Skip to content
2000
  1. Home
  2. A-Z Publications
  3. Current Medical Imaging
  4. Volume 20, Issue 1
  5. Article
Volume 20, Issue 1
  • ISSN: 1573-4056
  • E-ISSN: 1875-6603
file format pdf download PDF
side by side viewer icon HTML

Abstract

Background

Medical image registration plays an important role in several applications. Existing approaches using unsupervised learning encounter issues due to the data imbalance problem, as their target is usually a continuous variable.

Objective

In this study, we introduce a novel approach known as Unsupervised Imbalanced Registration, to address the challenge of data imbalance and prevent overconfidence while increasing the accuracy and stability of 4D image registration.

Methods

Our approach involves performing unsupervised image mixtures to smooth the input space, followed by unsupervised image registration to learn the continual target. We evaluated our method on 4D-Lung using two widely used unsupervised methods, namely VoxelMorph and ViT-V-Net.

Results

Our findings demonstrate that our proposed method significantly enhances the mean accuracy of registration by 3%-10% on a small dataset while also reducing the accuracy variance by 10%.

Conclusion

Unsupervised Imbalanced Registration is a promising approach that is compatible with current unsupervised image registration methods applied to 4D images.

© 2024 The Author(s). Published by Bentham Science Publisher.
This is an open access article distributed under the terms of the Creative Commons Attribution 4.0 International Public License (CC-BY 4.0), a copy of which is available at: https://creativecommons.org/licenses/by/4.0/legalcode. This license permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
Loading

Article metrics loading...

/content/journals/cmir/10.2174/0115734056265001231122110350
2024-01-01
2025-06-25

  • From This Site

    /content/journals/cmir/10.2174/0115734056265001231122110350
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
The full text of this item is not currently available.

References

  1. McClellandJ.R. HawkesD.J. SchaeffterT. KingA.P. Respiratory motion models: A review.Med. Image Anal.2013171194210.1016/j.media.2012.09.00523123330
     [Google Scholar]
  2. SotirasA. DavatzikosC. ParagiosN. Deformable medical image registration: A survey.IEEE Trans. Med. Imaging20133271153119010.1109/TMI.2013.226560323739795
     [Google Scholar]
  3. ChenJ. HeY. FreyE.C. LiY. DuY. ViT-V-Net: Vision transformer for unsupervised volumetric medical image registration.ArXiv abs/2104.064682021
     [Google Scholar]
  4. BalakrishnanG. ZhaoA. SabuncuM.R. GuttagJ. DalcaA.V. VoxelMorph: A learning framework for deformable medical image registration.IEEE Trans. Med. Imaging20193881788180010.1109/TMI.2019.289753830716034
     [Google Scholar]
  5. ChawlaN.V. BowyerK.W. HallL.O. KegelmeyerW.P. SMOTE: Synthetic minority over-sampling technique.J. Artif. Intell. Res.200216132135710.1613/jair.953
     [Google Scholar]
  6. GarcíaS.H. Evolutionary undersampling for classification with imbalanced datasets: Proposals and taxonomy.Evolutionary Computation2009173275306
     [Google Scholar]
  7. CaoK. WeiC. GaidonA. ArechigaN. MaT. Learning imbalanced datasets with label-distribution-aware margin loss.Proceedings of the 33rd International Conference on Neural Information Processing SystemsCurran Associates Inc.2019
     [Google Scholar]
  8. DoanT.N.N. KimK. SongB. KwakJ.T. GradMix for nuclei segmentation and classification in imbalanced pathology image datasets.ArXiv abs/2210.12938202210.1007/978‑3‑031‑16434‑7_17
     [Google Scholar]
  9. LinY. YaoH. LiZ. ZhengG. LiX. Calibrating label distribution for class-imbalanced barely-supervised knee segmentation.International Conference on Medical Image Computing and Computer-Assisted Intervention202210.1007/978‑3‑031‑16452‑1_11
     [Google Scholar]
  10. YangY. ZhaK. ChenY. WangH. KatabiD. Delving into deep imbalanced regression.presented at the Proceedings of the 38th International Conference on Machine Learning, Proceedings of Machine Learning Research2021
     [Google Scholar]
  11. LiH. XueF-F ChaitanyaK. Imbalance-aware self-supervised learning for 3D radiomic representations.Medical Image Computing and Computer Assisted Intervention : MICCAIChamSpringer International Publishing2021364610.1007/978‑3‑030‑87196‑3_4
     [Google Scholar]
  12. UzunovaH. WilmsM. HandelsH. EhrhardtJ. Training CNNs for image registration from few samples with model-based data augmentation.International Conference on Medical Image Computing and Computer-Assisted Intervention201710.1007/978‑3‑319‑66182‑7_26
     [Google Scholar]
  13. ZhangH. CisséM. DauphinY. Lopez-PazD. mixup: Beyond empirical risk minimization.ArXiv abs/1710.094122018
     [Google Scholar]
  14. BalikS. WeissE. JanN. RomanN. SleemanW.C. FatygaM. ChristensenG.E. ZhangC. MurphyM.J. LuJ. KeallP. WilliamsonJ.F. HugoG.D. Evaluation of 4-dimensional computed tomography to 4-dimensional cone-beam computed tomography deformable image registration for lung cancer adaptive radiation therapy.Int. J. Radiat. Oncol. Biol. Phys.201386237237910.1016/j.ijrobp.2012.12.02323462422
     [Google Scholar]
  15. ClarkK. VendtB. SmithK. FreymannJ. KirbyJ. KoppelP. MooreS. PhillipsS. MaffittD. PringleM. TarboxL. PriorF. The Cancer Imaging Archive (TCIA): Maintaining and operating a public information repository.J. Digit. Imaging20132661045105710.1007/s10278‑013‑9622‑723884657
     [Google Scholar]
  16. HugoG.D. WeissE. SleemanW.C. BalikS. KeallP.J. LuJ. WilliamsonJ.F. A longitudinal four‐dimensional computed tomography and cone beam computed tomography dataset for image‐guided radiation therapy research in lung cancer.Med. Phys.201744276277110.1002/mp.1205927991677
     [Google Scholar]
  17. RomanN.O. ShepherdW. MukhopadhyayN. HugoG.D. WeissE. Interfractional positional variability of fiducial markers and primary tumors in locally advanced non-small-cell lung cancer during audiovisual biofeedback radiotherapy.Int. J. Radiat. Oncol. Biol. Phys.20128351566157210.1016/j.ijrobp.2011.10.05122391105
     [Google Scholar]
  18. ChenP. GuoY. WangD. ChenC. Dlung: Unsupervised few-shot diffeomorphic respiratory motion modeling.arXiv:1710.09412202210.1007/s12204‑022‑2525‑3
     [Google Scholar]
  19. GoceriE.J.A.I.R. Medical image data augmentation: techniques, comparisons and interpretations.Artif Intell Rev202320145
     [Google Scholar]
  20. GoceriE. J. I. J. o. I. S. Comparison of the impacts of dermoscopy image augmentation methods on skin cancer classification and a new augmentation method with wavelet packets.Int. J. Imag. Sys. Technol.2023335172744
     [Google Scholar]
  21. GoceriE.J.I.I.C.I.P. Image augmentation for deep learning based lesion classification from skin images.Applic. Sys.2020144148
     [Google Scholar]
  22. GoceriE. Evaluation of denoising techniques to remove speckle and Gaussian noise from dermoscopy images.Comput Biol Med2023152106474
     [Google Scholar]
  23. GoceriE. Intensity normalization in brain MR images using spatially varying distribution matching.Academia2017
     [Google Scholar]
  24. GoceriE.J.C.B.U.F.B.D. Fully automated and adaptive intensity normalization using statistical features for brain MR images.Celal Bayar Üniversitesi Fen Bilimleri Dergisi201814125134
     [Google Scholar]
/content/journals/cmir/10.2174/0115734056265001231122110350
Loading
Unsupervised Imbalanced Registration for Enhancing Accuracy and Stability in Medical Image Registration
Curr. Med. Imaging 20, e15734056265001 (2024); https://doi.org/10.2174/0115734056265001231122110350
/content/journals/cmir/10.2174/0115734056265001231122110350
/content/journals/cmir/10.2174/0115734056265001231122110350
Loading

Data & Media loading...


  • Article Type:     Research Article
Keyword(s): 4d-Lung; Continuous variable; Data imbalance; Medical image registration; Unsupervised image mixtures; Unsupervised imbalanced registration

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