, Chunxia Lu, Zonglian Wang, Jiandun Chen, Shanshan Xu. A novel stochastic resonance based closed-loop neural network method for image segmentation[J]. Electronic Research Archive, 2026, 34(3): 1363-1385. doi: 10.3934/era.2026062

Related Papers:

Abstract

Extracting multi-level information in colony images facilitates analysis and identification tasks of biomedical informatics. In order to achieve multi-level segmentation in colony images with multiple contrast levels, a closed-loop neural network model based on the stochastic resonance (SR) mechanism of neurons is proposed. First, this paper realizes the detection of transition pulses in sinusoidal, non-periodic bipolar binary signals, and one-dimensional strong and weak transition signals with multiple amplitude values. Then, through enhancement processing for the detection by the SR-based closed-loop neural network model, combined with the coati optimization algorithm, multi-target detection is achieved. Eventually, it can be applied to the segmentation of multi-level grayscale signals in two-dimensional images. Experimental results show that the proposed method can simultaneously detect strong and weak contrast edges, enrich image details, highlight image contours, and enhance the hierarchical sense of image edges, while exhibiting strong robustness against external noise. As a result, the proposed method provides a novel research framework for multi-contrast grayscale image segmentation under strong noise background.

References

[1]	N. Yudistira, M. S. Kavitha, J. Rajan, T. Kurita, Attention-effective multiple instance learning on weakly stem cell colony segmentation, Intell. Syst. Appl., 17 (2023), 200187. https://doi.org/10.1016/j.iswa.2023.200187 doi: 10.1016/j.iswa.2023.200187
[2]	C. Spahn, E. Gómez-de-Mariscal, R. F. Laine, P. M. Pereira, L. von Chamier, M. Conduit, et al., DeepBacs for multi-task bacterial image analysis using open-source deep learning approaches, Commun. Biol., 5 (2022), 688. https://doi.org/10.1038/s42003-022-03634-z doi: 10.1038/s42003-022-03634-z
[3]	P. Ma, C. Li, M. M. Rahaman, Y. Yao, J. Zhang, S. Zou, et al., A state-of-the-art survey of object detection techniques in microorganism image analysis: from classical methods to deep learning approaches, Artif. Intell. Rev., 56 (2023), 1627–1698. https://doi.org/10.1007/s10462-022-10209-1 doi: 10.1007/s10462-022-10209-1
[4]	A. Soni, A. Rai, CT scan based brain tumor recognition and extraction using Prewitt and morphological dilation, in 2021 International Conference on Computer Communication and Informatics (ICCCI), (2021), 1–6. https://doi.org/10.1109/ICCCI50826.2021.9402677
[5]	R. V. Patil, R. Aggarwal, G. M. Poddar, M. Bhowmik, M. K. Patil, Embedded integration strategy to image segmentation using canny edge and K-means algorithm, SSRN Electron. J., 12 (2024), 1–8. https://doi.org/10.2139/ssrn.5095501 doi: 10.2139/ssrn.5095501
[6]	Y. Su, W. Tan, Y. Dong, W. Xu, P. Huang, J. Zhang, et al., Enhancing concealed object detection in Active Millimeter Wave Images using wavelet transform, Signal Process., 216 (2024), 109303. https://doi.org/10.1016/j.sigpro.2023.109303 doi: 10.1016/j.sigpro.2023.109303
[7]	S. Ghosh, S. Das, Multi-scale morphology-aided deep medical image segmentation, Eng. Appl. Artif. Intell., 137 (2024), 109047. https://doi.org/10.1016/j.engappai.2024.109047 doi: 10.1016/j.engappai.2024.109047
[8]	H. Cui, X. Zheng, W. Zeng, R. Ma, Y. Zhang, Q. Yin, et al., Intuitionistic fuzzy local information C-means algorithm for image segmentation, Inf. Sci., 681 (2024), 121205. https://doi.org/10.1016/j.ins.2024.121205 doi: 10.1016/j.ins.2024.121205
[9]	H. Ziang, J. Zhang, L. Li, Framework for lung CT image segmentation based on UNet++, preprint, arXiv: 2501.02428.
[10]	S. Rezvani, M. Fateh, Y. Jalali, A. Fateh, FusionLungNet: Multi-scale fusion convolution with refinement network for lung CT image segmentation, Biomed. Signal Process. Control, 107 (2025), 107858. https://doi.org/10.1016/j.bspc.2025.107858 doi: 10.1016/j.bspc.2025.107858
[11]	Z. Zhu, M. Sun, G. Qi, Y. Li, X. Gao, Y. Liu, Sparse dynamic volume TransUNet with multi-level edge fusion for brain tumor segmentation, Comput. Biol. Med., 172 (2024), 108284. https://doi.org/10.1016/j.compbiomed.2024.108284 doi: 10.1016/j.compbiomed.2024.108284
[12]	T. Chen, Cell image segmentation method based on convolution neural network, in 2019 IEEE 5th International Conference on Computer and Communications (ICCC), (2019), 1765–1770. https://doi.org/10.1109/ICCC47050.2019.9064436
[13]	J. Du, Y. Zhang, X. Jin, X. Zhang, A cell image segmentation method based on edge feature residual fusion, Methods, 219 (2023), 111–118. https://doi.org/10.1016/j.ymeth.2023.09.009 doi: 10.1016/j.ymeth.2023.09.009
[14]	M. E. Cek, I. F. Uludag, Spectral resonance in Fitzhugh-Nagumo neuron system: relation with stochastic resonance and its role in EMG signal characterization, Cogn. Neurodyn., 18 (2024), 1779–1787. https://doi.org/10.1007/s11571-023-10043-3 doi: 10.1007/s11571-023-10043-3
[15]	M. Ge, K. Jia, X. Wang, Y. Liu, Y. Jiang, Researches on dynamics and noise effects of FHN neuron based on memristor-memcapacitor coupling, Nonlinear Dyn., 113 (2025), 26671–26693. https://doi.org/10.1007/s11071-025-11454-z doi: 10.1007/s11071-025-11454-z
[16]	K. Wu, J. Li, Effects of high-low-frequency electromagnetic radiation on vibrational resonance in FitzHugh-Nagumo neuronal systems, Eur. Phys. J. B, 96 (2023), 126. https://doi.org/10.1140/epjb/s10051-023-00594-z doi: 10.1140/epjb/s10051-023-00594-z
[17]	C. Laing, G. J. Lord, Stochastic Methods in Neuroscience, Oxford University Press, 2009. https://doi.org/10.1093/acprof: oso/9780199235070.001.0001
[18]	H. Zhang, J. Yu, Y. Ma, Z. Pan, J. Zhao, Image restoration based on stochastic resonance in a parallel array of Fitzhugh-Nagumo neuron, Complexity, 2020 (2020), 8843950. https://doi.org/10.1155/2020/8843950 doi: 10.1155/2020/8843950
[19]	M. Dehghani, Z. Montazeri, E. Trojovská, P. Trojovský, Coati optimization algorithm: A new bio-inspired metaheuristic algorithm for solving optimization problems, Knowl. -based Syst., 259 (2023), 110011. https://doi.org/10.1016/j.knosys.2022.110011 doi: 10.1016/j.knosys.2022.110011
[20]	P. Kandhway, A novel adaptive contextual information-based 2D-histogram for image thresholding, Expert Syst. Appl., 238 (2024), 122026. https://doi.org/10.1016/j.eswa.2023.122026 doi: 10.1016/j.eswa.2023.122026
[21]	K. Manikandan, B. Sudhakar, Optimized multi-threshold image segmentation using a hybrid bee-pollinator algorithm, Syst. Soft Comput., 7 (2025), 200404. https://doi.org/10.1016/j.sasc.2025.200404 doi: 10.1016/j.sasc.2025.200404
[22]	D. R. I. M. Setiadi, PSNR vs SSIM: imperceptibility quality assessment for image steganography, Multimed. Tools Appl., 80 (2021), 8423–8444. https://doi.org/10.1007/s11042-020-10035-z doi: 10.1007/s11042-020-10035-z
[23]	Y. Al Najjar, Comparative analysis of image quality assessment metrics: MSE, PSNR, SSIM and FSIM, Int. J. Sci. Res., 13 (2024), 110–114. https://doi.org/10.21275/SR24302013533

Reader Comments

Your name:*

Email:*
© 2026 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)