MFAINet: Multi-receptive Field Feature Fusion with Attention-Integrated for Polyp Segmentation

Guangzu Lv; Bin Wang; Cunlu Xu; Weiping Ding; Jun Liu

doi:10.1109/JAS.2025.125408

IEEE/CAA Journal of Automatica Sinica

JCR Impact Factor: 15.3, Top 1 (SCI Q1)

CiteScore: 23.5, Top 2% (Q1)
Google Scholar h5-index: 77， TOP 5

Turn off MathJax

Article Contents

Article Navigation > IEEE/CAA Journal of Automatica Sinica > 2025 > In Press, Accepted Manuscript

G. Lv, B. Wang, C. Xu, W. Ding, and J. Liu, “MFAINet: Multi-receptive field feature fusion with attention-integrated for polyp segmentation,” IEEE/CAA J. Autom. Sinica, 2025. doi: 10.1109/JAS.2025.125408

Citation:

G. Lv, B. Wang, C. Xu, W. Ding, and J. Liu, “MFAINet: Multi-receptive field feature fusion with attention-integrated for polyp segmentation,” IEEE/CAA J. Autom. Sinica, 2025. doi: 10.1109/JAS.2025.125408

Citation:

PDF( 29879 KB)

MFAINet: Multi-receptive Field Feature Fusion with Attention-Integrated for Polyp Segmentation

doi: 10.1109/JAS.2025.125408

Funds: This work was supported by the Science and Technology Project of Gansu (22YF7GA003, 24JRRA864, 21YF5GA102, 21YF5GA006, 21ZD8RA008, 22ZD6GA029), the Fundamental Research Funds for the Central Universities (lzujbky-2022-ct06), Supercomputing Center of Lanzhou University

More Information

Author Bio:
Guangzu Lv graduated with a Bachelor’s degree in Computer Science and Technology from the School of Information Science and Engineering at Shandong Normal University. He is currently pursuing a Master’s degree in Computer Science and Technology at the School of Information Science and Engineering at Lanzhou University. His research interests include medical image processing algorithms, diffusion image generation, and drug generation for protein-small molecule interactions

Bin Wang received the Ph.D. degree in computer science from Fudan University, Shanghai, China, in 2007. He is currently a Professor at the School of Information Engineering, Nanjing University of Finance and Economics, China, where he leads a media computing research team. He is also an Adjunct Research Fellow and Doctoral Advisor at the Institute for Integrated and Intelligent Systems, Griffith University, Australia. Previously, he was a Postdoctoral Research Fellow at the School of Computer Science and Engineering, Southeast University, and a Research Fellow at the School of Engineering, Griffith University. His research interests include computer vision, image retrieval, pattern recognition, and smart agriculture

Cunlu Xu received the Ph.D. degree in computer software and theory from Fudan University, Fudan, China, in 2006. He is currently an associate professor in the School of Information Science and Engineering, Lanzhou University. He was a postdoctoral fellow in the State Key Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, China (Sep. 2008-Sep.2009), and a visiting scholar in Department of Electronic and Computer Engineering, Duke University, USA (Dec. 2018, Dec. 2019). His main research interests include computer vision, machine learning applications, and information accessibility. He serves as an Area Editor of Journal of Ambient Intelligence and Humanized Computing

Weiping Ding (M’16-SM’19) received the Ph.D. degree in Computer Science, Nanjing University of Aeronautics and Astronautics, Nanjing, China, in 2013. From 2014 to 2015, he was a Postdoctoral Researcher at the Brain Research Center, National Chiao Tung University, Hsinchu, Taiwan, China. In 2016, he was a Visiting Scholar at National University of Singapore, Singapore. From 2017 to 2018, he was a Visiting Professor at University of Technology Sydney, Australia. His main research directions involve deep neural networks, granular data mining, and multimodal machine learning. He ranked within the top 2% Ranking of Scientists in the World by Stanford University (2020-2024). He has published over 360 articles, including over 170 IEEE Transactions papers. His twenty authored/co-authored papers have been selected as ESI Highly Cited Papers. He has co-authored five books. He has holds more than 50 approved invention patents, including three U.S. patents and one Australian patent. He serves as an Associate Editor/Area Editor/Editorial Board member of more than 10 international prestigious journals, such as IEEE Transactions on Neural Networks and Learning Systems, IEEE Transactions on Fuzzy Systems, IEEE/CAA Journal of Automatica Sinica, IEEE Transactions on Emerging Topics in Computational Intelligence, IEEE Transactions on Intelligent Transportation Systems, IEEE Transactions on Artificial Intelligence, Information Fusion, Information Sciences, Neurocomputing, Applied Soft Computing, Engineering Applications of Artificial Intelligence, Swarm and Evolutionary Computation, et al. He was/is the Leading Guest Editor of Special Issues in several prestigious journals, including IEEE Transactions on Evolutionary Computation, IEEE Transactions on Fuzzy Systems, Information Fusion, Information Sciences, et al. Now he is the Co-Editor-in-Chief of such three international journals as Journal of Artificial Intelligence and Systems, Journal of Artificial Intelligence Advances, and Sustainable Machine Intelligence Journal

Jun Liu is currently a Professor in Artificial Intelligence, Director of Artificial Intelligence Research Centre (AIRC) at School of Computing, Ulster University, Northern Ireland, UK. Before he joined Ulster, he was a Postdoc at The University of Manchester, and a Postdoc at Belgian Nuclear Research Centre. He received BSc. and MSc. degrees in Applied Mathematics, and PhD. degree in Information Engineering from Southwest Jiaotong University, China, in 1993, 1996, and 1999, respectively. He worked in the field of AI for many years. His current research is focused on two themes: 1) trust and explainable data-knowledge integrated AI decision model/system with applications in management, engineering, and industry field etc.; 2) logic and automated reasoning methods for intelligent systems including software verification and automated theorem proving. In particular: resolution-based automated reasoning methods, algorithm, and tools with applications (including software verification and automated theorem proving); lattice-valued logics with focus on handling incomparability, inconsistency, and imprecision. He has over 270 peer-reviewed publications. He is an IEEE Senior Member including IEEESMC and IEEECI. He serves as an Associated Editor of IEEE Transaction on Fuzzy Systems and Knowledge-Based Systems
Corresponding author: Cunlu Xu, e-mail: clxu@lzu.edu.cn
Received Date: 2024-12-11
Revised Date: 2025-01-04
Accepted Date: 2025-03-05

Available Online: 2025-04-28

Abstract

Abstract

Colorectal cancer has become a global public health concern. Removing polyps before they become malignant can effectively prevent the onset of colorectal cancer. Currently, multi-receptive field feature extraction and attention mechanisms have achieved significant success in polyp segmentation. However, how to effectively fuse these mechanisms and fully leverage their respective strengths remains an open problem. In this paper, we propose a polyp segmentation network, MFAINet. We design an Attention-Integrated Multi-receptive Field Feature Extraction module (AMFE), which uses layering and multiple weightings to fuse the multi-receptive field feature extraction and attention mechanisms, maximizing the extraction of both global and detailed information from the image. To ensure that the input to AMFE contains richer target feature information, we introduce a Multi-layer Progressive Fusion module (MPF). MPF progressively merges features at each layer, fully integrating contextual information. Finally, we employ the Selective Fusion module (SFM) to combine the high-level features produced by AMFE, resulting in an accurate polyp segmentation map. To evaluate the learning and generalization capabilities of MFAINet, we conduct experiments on five widely-used public polyp datasets using four evaluation metrics. Notably, our model achieves the best results in nearly all cases. The source code is available at: https://github.com/MFAINet.
- Attention mechanisms,
- multi-receptive field,
- polyp segmentation

FullText(HTML)

References(49)

References

[1]	X. Tang, X. Qiao, C. Chen, et al., “Regulation mechanism of long noncoding rnas in colon cancer development and progression,” Yonsei medical journal, vol. 60, no. 4, pp. 319–325, 2019. doi: 10.3349/ymj.2019.60.4.319
[2]	M. P. Singh, S. Rai, A. Pandey, et al., “Molecular subtypes of colorectal cancer: An emerging therapeutic opportunity for personalized medicine,” Genes & Diseases, vol. 8, no. 2, pp. 133–145, 2021.
[3]	R. Zhang, G. Li, Z. Li, and et al., “Adaptive context selection for polyp segmentation,” in Medical Image Computing and Computer Assisted Intervention–MICCAI 2020: 23rd Int. Conf., vol. 12266, (October 4–8, Proceedings, Part VI 23), pp. 253–262, Springer Int. Publishing, 2020.
[4]	M. Maida, D. S. Dahiya, Y. R. Shah, et al., “Screening and surveillance of colorectal cancer: A review of the literature,” Cancers, vol. 16, no. 15, p. 2746, 2024. doi: 10.3390/cancers16152746
[5]	R. Abedizadeh, F. Majidi, H. R. Khorasani, et al., “Colorectal cancer: a comprehensive review of carcinogenesis, diagnosis, and novel strategies for classified treatments,” Cancer and Metastasis Reviews, vol. 43, no. 2, pp. 729–753, 2024. doi: 10.1007/s10555-023-10158-3
[6]	S. Y. Kim, H. Kim, and H. J. Park, “Adverse events related to colonoscopy: Global trends and future challenges,” World Journal of Gastroenterology, vol. 25, pp. 190–204, 2019. doi: 10.3748/wjg.v25.i2.190
[7]	E. Sanderson and B. J. Matuszewski, “Fcn-transformer feature fusion for polyp segmentation,” in Annual Conf. on Medical Image Understanding and Analysis, (Cham), pp. 892–907, Springer Int. Publishing, 2022.
[8]	B. Sushma, C. Raghavendra, and J. Prashanth, “Cnn based u-net with modified skip connections for colon polyp segmentation,” 2021 5th Int. Conf. on Computing Methodologies and Communication (ICCMC), pp. 1762–1766, 2021.
[9]	D. Jha, P. H. Smedsrud, M. Riegler, and et al., “Kvasir-seg: A segmented polyp dataset,” pp. 451–462, 2020.
[10]	D. Vázquez, J. Bernal, F. J. Sánchez, and et al., “A benchmark for endoluminal scene segmentation of colonoscopy images,” Journal of healthcare engineering, vol. 2017, no. 1, p. 4037190, 2017.
[11]	J. Silva, A. Histace, O. Romain, X. Dray, and B. Granado, “Toward embedded detection of polyps in wce images for early diagnosis of colorectal cancer,” Int. Journal of Computer Assisted Radiology and Surgery, vol. 9, pp. 283–293, 2014. doi: 10.1007/s11548-013-0926-3
[12]	N. Tajbakhsh, S. R. Gurudu, and J. Liang, “Automated polyp detection in colonoscopy videos using shape and context information,” IEEE Trans. Medical Imaging, vol. 35, pp. 630–644, 2016. doi: 10.1109/TMI.2015.2487997
[13]	J. Bernal, F. J. Sánchez, G. Fernández-Esparrach, D. Gil, C. R. de Miguel, and F. Vilariño, “Wm-dova maps for accurate polyp highlighting in colonoscopy: Validation vs. saliency maps from physicians,” Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society, vol. 43, pp. 99–111, 2015. doi: 10.1016/j.compmedimag.2015.02.007
[14]	O. Ronneberger, P. Fischer, and T. Brox, “U-net: Convolutional networks for biomedical image segmentation,” in Medical Image Computing and Computer-Assisted Intervention–MICCAI 2015: 18th Int. Conf., (October 5–9, 2015, Proceedings, Part III), pp. 234–241, Springer Int. Publishing, 2015.
[15]	Z. Zhou, M. M. R. Siddiquee, N. Tajbakhsh, and J. Liang, “Unet++: A nested u-net architecture for medical image segmentation,” Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support : 4th Int. Workshop, DLMIA 2018, and 8th Int. Workshop, ML-CDS 2018, held in conjunction with MICCAI 2018, Granada, Spain, S.., vol. 11045, pp. 3–11, 2018.
[16]	Y. Fang, C. Chen, Y. Yuan, and R. K.-Y. Tong, “Selective feature aggregation network with area-boundary constraints for polyp segmentation,” in Medical Image Computing and Computer Assisted Intervention–MICCAI 2019: 22nd Int. Conf., (October 13–17, 2019, Proceedings, Part I 22), pp. 302–310, Springer Int. Publishing, 2019.
[17]	D.-P. Fan, G. Ji, T. Zhou, G. Chen, H. Fu, J. Shen, and L. Shao, “Pranet: Parallel reverse attention network for polyp segmentation,” in Medical Image Computing and Computer Assisted Intervention–MICCAI 2020: 23rd Int. Conf., (October 4–8, 2020, Proceedings, Part VI 23), pp. 263–273, Springer Int. Publishing, 2020.
[18]	J. Wei, Y. Hu, R. Zhang, et al., “Shallow attention network for polyp segmentation,” in Medical Image Computing and Computer Assisted Intervention–MICCAI 2021: 24th Int. Conf., (September 27–October 1Proceedings, Part I 24), pp. 699–708, Springer Int. Publishing, 2021.
[19]	B. Dong, W. Wang, D.-P. Fan, J. Li, H. Fu, and L. Shao, “Polyp-pvt: Polyp segmentation with pyramid vision transformers,” CAAI Artificial Intelligence Research, vol. 2, p. 9150015, 2023.
[20]	N. T. Duc, N. T. Oanh, N. T. Thuy, T. M. Triet, and V. S. Dinh, “Colonformer: An efficient transformer based method for colon polyp segmentation,” IEEE Access, vol. 10, pp. 80575–80586, 2022. doi: 10.1109/ACCESS.2022.3195241
[21]	M. Nguyen, T. Bui, Q. Nguyen, T. T. Nguyen, and T. V. Pham, “Lapformer: A light and accurate polyp segmentation transformer,” ArXiv, vol. abs/2210.04393, 2022.
[22]	X. Zhao, H. Jia, Y. Pang, L. Lv, F. Tian, L. Zhang, W. Sun, and H. Lu, “M2snet: Multi-scale in multi-scale subtraction network for medical image segmentation,” ArXiv, vol. abs/2303.10894, 2023.
[23]	J. Liu, Q. Chen, Y. Zhang, Z. Wang, D. Xin, and J. Wang, “Multi-level feature fusion network combining attention mechanisms for polyp segmentation,” Inf. Fusion, vol. 104, p. 102195, 2023.
[24]	W. Li, Y. Zhao, F. Li, and L. Wang, “Mia-net: Multi-information aggregation network combining transformers and convolutional feature learning for polyp segmentation,” Knowl. Based Syst., vol. 247, p. 108824, 2022. doi: 10.1016/j.knosys.2022.108824
[25]	N.-T. Bui, D.-H. Hoang, Q.-T. Nguyen, M.-T. Tran, and N. Le, “Meganet: Multi-scale edge-guided attention network for weak boundary polyp segmentation,” 2024 IEEE/CVF Winter Conf. on Applications of Computer Vision (WACV), pp. 7970–7979, 2023.
[26]	F. Liu, Z. Hua, J. Li, et al., “Dbmf: Dual branch multiscale feature fusion network for polyp segmentation,” Computers in Biology and Medicine, vol. 151, p. 106304, 2022. doi: 10.1016/j.compbiomed.2022.106304
[27]	W. Li, Z. Huang, F. Li, et al., “CIFG-Net: Cross-level information fusion and guidance network for polyp segmentation,” Computers in Biology and Medicine, vol. 169, p. 107931, 2024. doi: 10.1016/j.compbiomed.2024.107931
[28]	Y. Xia, H. Yun, and Y. Liu, “MFEFNet: Multi-scale feature enhancement and fusion network for polyp segmentation,” Computers in Biology and Medicine, vol. 157, p. 106735, 2023. doi: 10.1016/j.compbiomed.2023.106735
[29]	U. Muhammad, Z. Huang, and N. Gu, “MMFIL-Net: Multi-level and multi-source feature interactive lightweight network for polyp segmentation,” Displays, vol. 81, p. 102600, 2024. doi: 10.1016/j.displa.2023.102600
[30]	N. T. Bui, D. H. Hoang, Q. T. Nguyen, et al., “Meganet: Multi-scale edge-guided attention network for weak boundary polyp segmentation,” in Proc. the IEEE/CVF Winter Conf. on Applications of Computer Vision, pp. 7985–7994, 2024.
[31]	X. Liu and S. Song, “Attention combined pyramid vision transformer for polyp segmentation,” Biomedical Signal Processing and Control, vol. 89, p. 105792, 2024. doi: 10.1016/j.bspc.2023.105792
[32]	M. M. Rahman and R. Marculescu, “Medical image segmentation via cascaded attention decoding,” in Proc. the IEEE/CVF Winter Conf. on Applications of Computer Vision, pp. 6222–6231, 2023.
[33]	N. Tajbakhsh, S. R. Gurudu, and J. Liang, “Automated polyp detection in colonoscopy videos using shape and context information,” IEEE Trans. Medical Imaging, vol. 35, no. 2, pp. 630–644, 2015.
[34]	A. V. Mamonov, I. N. Figueiredo, P. N. Figueiredo, and Y.-H. R. Tsai, “Automated polyp detection in colon capsule endoscopy,” IEEE Trans. Medical Imaging, vol. 33, no. 7, pp. 1488–1502, 2014. doi: 10.1109/TMI.2014.2314959
[35]	S. Y. Park, D. Sargent, I. Spofford, et al., “A colon video analysis framework for polyp detection,” IEEE Trans. Biomedical Engineering, vol. 59, no. 5, pp. 1408–1418, 2012. doi: 10.1109/TBME.2012.2188397
[36]	C. Van Wijk, V. F. Van Ravesteijn, F. M. Vos, et al., “Detection and segmentation of colonic polyps on implicit isosurfaces by second principal curvature flow,” IEEE Trans. Medical Imaging, vol. 29, no. 3, pp. 688–698, 2010. doi: 10.1109/TMI.2009.2031323
[37]	D. Jha, P. H. Smedsrud, M. Riegler, D. Johansen, T. de Lange, P. Halvorsen, and H. D. Johansen, “Resunet++: An advanced architecture for medical image segmentation,” 2019 IEEE Int. Symposium on Multimedia (ISM), pp. 225–2255, 2019.
[38]	T. Zhou, Y. Zhou, K. He, et al., “Cross-level feature aggregation network for polyp segmentation,” Pattern Recognition, vol. 140, p. 109555, 2023. doi: 10.1016/j.patcog.2023.109555
[39]	B. Murugesan, K. Sarveswaran, S. M. Shankaranarayana, K. Ram, and M. Sivaprakasam, “Psi-net: Shape and boundary aware joint multi-task deep network for medical image segmentation,” 2019 41st Annual Int. Conf. of the IEEE Engineering in Medicine and Biology Society (EMBC), pp. 7223–7226, 2019.
[40]	Y. Zhang, H. Liu, and Q. Hu, “Transfuse: Fusing transformers and cnns for medical image segmentation,” in Int. Conf. on Medical Image Computing and Computer-Assisted Intervention, pp. 14–24, 2021.
[41]	W. Wang, E. Xie, X. Li, D.-P. Fan, K. Song, D. Liang, T. Lu, P. Luo, and L. Shao, “Pvt v2: Improved baselines with pyramid vision transformer,” Computational Visual Media, vol. 8, pp. 415–424, 2021.
[42]	R. Margolin, L. Zelnik-Manor, and A. Tal, “How to evaluate foreground maps?,” in Proc. the IEEE Conf. On Computer Vision And Pattern Recognition, pp. 248–255, 2014.
[43]	F. Perazzi, P. Krähenbühl, Y. Pritch, and A. Sorkine-Hornung, “Saliency filters: Contrast based filtering for salient region detection,” 2012 IEEE Conf. on Computer Vision and Pattern Recognition, pp. 733–740, 2012.
[44]	I. Loshchilov and F. Hutter, “Decoupled weight decay regularization,” arXiv preprint arXiv: 1711.05101, 2017.
[45]	J. Wei, S. Wang, and Q. Huang, “F³net: Fusion, feedback and focus for salient object detection,” in Proc. the AAAI Conf. on Artificial Intelligence, vol. 34, pp. 12321–12328, 2020.
[46]	C.-H. Huang, H.-Y. Wu, and Y.-L. S. Lin, “Hardnet-mseg: A simple encoder-decoder polyp segmentation neural network that achieves over 0.9 mean dice and 86 fps,” ArXiv, vol. abs/2101.07172, 2021.
[47]	K. Patel, A. M. Bur, and G. Wang, “Enhanced u-net: A feature enhancement network for polyp segmentation,” 2021 18th Conf. on Robots and Vision (CRV), pp. 181–188, 2021.
[48]	P. Naylor, M. Lae, F. Reyal, and T. Walter, “Segmentation of nuclei in histopathology images by deep regression of the distance map,” IEEE Trans. Medical Imaging, vol. 38, no. 2, pp. 448–459, 2018.
[49]	R. Azad, M. Asadi-Aghbolaghi, M. Fathy, et al., “Bi-directional convlstm u-net with densely connected convolutions,” in Proc. the IEEE/CVF Int. Conf. on Computer Vision Workshops, pp. 0–0, 2019.

Supplements(0)

Cited By

Proportional views

Proportional views

通讯作者: 陈斌, bchen63@163.com

1.
沈阳化工大学材料科学与工程学院沈阳 110142

Figures(12) / Tables(4)

Get Citation

PDF

XML

Article Metrics

Article views (12) PDF downloads(1)

MFAINet: Multi-receptive Field Feature Fusion with Attention-Integrated for Polyp Segmentation

doi: 10.1109/JAS.2025.125408

Abstract

References

Proportional views

Catalog

通讯作者: 陈斌, bchen63@163.com

Article Metrics

Export File

Citation

Format

Content