Skip to content
2000
Volume 21, Issue 1
  • ISSN: 1573-4056
  • E-ISSN: 1875-6603
file format pdf download PDF
file format text download EPUB
side by side viewer icon HTML

Abstract

Introduction

Accurate segmentation of small and irregular pulmonary nodules remains a significant challenge in lung cancer diagnosis, particularly in complex imaging backgrounds. Traditional U-Net models often struggle to capture long-range dependencies and integrate multi-scale features, limiting their effectiveness in addressing these challenges. To overcome these limitations, this study proposes an enhanced U-Net hybrid model that integrates multiple attention mechanisms to enhance feature representation and improve the precision of segmentation outcomes.

Methods

The assessment of the proposed model was conducted using the LUNA16 dataset, which contains annotated CT scans of pulmonary nodules. Multiple attention mechanisms, including Spatial Attention (SA), Dilated Efficient Channel Attention (Dilated ECA), Convolutional Block Attention Module (CBAM), and Squeeze-and-Excitation (SE) Block, were integrated into a U-Net backbone. These modules were strategically combined to enhance both local and global feature representations. The model’s architecture and training procedures were designed to address the challenges of segmenting small and irregular pulmonary nodules.

Results

The proposed model achieved a Dice similarity coefficient of 84.30%, significantly outperforming the baseline U-Net model. This result demonstrates improved accuracy in segmenting small and irregular pulmonary nodules.

Discussion

The integration of multiple attention mechanisms significantly enhances the model’s ability to capture both local and global features, addressing key limitations of traditional U-Net architectures. SA preserves spatial features for small nodules, while Dilated ECA captures long-range dependencies. CBAM and SE further refine feature representations. Together, these modules improve segmentation performance in complex imaging backgrounds. A potential limitation is that performance may still be constrained in cases with extreme anatomical variability or low-contrast lesions, suggesting directions for future research.

Conclusion

The Enhanced U-Net hybrid model outperforms the traditional U-Net, effectively addressing challenges in segmenting small and irregular pulmonary nodules within complex imaging backgrounds.

© 2025 The Author(s). Published by Bentham Science Publishers.
This is an open access article published under CC BY 4.0 https://creativecommons.org/licenses/by/4.0/legalcode
Loading

Article metrics loading...

/content/journals/cmir/10.2174/0115734056386382250902064757
2025-09-11
2025-11-08

  • From This Site

    /content/journals/cmir/10.2174/0115734056386382250902064757
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

/deliver/fulltext/cmir/21/1/CMIR-21-E15734056386382.html?itemId=/content/journals/cmir/10.2174/0115734056386382250902064757&mimeType=html&fmt=ahah

References

  1. ZhouQ. FanY. WangY. QiaoY. WangG. HuangY. WangX. WuN. ZhangG. ZhengX. BuH. [China national guideline of classification, diagnosis and treatment for lung nodules (2016 version)].Zhongguo Fei Ai Za Zhi2016191279379810.3779/j.issn.1009‑3419.2016.12.1227978863
     [Google Scholar]
  2. van KlaverenR.J. OudkerkM. ProkopM. ScholtenE.T. NackaertsK. VernhoutR. van IerselC.A. van den BerghK.A.M. van ’t WesteindeS. van der AalstC. ThunnissenE. XuD.M. WangY. ZhaoY. GietemaH.A. de HoopB.J. GroenH.J.M. de BockG.H. van OoijenP. WeeninkC. VerschakelenJ. LammersJ.W.J. TimensW. WillebrandD. VinkA. MaliW. de KoningH.J. Management of lung nodules detected by volume CT scanning.N. Engl. J. Med.2009361232221222910.1056/NEJMoa090608519955524
     [Google Scholar]
  3. ArestaG. JacobsC. AraújoT. CunhaA. RamosI. van GinnekenB. CampilhoA. iW-Net: An automatic and minimalistic interactive lung nodule segmentation deep network.Sci. Rep.2019911159110.1038/s41598‑019‑48004‑831406194
     [Google Scholar]
  4. LoS.C.B. ChanH.P. LinJ.S. LiH. FreedmanM.T. MunS.K. Artificial convolution neural network for medical image pattern recognition.Neural Netw.199587-81201121410.1016/0893‑6080(95)00061‑5
     [Google Scholar]
  5. LongJ. ShelhamerE. DarrellT. Fully convolutional networks for semantic segmentation.Proc IEEE Conf Comput Vis Pattern Recognit (CVPR)Boston, MA, USA, 07-12 June 2015.10.1109/CVPR.2015.7298965
     [Google Scholar]
  6. RonnebergerO. FischerP. BroxT. U-Net: Convolutional networks for biomedical image segmentation.Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015 NavabN HorneggerJ WellsW ChamSpringer9351201510.1007/978‑3‑319‑24574‑4_28
     [Google Scholar]
  7. ZhouZ. SiddiqueeM.M.R. TajbakhshN. LiangJ. UNet++: A nested U-Net architecture for medical image segmentation.Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision SupportGranada, Spain20181104531110.1007/978‑3‑030‑00889‑5_1
     [Google Scholar]
  8. OktayO. SchlemperJ. FolgocL.L. LeeM. HeinrichM. MisawaK. Attention u-net: Learning where to look for the pancreas.arXiv:1804.0399920181510.48550/arXiv.1804.03999
     [Google Scholar]
  9. LuoD. HeQ. MaM. YanK. LiuD. WangP. ECANodule: Accurate pulmonary nodule detection and segmentation with efficient channel attention.Proceedings of the International Joint Conference on Neural Networks (IJCNN)Gold Coast, Australia, 2023 Jun 18-23.10.1109/IJCNN54540.2023.10191210
     [Google Scholar]
  10. ÇiçekÖ. AbdulkadirA. LienkampS.S. BroxT. RonnebergerO. 3D U-Net: Learning dense volumetric segmentation from sparse annotation.Medical Image Computing and Computer-Assisted Intervention – MICCAI 2016 OurselinS JoskowiczL SabuncuM UnalG WellsW Lecture Notes in Computer Science9901ChamSpringer201610.1007/978‑3‑319‑46723‑8_49
     [Google Scholar]
  11. HuJ. ShenL. SunG. AlbanieS. WuE. Squeeze-and-excitation networks.Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)Salt Lake City, 2018 Jun 18-22, pp. 7132-7141.10.1109/CVPR.2018.00745
     [Google Scholar]
  12. WooS. ParkJ. LeeJ-Y. KweonI.S. CBAM: Convolutional block attention module.Proceedings of the European Conference on Computer Vision (ECCV)Munich, Germany, 2018 Sep 8-14, pp. 3-19.10.1007/978‑3‑030‑01234‑2_1
     [Google Scholar]
  13. WangQ. WuB. ZhuP. LiP. ZuoW. HuQ. ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks.Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)2020 Jun 14-19Seattle, USAIEEE11531910.1109/CVPR42600.2020.01155
     [Google Scholar]
  14. HuB. ZhouP. YuH. DaiY. WangM. TanS. SunY. LeaNet: Lightweight U-shaped architecture for high-performance skin cancer image segmentation.Comput. Biol. Med.202416910791910.1016/j.compbiomed.2024.10791938176212
     [Google Scholar]
  15. DuanX. SunY. WangJ. ECA-UNet for coronary artery segmentation and three-dimensional reconstruction.Signal Image Video Process.202317378378910.1007/s11760‑022‑02288‑y
     [Google Scholar]
  16. JiZ. ZhaoZ. ZengX. WangJ. ZhaoL. ZhangX. GanchevI. ResDSda_U-Net: A novel u-net-based residual network for segmentation of pulmonary nodules in lung CT images.IEEE Access202311877758778910.1109/ACCESS.2023.3305270
     [Google Scholar]
  17. SadremomtazA. ZadnorouziM. Improving the quality of pulmonary nodules segmentation using the new proposed U-Net neural network.Intell. Based Med.20241010016610.1016/j.ibmed.2024.100166
     [Google Scholar]
  18. NguyenT.C. NguyenT.P. CaoT. DaoT.T.P. HoT.N. NguyenT.V. TranM.T. MANet: Multi-branch attention auxiliary learning for lung nodule detection and segmentation.Comput. Methods Programs Biomed.202324110774810.1016/j.cmpb.2023.10774837598474
     [Google Scholar]
  19. LiX. JiangA. QiuY. LiM. ZhangX. YanS. TPFR-Net: U-shaped model for lung nodule segmentation based on transformer pooling and dual-attention feature reorganization.Med. Biol. Eng. Comput.20236181929194610.1007/s11517‑023‑02852‑937243853
     [Google Scholar]
  20. AnnavarapuC.S.R. ParisapoguS.A.B. KeethaN.V. DontaP.K. RajitaG. A Bi-FPN-based encoder–decoder model for lung nodule image segmentation.Diagnostics2023138140610.3390/diagnostics1308140637189507
     [Google Scholar]
  21. ZengQ. ZhouJ. TaoJ. ChenL. NiuX. ZhangY. Multiscale global context network for semantic segmentation of high-resolution remote sensing images.IEEE Trans. Geosci. Remote Sens.202462411310.1109/TGRS.2024.3393489
     [Google Scholar]
  22. MilletariF. NavabN. AhmadiS.A. V-Net: Fully convolutional neural networks for volumetric medical image segmentation.Fourth International Conference on 3D Vision (3DV)Stanford, CA, USA, 2016, pp. 565-571.10.1109/3DV.2016.79
     [Google Scholar]
  23. RezatofighiH. TsoiN. GwakJ.Y. SadeghianA. ReidI. SavareseS. Generalized Intersection over Union: A Metric and a Loss for Bounding Box Regression.Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)Long Beach, CA, USA, 2019 Jun 16-20, pp. 658-666.10.1109/CVPR.2019.00075
     [Google Scholar]
  24. KennedyJ. EberhartR. Particle swarm optimization.Proceedings of the IEEE International Conference on Neural Networks (ICNN’95)Perth, WA, Australia, 1995 Nov 27–Dec 1, pp. 8.10.1109/ICNN.1995.488968
     [Google Scholar]
  25. KingmaD.P. BaJ. Adam: A method for stochastic optimization.Proceedings of the 3rd International Conference on Learning Representations (ICLR)San Diego, USA, 2015 May 7-9 1998.
     [Google Scholar]
  26. LoshchilovI. HutterF. Decoupled weight decay regularization.Proceedings of the International Conference on Learning Representations (ICLR)New Orleans, LA, USA, 2019 May 6-9.
     [Google Scholar]
  27. LiuL. JiangH. HeP. On the variance of the adaptive learning rate and beyond.Proceedings of the 8th International Conference on Learning Representations (ICLR)Addis Ababa, Ethiopia, 2020 Apr 26-30.
     [Google Scholar]
  28. JoshuaE.S.N. BhattacharyyaD. ChakkravarthyM. Lung nodule semantic segmentation with bi-direction features using U-INET.J Med Pharm Allied Sci20231015145410.22270/jmpas.V1015.1454
     [Google Scholar]
  29. ZhouF. LuoF. Efio-AkollyK. HAUNet-3D: A novel hierarchical attention 3D unet for lung nodule segmentation.Proceedings of the 2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)Houston, TX, USA, 2021 Dec 9-12, pp. 1292-1299.10.1109/BIBM52615.2021.9669883
     [Google Scholar]
  30. LinH. ZhangY. ChenX. WangH. XiaL. Research on pulmonary nodule segmentation algorithm based on improved V-Net.2022 IEEE 6th Advanced Information Technology, Electronic and Automation Control Conference (IAEAC )Beijing, China, 03-05 October 2022, pp. 1-6.10.1109/IAEAC54830.2022.9929520
     [Google Scholar]
  31. WangZ. MenJ. ZhangF. Improved V-Net lung nodule segmentation method based on selective kernel.Signal Image Video Process.20231751763177410.1007/s11760‑022‑02387‑w
     [Google Scholar]
  32. TyagiS. TalbarS.N. CSE-GAN: A 3D conditional generative adversarial network with concurrent squeeze-and-excitation blocks for lung nodule segmentation.Comput. Biol. Med.202214710578110.1016/j.compbiomed.2022.10578135777084
     [Google Scholar]
/content/journals/cmir/10.2174/0115734056386382250902064757
Loading
Enhanced U-Net with Attention Mechanisms for Improved Feature Representation in Lung Nodule Segmentation
Curr. Med. Imaging 21, E15734056386382 (2025); https://doi.org/10.2174/0115734056386382250902064757
/content/journals/cmir/10.2174/0115734056386382250902064757
/content/journals/cmir/10.2174/0115734056386382250902064757
Loading

Data & Media loading...


  • Article Type:     Research Article
Keyword(s): Attention mechanisms; Computer-aided diagnosis; Deep learning; LUNA16 dataset; Medical image analysis; Pulmonary nodule segmentation; U-Net

Most Cited Most Cited RSS feed

This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error
Please enter a valid_number test