Potential-Guided Connected Network for Tiny Structure Segmentation in Medical Images

Chouyu Chen; Yaotong Song; Junyan Yi; Lijun Guo; Zhenyu Lei; Shangce Gao

doi:10.1109/JAS.2025.125705

Volume 13 Issue 8

Aug. 2026

IEEE/CAA Journal of Automatica Sinica

JCR Impact Factor: 18.3, Top 1 (SCI Q1)

CiteScore: 28.2, Top 1% (Q1)
Google Scholar h5-index: 95， TOP 5

Turn off MathJax

Article Contents

Article Navigation > IEEE/CAA Journal of Automatica Sinica > 2026 > 13(8): 1826-1841

C. Chen, Y. Song, J. Yi, L. Guo, Z. Lei, and S. Gao, “Potential-guided connected network for tiny structure segmentation in medical images,” IEEE/CAA J. Autom. Sinica, vol. 13, no. 8, pp. 1826–1841, Aug. 2026. doi: 10.1109/JAS.2025.125705

Citation:

C. Chen, Y. Song, J. Yi, L. Guo, Z. Lei, and S. Gao, “Potential-guided connected network for tiny structure segmentation in medical images,” IEEE/CAA J. Autom. Sinica, vol. 13, no. 8, pp. 1826–1841, Aug. 2026. doi: 10.1109/JAS.2025.125705

Citation:

PDF( 8800 KB)

Potential-Guided Connected Network for Tiny Structure Segmentation in Medical Images

doi: 10.1109/JAS.2025.125705

Funds: This work was partially supported by the Japan Society for the Promotion of Science (JSPS) KAKENHI (JP25K21298, JP25K03179) and Japan Science and Technology Agency (JST) Support for Pioneering Research Initiated by the Next Generation (SPRING) (JPMJSP2145)

More Information

Author Bio:
Chouyu Chen received the B.S. degree in automation from the University of Science and Technology Beijing in 2020, and the M.S. degree in computer science and technology from Beijing University of Civil Engineering and Architecture in 2023. He is currently pursuing the Ph.D. degree with the University of Toyama, Toyama, Japan. His research interests include artificial intelligence, neural networks, deep learning, pattern recognition, and image processing

Yaotong Song received the B.S. degree from Beijing University of Civil Engineering and Architecture. He is currently pursuing the M.E. degree from the University of Toyama, Toyama, Japan. His current research interests include computational intelligence and neural networks for real-world applications

Junyan Yi received the B.S. degree and the M.S. degree from Shandong University in 2001 and 2005 respectively, and received the Ph.D. degree from the University of Toyama, Toyama, Japan in 2009, all in computer science. Between 2007 and 2009, she worked as a Research Assistant at the University of Toyama, Toyama, Japan. She joined the College of Computer Science and Technology, Zhejiang University of Technology in 2009 as an Associate Professor. She is currently an Associate Professor with the Department of Computer Science and Technology, Beijing University of Civil Engineering and Architecture. Her research interests include intellectual information technology, neural networks, data mining, image processing, and optimizations problems

Lijun Guo received the Ph.D. degree in computer science from the Institute of Computing Technology, Chinese Academy of Sciences in 2011. He is currently a Full Professor with Ningbo University. His research interests include intelligent computing, computer vision, neuromorphic computing, and medical image analysis. He serves as a Committee Member for the Cognitive Computing Special Committee of the Chinese Association for Artificial Intelligence

Zhenyu Lei (Member, IEEE) received the Ph.D. degree in science and engineering from the University of Toyama, Toyama, Japan, in 2023. He is currently an Assistant Professor at the Faculty of Engineering, University of Toyama, Toyama, Japan. His current research interests include evolutionary computation, machine learning, and neural networks for real-world applications and optimization problems

Shangce Gao (Senior Member, IEEE) received the Ph.D. degree in innovative life science from the University of Toyama, Toyama, Japan in 2011. He is currently a Professor with the Faculty of Engineering, University of Toyama, Toyama, Japan. His current research interests include nature-inspired technologies, machine learning, and neural networks for real-world applications. He serves as an Associate Editor for many international journals such as IEEE Transactions on Neural Networks and Learning Systems, and IEEE/CAA Journal of Automatica Sinica
Corresponding author: Zhenyu Lei, e-mail: leizg@eng.u-toyama.ac.jp; Shangce Gao, e-mail: gaosc@eng.u-toyama.ac.jp
Received Date: 2025-02-23
Revised Date: 2025-05-28
Accepted Date: 2025-07-06

Available Online: 2026-08-20

Abstract

Abstract

Medical images provide essential information for diagnosing and monitoring various diseases and systemic disorders. With advancements in deep learning and neural networks, numerous methods have been proposed to achieve high-level medical image segmentation results. However, the variability of tiny structures and their high similarity to the background often lead to mis-segmentation in existing methods. To mitigate these challenges, we propose a potential-guided connected network (PCNet) that integrates an innovative dual soft-hard constraint strategy, combining two different progressive supervisions. This strategy modulates the ability of network to differentiate between well-defined and ambiguous structures through a hyper-parameter, thereby enhancing its capability to detect tiny structures. Furthermore, PCNet is composed of two key modules, including the intermediate generation (IG) module and the progressive inference (PI) module. The IG module produces a range of outputs with varying segmentation potentials using a novel serial architecture, which serves as the foundational input for progressive reasoning in the PI module. The PI module, leveraging the outputs of the IG module, is designed to progressively extract comprehensive contextual information, ultimately producing refined segmentation results. PCNet is evaluated on several publicly available datasets, including DRIVE, MoNuSeg, CoNIC, FIVES, and GlaS, achieving accuracy of 96.92%, 90.29%, 93.93%, 98.82%, and 92.00%, respectively. Extensive experiments demonstrate that our model outperforms the current state-of-the-art methods for tiny structure segmentation in medical images.
- Connected network,
- medical image,
- potential-guided,
- progressive inference (PI),
- segmentation

FullText(HTML)

References(43)

References

[1]	M. D. Abràmoff, M. K. Garvin, and M. Sonka, “Retinal imaging and image analysis,” IEEE Rev. Biomed. Eng., vol. 3, pp. 169–208, Dec. 2010. doi: 10.1109/RBME.2010.2084567
[2]	E. Meijering, “Cell segmentation: 50 years down the road [life sciences],” IEEE Signal Process. Mag., vol. 29, no. 5, pp. 140–145, Sep. 2012. doi: 10.1109/MSP.2012.2204190
[3]	M. Niemeijer, X. Xu, A. V. Dumitrescu, P. Gupta, B. van Ginneken, J. C. Folk, and M. D. Abramoff, “Automated measurement of the arteriolar-to-venular width ratio in digital color fundus photographs,” IEEE Trans. Med. Imag., vol. 30, no. 11, pp. 1941–1950, Nov. 2011. doi: 10.1109/TMI.2011.2159619
[4]	N. F. Greenwald, G. Miller, E. Moen, A. Kong, A. Kagel, T. Dougherty, et al., “Whole-cell segmentation of tissue images with human-level performance using large-scale data annotation and deep learning,” Nat. Biotechnol., vol. 40, no. 4, pp. 555–565, Apr. 2022. doi: 10.1038/s41587-021-01094-0
[5]	S. K. Singh, I. D. Clarke, M. Terasaki, V. E. Bonn, C. Hawkins, J. Squire, and P. B. Dirks, “Identification of a cancer stem cell in human brain tumors,” Cancer Res., vol. 63, no. 18, pp. 5821–5828, Sep. 2003.
[6]	L. Fang and H. Qiao, “Diabetic retinopathy classification using a novel DAG network based on multi-feature of fundus images,” Biomed. Signal Process. Control, vol. 77, Art. no. 103810, Aug. 2022. doi: 10.1016/j.bspc.2022.103810
[7]	Y. Tian and S. Fu, “A descriptive framework for the field of deep learning applications in medical images,” Knowl.-Based Syst., vol. 210, Art. no. 106445, Dec. 2020. doi: 10.1016/j.knosys.2020.106445
[8]	O. Ronneberger, P. Fischer, and T. Brox, “U-Net: Convolutional networks for biomedical image segmentation,” in Proc. 18th Int. Conf. Medical Image Computing and Computer-Assisted Intervention, Munich, Germany, 2015, pp. 234−241.
[9]	Z. Liu, Y. Lin, Y. Cao, H. Hu, Y. Wei, Z. Zhang, S. Lin, and B. Guo, “Swin Transformer: Hierarchical vision transformer using shifted windows,” in Proc. IEEE/CVF Int. Conf. Computer Vision, Montreal, Canada, 2021, pp. 9992−10002.
[10]	X. Xie, W. Zhang, X. Pan, L. Xie, F. Shao, W. Zhao, and J. An, “CANet: Context aware network with dual-stream pyramid for medical image segmentation,” Biomed. Signal Process. Control, vol. 81, Art. no. 104437, Mar. 2023. doi: 10.1016/j.bspc.2022.104437
[11]	F. Yu, V. Koltun, and T. Funkhouser, “Dilated residual networks,” in Proc. IEEE Conf. Computer Vision and Pattern Recognition, Honolulu, USA, 2017, pp. 636−644.
[12]	J. Dai, H. Qi, Y. Xiong, Y. Li, G. Zhang, H. Hu, and Y. Wei, “Deformable convolutional networks,” in Proc. IEEE Int. Conf. Computer Vision, Venice, Italy, 2017, pp. 764−773.
[13]	J. Yi, C. Chen, Q. Wei, D. Ding, and G. Yang, “MMF-Net: A novel multimodal multiscale fusion network for artery/vein segmentation in retinal fundus,” in Proc. IEEE Int. Conf. Systems, Man, and Cybernetics, Prague, Czech Republic, 2022, pp. 1192−1197.
[14]	P. Tang, P. Yang, D. Nie, X. Wu, J. Zhou, and Y. Wang, “Unified medical image segmentation by learning from uncertainty in an end-to-end manner,” Knowl.-Based Syst., vol. 241, Art. no. 108215, Apr. 2022. doi: 10.1016/j.knosys.2022.108215
[15]	X. Huang, H. Gong, and J. Zhang, “HST-MRF: Heterogeneous Swin transformer with multi-receptive field for medical image segmentation,” IEEE J. Biomed. Health Inform., vol. 28, no. 7, pp. 4048–4061, Jul. 2024. doi: 10.1109/JBHI.2024.3397047
[16]	R. A. Karlsson and S. H. Hardarson, “Artery vein classification in fundus images using serially connected U-Nets,” Comput. Methods Programs Biomed., vol. 216, Art. no. 106650, Apr. 2022. doi: 10.1016/j.cmpb.2022.106650
[17]	Y. Qi, Y. He, X. Qi, Y. Zhang, and G. Yang, “Dynamic snake convolution based on topological geometric constraints for tubular structure segmentation,” in Proc. IEEE/CVF Int. Conf. Computer Vision, Paris, France, 2023, pp. 6047−6056.
[18]	Y. Wang, L. Gu, T. Jiang, and F. Gao, “MDE-UNet: A multitask deformable UNet combined enhancement network for farmland boundary segmentation,” IEEE Geosci. Remote Sens. Lett., vol. 20, Art. no. 3001305, Mar. 2023. doi: 10.1109/lgrs.2023.3252048
[19]	Y. Chen, X. Dai, M. Liu, D. Chen, L. Yuan, and Z. Liu, “Dynamic convolution: Attention over convolution kernels,” in Proc. IEEE/CVF Conf. Computer Vision and Pattern Recognition, Seattle, USA, 2020, pp. 11027−11036.
[20]	Z. Zhou, M. M. R. Siddiquee, N. Tajbakhsh, and J. Liang, “UNet++: Redesigning skip connections to exploit multiscale features in image segmentation,” IEEE Trans. Med. Imag., vol. 39, no. 6, pp. 1856–1867, Jun. 2020. doi: 10.1109/TMI.2019.2959609
[21]	L. Lan, P. Cai, L. Jiang, X. Liu, Y. Li, and Y. Zhang, “BRAU-Net++: U-Shaped hybrid CNN-Transformer network for medical image segmentation,” IEEE Trans. Radiat. Plasma Med. Sci., 2026, DOI: 10.1109/TRPMS.2026.3666783.
[22]	H. Huang, L. Lin, R. Tong, H. Hu, Q. Zhang, Y. Iwamoto, X. Han, Y.-W. Chen, and J. Wu, “UNet 3+: A full-scale connected UNet for medical image segmentation,” in Proc. IEEE Int. Conf. Acoustics, Speech and Signal Processing, Barcelona, Spain, 2020, pp. 1055−1059.
[23]	H. Fu, J. Cheng, Y. Xu, D. W. K. Wong, J. Liu, and X. Cao, “Joint optic disc and cup segmentation based on multi-label deep network and polar transformation,” IEEE Trans. Med. Imag., vol. 37, no. 7, pp. 1597–1605, Jul. 2018. doi: 10.1109/TMI.2018.2791488
[24]	J. Yi, C. Chen, and G. Yang, “Retinal artery/vein classification by multi-channel multi-scale fusion network,” Appl. Intell., vol. 53, no. 22, pp. 26400–26417, Nov. 2023. doi: 10.1007/s10489-023-04939-0
[25]	X. Shu, Y. Yang, and B. Wu, “Adaptive segmentation model for liver CT images based on neural network and level set method,” Neurocomputing, vol. 453, pp. 438–452, Sep. 2021. doi: 10.1016/j.neucom.2021.01.081
[26]	H. Du, J. Wang, M. Liu, Y. Wang, and E. Meijering, “SwinPA-Net: Swin transformer-based multiscale feature pyramid aggregation network for medical image segmentation,” IEEE Trans. Neural Netw. Learn. Syst., vol. 35, no. 4, pp. 5355–5366, Apr. 2024. doi: 10.1109/TNNLS.2022.3204090
[27]	M. M. Rahman, M. Munir, and R. Marculescu, “EMCAD: Efficient multi-scale convolutional attention decoding for medical image segmentation,” in Proc. IEEE/CVF Conf. Computer Vision and Pattern Recognition, Seattle, USA, 2024, pp. 11769−11779.
[28]	J. M. J. Valanarasu, V. A. Sindagi, I. Hacihaliloglu, and V. M. Patel, “KiU-Net: Overcomplete convolutional architectures for biomedical image and volumetric segmentation,” IEEE Trans. Med. Imag., vol. 41, no. 4, pp. 965–976, Apr. 2022. doi: 10.1109/TMI.2021.3130469
[29]	B. Zhao, X. Chen, Z. Li, Z. Yu, S. Yao, L. Yan, Y. Wang, Z. Liu, C. Liang, and C. Han, “Triple U-Net: Hematoxylin-aware nuclei segmentation with progressive dense feature aggregation,” Med. Image Anal., vol. 65, Art. no. 101786, Oct. 2020. doi: 10.1016/j.media.2020.101786
[30]	Z. Han, M. Jian, and G.-G. Wang, “ConvUNeXt: An efficient convolution neural network for medical image segmentation,” Knowl.-Based Syst., vol. 253, Art. no. 109512, Oct. 2022. doi: 10.1016/j.knosys.2022.109512
[31]	Y. Shu, J. Zhang, B. Xiao, and W. Li, “Medical image segmentation based on active fusion-transduction of multi-stream features,” Knowl.-Based Syst., vol. 220, Art. no. 106950, May 2021. doi: 10.1016/j.knosys.2021.106950
[32]	K. A. J. Eppenhof, M. W. Lafarge, M. Veta, and J. P. W. Pluim, “Progressively trained convolutional neural networks for deformable image registration,” IEEE Trans. Med. Imag., vol. 39, no. 5, pp. 1594–1604, May 2020. doi: 10.1109/TMI.2019.2953788
[33]	W. Zhou, W. Bai, J. Ji, Y. Yi, N. Zhang, and W. Cui, “Dual-path multi-scale context dense aggregation network for retinal vessel segmentation,” Comput. Biol. Med., vol. 164, Art. no. 107269, Sep. 2023. doi: 10.1016/j.compbiomed.2023.107269
[34]	Z. Li, Y. Zheng, D. Shan, S. Yang, Q. Li, B. Wang, Y. Zhang, Q. Hong, and D. Shen, “ScribFormer: Transformer makes CNN work better for scribble-based medical image segmentation,” IEEE Trans. Med. Imag., vol. 43, no. 6, pp. 2254–2265, Jun. 2024. doi: 10.1109/TMI.2024.3363190
[35]	C. E. Shannon, “A mathematical theory of communication,” Bell Syst. Tech. J., vol. 27, no. 3, pp. 379–423, Jul. 1948. doi: 10.1002/j.1538-7305.1948.tb01338.x
[36]	A. L. Maas, A. Y. Hannun, and A. Y. Ng, “Rectifier nonlinearities improve neural network acoustic models,” in Proc. 30th Int. Conf. Machine Learning, Atlanta, USA, 2013, pp. 3−6.
[37]	Q. Hu, M. D. Abràmoff, and M. K. Garvin, “Automated separation of binary overlapping trees in low-contrast color retinal images,” in Proc. 16th Int. Conf. Medical Image Computing and Computer-Assisted Intervention, Nagoya, Japan, 2013, pp. 436−443.
[38]	N. Kumar, R. Verma, D. Anand, Y. Zhou, O. F. Onder, E. Tsougenis, et al., “A multi-organ nucleus segmentation challenge,” IEEE Trans. Med. Imag., vol. 39, no. 5, pp. 1380–1391, May 2020. doi: 10.1109/TMI.2019.2947628
[39]	S. Graham, Q. D. Vu, M. Jahanifar, M. Weigert, U. Schmidt, W. Zhang, et al., “CoNIC challenge: Pushing the frontiers of nuclear detection, segmentation, classification and counting,” Med. Image Anal., vol. 92, Art. no. 103047, Feb. 2024. doi: 10.1016/j.media.2023.103047
[40]	K. Jin, X. Huang, J. Zhou, Y. Li, Y. Yan, Y. Sun, Q. Zhang, Y. Wang, and J. Ye, “FIVES: A fundus image dataset for artificial intelligence based vessel segmentation,” Sci. Data, vol. 9, no. 1, Art. no. 475, Aug. 2022. doi: 10.1038/s41597-022-01564-3
[41]	K. Sirinukunwattana, J. P. W. Pluim, H. Chen, X. Qi, P.-A. Heng, Y. B. Guo, et al., “Gland segmentation in colon histology images: The glas challenge contest,” Med. Image Anal., vol. 35, pp. 489–502, Jan. 2017. doi: 10.1016/j.media.2016.08.008
[42]	X. Huang, Z. Deng, D. Li, X. Yuan, and Y. Fu, “MISSFormer: An effective transformer for 2D medical image segmentation,” IEEE Trans. Med. Imag., vol. 42, no. 5, pp. 1484–1494, May 2023. doi: 10.1109/TMI.2022.3230943
[43]	J. Hu, L. Shen, and G. Sun, “Squeeze-and-excitation networks,” in Proc. IEEE/CVF Conf. Computer Vision and Pattern Recognition, Salt Lake City, USA, 2018, pp. 7132−7141.