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

Abstract

Background

Accurate segmentation of lesion areas from Lugol's Iodine Staining images is crucial for screening pre-cancerous cervical lesions. However, in underdeveloped regions lacking skilled clinicians, this method may lead to misdiagnosis and missed diagnoses. In recent years, deep learning methods have been widely applied to assist in medical image segmentation.

Objective

This study aims to improve the accuracy of cervical cancer lesion segmentation by addressing the limitations of Convolutional Neural Networks (CNNs) and attention mechanisms in capturing global features and refining upsampling details.

Methods

This paper presents a Multi-Scale Bidirectional Lesion Enhancement Network, named MBLEformer, which employs the Swin Transformer encoder to extract image features at multiple stages and utilizes a multi-scale attention mechanism to capture semantic features from different perspectives. Additionally, a bidirectional lesion enhancement upsampling strategy is introduced to refine the edge details of lesion areas.

Results

Experimental results demonstrate that the proposed model exhibits superior segmentation performance on a proprietary cervical cancer colposcopic dataset, outperforming other medical image segmentation methods, with a mean Intersection over Union (mIoU) of 82.5%, accuracy, and specificity of 94.9% and 83.6%.

Conclusion

MBLEformer significantly improves the accuracy of lesion segmentation in iodine-stained cervical cancer images, with the potential to enhance the efficiency and accuracy of pre-cancerous lesion diagnosis and help address the issue of imbalanced medical resources.

© 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/10.2174/0115734056357180250516022218
2025-09-16
2025-10-29

  • From This Site

    /content/journals/cmir/10.2174/0115734056357180250516022218
    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-E15734056357180.html?itemId=/content/journals/cmir/10.2174/0115734056357180250516022218&mimeType=html&fmt=ahah

References

  1. BoisenM. GuidoR. Emerging Treatment Options for Cervical Dysplasia and Early Cervical Cancer.Clin. Obstet. Gynecol.202366350051510.1097/GRF.000000000000079037650664
     [Google Scholar]
  2. KakotkinV.V. SeminaE.V. ZadorkinaT.G. AgapovM.A. Prevention strategies and early diagnosis of cervical cancer: current state and prospects.Diagnostics (Basel)202313461010.3390/diagnostics1304061036832098
     [Google Scholar]
  3. LemmaT.M. BalaE.T. HordofaM.A. SolbanaL.K. Precancerous cervical lesions and associated factors among women on antiretroviral therapy at Dukem Health Center, Central Ethiopia: A cross‐sectional study.Health Sci. Rep.202473e197210.1002/hsr2.197238476585
     [Google Scholar]
  4. CairdH. SimkinJ. SmithL. Van NiekerkD. OgilvieG. The path to eliminating cervical cancer in Canada: past, present and future directions.Curr. Oncol.20222921117112210.3390/curroncol2902009535200594
     [Google Scholar]
  5. YadavJ. AgarwalS. JainA. Comparison of Visual Inspection Methods with Pap Smear as Screening Test for Premalignant Lesions of the Cervix.J Midlife Health2024151192410.4103/jmh.jmh_201_2338764929
     [Google Scholar]
  6. AzadR. AghdamE.K. RaulandA. Medical image segmentation review: The success of U-Net.IEEE Trans Pattern Anal Mach Intell.20244612100761009510.1109/TPAMI.2024.3435571
     [Google Scholar]
  7. AttallahO. Cervical cancer diagnosis based on multi-domain features using deep learning enhanced by handcrafted descriptors.Appl. Sci. (Basel)2023133191610.3390/app13031916
     [Google Scholar]
  8. CalikN. AlbayrakA. AkhanA. TurkmenI. CaparA. ToreyinB.U. BilginG. MuezzinogluB. Durak-AtaL. Classification of cervical precursor lesions via local histogram and cell morphometric features.IEEE J. Biomed. Health Inform.20232741747175736318553
     [Google Scholar]
  9. DosovitskiyA. BeyerL. KolesnikovA. An image is worth 16×16 words: Transformers for image recognition at scale.arXiv:2010.11929202010.48550/arXiv.2010.11929
     [Google Scholar]
  10. LiuZ. LinY. CaoY. Swin transformer: Hierarchical vision transformer using shifted windows.2021 IEEE/CVF International Conference on Computer Vision (ICCV)IEEE Computer Society202110.1109/ICCV48922.2021.00986
     [Google Scholar]
  11. LiJ. AdoboS.D. ShiH. JudicaelK.A.W. LinN. GaoL. Screening Methods for Cervical Cancer.ChemMedChem20241916e20240002110.1002/cmdc.20240002138735844
     [Google Scholar]
  12. CartwrightK. KosichM. GonyaM. KandaD. LeekityS. ShecheJ. EdwardsonN. PankratzV.S. MishraS.I. Cervical cancer knowledge and screening patterns in Zuni Pueblo women in the southwest United States.J. Cancer Educ.20233851531153810.1007/s13187‑023‑02295‑837046142
     [Google Scholar]
  13. DufeilE. KenfackB. TinchoE. FouogueJ. WisniakA. SormaniJ. VassilakosP. PetignatP. Addition of digital VIA/VILI to conventional naked-eye examination for triage of HPV-positive women: A study conducted in a low-resource setting.PLoS One2022175e026801510.1371/journal.pone.026801535552564
     [Google Scholar]
  14. HuS.Y. ZhaoX.L. ZhaoF.H. WeiL.H. ZhouQ. NiyaziM. LiuJ.H. WangC.Y. LiL.Y. ChengX.D. DuanX.Z. SauvagetC. QiaoY.L. SankaranarayananR. Implementation of visual inspection with acetic acid and Lugol’s iodine for cervical cancer screening in rural China.Int. J. Gynaecol. Obstet.2023160257157810.1002/ijgo.1436835871356
     [Google Scholar]
  15. HonH.J. ChongP.P. ChooH.L. KhineP.P. A Comprehensive Review of Cervical Cancer Screening Devices: The Pros and the Cons.Asian Pac. J. Cancer Prev.20232472207221510.31557/APJCP.2023.24.7.220737505749
     [Google Scholar]
  16. RonnebergerO. FischerP. BroxT. U-net: Convolutional networks for biomedical image segmentation.Medical Image Computing and Computer-Assisted InterventionOct. 5-9, 2015, Munich, Germany, 2015, pp. 234-241.10.1007/978‑3‑319‑24574‑4_28
     [Google Scholar]
  17. SunG. PanY. KongW. XuZ. MaJ. RacharakT. NguyenL.M. XinJ. DA-TransUNet: integrating spatial and channel dual attention with transformer U-net for medical image segmentation.Front. Bioeng. Biotechnol.202412139823710.3389/fbioe.2024.139823738827037
     [Google Scholar]
  18. ChenJ. LuY. YuQ. Transunet: Transformers make strong encoders for medical image segmentation.arXiv:2102.04306202110.48550/arXiv.2102.04306
     [Google Scholar]
  19. QianL. HuangH. XiaX. LiY. ZhouX. Automatic segmentation method using FCN with multi-scale dilated convolution for medical ultrasound image.Vis. Comput.202339115953596910.1007/s00371‑022‑02705‑w
     [Google Scholar]
  20. XingZ. TianY. YijunY. SegMamba: Long-range sequential modeling Mamba for 3D medical image segmentation.International Conference on Medical Image Computing and Computer-Assisted Intervention.SpringerCham202410.1007/978‑3‑031‑72111‑3_54
     [Google Scholar]
  21. JinQ. CuiH. SunC. MengZ. WeiL. SuR. Domain adaptation based self-correction model for COVID-19 infection segmentation in CT images.Expert Syst. Appl.202117611484810.1016/j.eswa.2021.11484833746369
     [Google Scholar]
  22. WangZ. ZhengJ.Q. ZhangY. Mamba-unet: Unet-like pure visual mamba for medical image segmentation.arXiv:2402.05079202410.48550/arXiv.2402.05079
     [Google Scholar]
  23. DingY. LiL. WangW. Clustering propagation for universal medical image segmentation.2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)16-22 June 2024, Seattle, WA, USA, 2024, pp. 3357-3369.10.1109/CVPR52733.2024.00323
     [Google Scholar]
  24. MengZ. ZhaoZ. SuF. Hierarchical spatial pyramid network for cervical precancerous segmentation by reconstructing deep segmentation networks.2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)19-25 June 2021, Nashville, TN, USA, 2021, pp. 3733-3740.10.1109/CVPRW53098.2021.00414
     [Google Scholar]
  25. LiuJ. LiangT. PengY. PengG. SunL. LiL. DongH. Segmentation of acetowhite region in uterine cervical image based on deep learning.Technol. Health Care202230246948210.3233/THC‑21289034180439
     [Google Scholar]
  26. ElakkiyaR. SubramaniyaswamyV. VijayakumarV. MahantiA. Cervical cancer diagnostics healthcare system using hybrid object detection adversarial networks.IEEE J. Biomed. Health Inform.20222641464147110.1109/JBHI.2021.309431134214045
     [Google Scholar]
  27. KimJ. ParkC.M. KimS.Y. ChoA. Convolutional neural network-based classification of cervical intraepithelial neoplasias using colposcopic image segmentation for acetowhite epithelium.Sci. Rep.20221211722810.1038/s41598‑022‑21692‑536241761
     [Google Scholar]
  28. WuT. LucasE. ZhaoF. BasuP. QiaoY. Artificial intelligence strengthens cervical cancer screening - present and future.Cancer Biol. Med.2024211086487939297572
     [Google Scholar]
  29. YanL. SongH. GuoY. RenP. ZhouW. LiS. YangJ. ShenX. HLDnet: Novel deep learning based Artificial Intelligence tool fuses acetic acid and Lugol’s iodine cervicograms for accurate pre-cancer screening.Biomed. Signal Process. Control20227110316310.1016/j.bspc.2021.103163
     [Google Scholar]
  30. ReichO. PickelH. 100 years of iodine testing of the cervix: A critical review and implications for the future.Eur. J. Obstet. Gynecol. Reprod. Biol.2021261344010.1016/j.ejogrb.2021.04.01133873086
     [Google Scholar]
  31. AsieduM.N. SimhalA. LamC.T. Image processing and machine learning techniques to automate diagnosis of Lugol’s iodine cervigrams for a low-cost point-of-care digital colposcope.Optics Biophotonics Low-Resource Settings IV.SPIE2018104851423
     [Google Scholar]
  32. HuangQ. ZhangW. ChenY. Review of cervical cell segmentation.Multimed Tools Appl.202410.1007/s11042‑024‑19799‑0
     [Google Scholar]
  33. VaswaniA. ShazeerN. ParmarN. Attention is all you need.arXiv:1706.037622017
     [Google Scholar]
  34. DaiY. GaoY. LiuF. Transmed: Transformers advance multi-modal medical image classification.Diagnostics (Basel)2021118138410.3390/diagnostics1108138434441318
     [Google Scholar]
  35. ZhuS. LinL. LiuQ. LiuJ. SongY. XuQ. Integrating a deep neural network and Transformer architecture for the automatic segmentation and survival prediction in cervical cancer.Quant. Imaging Med. Surg.20241485408541910.21037/qims‑24‑56039144008
     [Google Scholar]
  36. NirmalaG. NayuduP.P. KumarA.R. SagarR. Automatic cervical cancer classification using adaptive vision transformer encoder with CNN for medical application.Pattern Recognit.202516011120110.1016/j.patcog.2024.111201
     [Google Scholar]
  37. KimG. AntakiM. SchmidtE.J. Intraoperative MRI-guided cervical cancer brachytherapy with automatic tissue segmentation using dual convolution-transformer network and real-time needle tracking.Medical Imaging 2024: Image-Guided Procedures, Robotic Interventions, and ModelingSan Diego, California, United StatesSPIE202410.1117/12.3005475
     [Google Scholar]
  38. TangH. ChenY. WangT. ZhouY. ZhaoL. GaoQ. DuM. TanT. ZhangX. TongT. HTC-Net: A hybrid CNN-transformer framework for medical image segmentation.Biomed. Signal Process. Control20248810560510.1016/j.bspc.2023.105605
     [Google Scholar]
  39. WuC. LongC. LiS. YangJ. JiangF. ZhouR. MSRAformer: Multiscale spatial reverse attention network for polyp segmentation.Comput. Biol. Med.2022151Pt A10627410.1016/j.compbiomed.2022.10627436375412
     [Google Scholar]
  40. SornapudiS. StanleyR.J. StoeckerW.V. LongR. XueZ. ZunaR. FrazierS.R. AntaniS. DeepCIN: attention-based cervical histology image classification with sequential feature modeling for pathologist-level accuracy.J. Pathol. Inform.20201114010.4103/jpi.jpi_50_2033828898
     [Google Scholar]
  41. GuoY. WangY. YangH. ZhangJ. SunQ. Dual-attention EfficientNet based on multi-view feature fusion for cervical squamous intraepithelial lesions diagnosis.Biocybern. Biomed. Eng.202242252954210.1016/j.bbe.2022.02.009
     [Google Scholar]
  42. AnY. LeiY. HuangZ. LiuY. HuangM. LiuZ. LiW. LiangD. HuangW. HuZ. MacNet: a mobile attention classification network combining convolutional neural network and transformer for the differentiation of cervical cancer.Quant. Imaging Med. Surg.2025151557310.21037/qims‑24‑81039839018
     [Google Scholar]
  43. HeY. LiuL. WangJ. ZhaoN. HeH. Colposcopic image segmentation based on feature refinement and attention.IEEE Access202412408564087010.1109/ACCESS.2024.3378097
     [Google Scholar]
  44. XiongL. ChenC. LinY. SongZ. SuJ. A Three‐Step Automated Segmentation Method for Early Cervical Cancer MRI Images Based on Deep Learning.Int. J. Imaging Syst. Technol.2025351e2320710.1002/ima.23207
     [Google Scholar]
  45. Al AbboodiH.M. Al-funjanA.W. AldhahabA. High-resolution model for segmenting and predicting brain tumor based on deep unet with multi attention mechanism.Int. J. Intell. Eng. Syst.202417229410.22266/ijies2024.0430.25
     [Google Scholar]
  46. ZhouZ. Rahman SiddiqueeM.M. TajbakhshN. Unet++: A nested u-net architecture for medical image segmentation.Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support.ChamSpringer311201810.1007/978‑3‑030‑00889‑5_1
     [Google Scholar]
  47. JhaD. SmedsrudP.H. RieglerM.A. Resunet++: An advanced architecture for medical image segmentation.2019 IEEE International Symposium on Multimedia (ISM)IEEE Computer Society2019225225510.1109/ISM46123.2019.00049
     [Google Scholar]
  48. ZhangY. HanZ. LiuL. WangS. DualA-Net: A generalizable and adaptive network with dual-branch encoder for medical image segmentation.Comput. Methods Programs Biomed.202424310787710.1016/j.cmpb.2023.10787739492180
     [Google Scholar]
  49. ZhouT. ZhouY. HeK. GongC. YangJ. FuH. ShenD. Cross-level feature aggregation network for polyp segmentation.Pattern Recognit.202314010955510.1016/j.patcog.2023.109555
     [Google Scholar]
/content/journals/cmir/10.2174/0115734056357180250516022218
Loading
MBLEformer: Multi-Scale Bidirectional Lesion Enhancement Transformer for Cervical Cancer Image Segmentation
Curr. Med. Imaging 21, E15734056357180 (2025); https://doi.org/10.2174/0115734056357180250516022218
/content/journals/cmir/10.2174/0115734056357180250516022218
/content/journals/cmir/10.2174/0115734056357180250516022218
Loading

Data & Media loading...


  • Article Type:     Research Article
Keyword(s): Attention mechanism; Cervical cancer; Image segmentation; Lugol's Iodine Staining; Transformer; upsampling

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