Article

Anatomy-Constrained Contrastive Learning for Synthetic Segmentation Without Ground-Truth

Authors:

James S. DuncanAuthors Info & Claims

Medical Image Computing and Computer Assisted Intervention – MICCAI 2021: 24th International Conference, Strasbourg, France, September 27–October 1, 2021, Proceedings, Part I

Pages 47 - 56

https://doi.org/10.1007/978-3-030-87193-2_5

Published: 27 September 2021 Publication History

Abstract

A large amount of manual segmentation is typically required to train a robust segmentation network so that it can segment objects of interest in a new imaging modality. The manual efforts can be alleviated if the manual segmentation in one imaging modality (e.g., CT) can be utilized to train a segmentation network in another imaging modality (e.g., CBCT/MRI/PET). In this work, we developed an anatomy-constrained contrastive synthetic segmentation network (AccSeg-Net) to train a segmentation network for a target imaging modality without using its ground-truth. Specifically, we proposed to use anatomy-constraint and patch contrastive learning to ensure the anatomy fidelity during the unsupervised adaptation, such that the segmentation network can be trained on the adapted image with correct anatomical structure/content. The training data for our AccSeg-Net consists of 1) imaging data paired with segmentation ground-truth in source modality, and 2) unpaired source and target modality imaging data. We demonstrated successful applications on CBCT, MRI, and PET imaging data, and showed superior segmentation performances as compared to previous methods. Our code is available at https://github.com/bbbbbbzhou/AccSeg-Net

References

[1]

Ronneberger O, Fischer P, and Brox T Navab N, Hornegger J, Wells WM, and Frangi AF U-Net: convolutional networks for biomedical image segmentation Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015 2015 Cham Springer 234-241

[2]

Oktay, O., et al.: Attention u-net: learning where to look for the pancreas. arXiv preprint arXiv:1804.03999 (2018)

[3]

Roy AG, Navab N, and Wachinger C Frangi AF, Schnabel JA, Davatzikos C, Alberola-López C, and Fichtinger G Concurrent spatial and channel ‘squeeze & excitation’ in fully convolutional networks Medical Image Computing and Computer Assisted Intervention – MICCAI 2018 2018 Cham Springer 421-429

[4]

Alom, M.Z., Yakopcic, C., Hasan, M., Taha, T.M., Asari, V.K.: Recurrent residual u-net for medical image segmentation. J. Med. Imaging 6(1), 014006 (2019)

[5]

Isensee, F., Jaeger, P.F., Kohl, S.A., Petersen, J., Maier-Hein, K.H.: nnu-net: a self-configuring method for deep learning-based biomedical image segmentation. Nature Methods, pp. 1–9 (2020)

[6]

Yu, Q., et al.: C2fnas: coarse-to-fine neural architecture search for 3d medical image segmentation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4126–4135 (2020)

[7]

Zhang Y, Miao S, Mansi T, and Liao R Frangi AF, Schnabel JA, Davatzikos C, Alberola-López C, and Fichtinger G Task driven generative modeling for unsupervised domain adaptation: application to x-ray image segmentation Medical Image Computing and Computer Assisted Intervention – MICCAI 2018 2018 Cham Springer 599-607

[8]

Kamnitsas K et al. Niethammer M, Styner M, Aylward S, Zhu H, Oguz I, Yap P-T, Shen D, et al. Unsupervised domain adaptation in brain lesion segmentation with adversarial networks Information Processing in Medical Imaging 2017 Cham Springer 597-609

[9]

Huo Y et al. Synseg-net: synthetic segmentation without target modality ground truth IEEE Trans. Med. Imaging 2018 38 4 1016-1025

[10]

Zhu, J.Y., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image translation using cycle-consistent adversarial networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2223–2232 (2017)

[11]

Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: International Conference on Machine Learning, PMLR, pp. 1597–1607 (2020)

[12]

Park T, Efros AA, Zhang R, and Zhu J-Y Vedaldi A, Bischof H, Brox T, and Frahm J-M Contrastive learning for unpaired image-to-image translation Computer Vision – ECCV 2020 2020 Cham Springer 319-345

[13]

Wu, Z., Xiong, Y., Yu, S.X., Lin, D.: Unsupervised feature learning via non-parametric instance discrimination. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3733–3742 (2018)

[14]

Yang, H., et al.: Unsupervised mr-to-ct synthesis using structure-constrained cyclegan. IEEE Trans. Med. Imaging 39, 4249–4261 (2020)

[15]

Bilic, P., et al.: The liver tumor segmentation benchmark (lits). arXiv preprint arXiv:1901.04056 (2019)

[16]

Kavur, A.E., et al.: Chaos challenge-combined (ct-mr) healthy abdominal organ segmentation. arXiv preprint arXiv:2001.06535 (2020)

Cited By

Wu XZhong TLiang SWang LLi GZhang Y(2023)Collaborative Modality Generation and Tissue Segmentation for Early-Developing Macaque Brain MR ImagesMedical Image Computing and Computer Assisted Intervention – MICCAI 202310.1007/978-3-031-43901-8_45(470-480)Online publication date: 8-Oct-2023
https://dl.acm.org/doi/10.1007/978-3-031-43901-8_45
Alefsen MVorontsov EKadoury S(2023)M-GenSeg: Domain Adaptation for Target Modality Tumor Segmentation with Annotation-Efficient SupervisionMedical Image Computing and Computer Assisted Intervention – MICCAI 202310.1007/978-3-031-43901-8_14(141-151)Online publication date: 8-Oct-2023
https://dl.acm.org/doi/10.1007/978-3-031-43901-8_14

Index Terms

Anatomy-Constrained Contrastive Learning for Synthetic Segmentation Without Ground-Truth
1. Applied computing
  1. Life and medical sciences
2. Computing methodologies
  1. Artificial intelligence
    1. Computer vision
      1. Computer vision problems
        Image segmentation
  2. Machine learning

Index terms have been assigned to the content through auto-classification.

Recommendations

ASCON: Anatomy-Aware Supervised Contrastive Learning Framework for Low-Dose CT Denoising
Medical Image Computing and Computer Assisted Intervention – MICCAI 2023
Abstract
While various deep learning methods have been proposed for low-dose computed tomography (CT) denoising, most of them leverage the normal-dose CT images as the ground-truth to supervise the denoising process. These methods typically ignore the ...
Self-supervised region-aware segmentation of COVID-19 CT images using 3D GAN and contrastive learning
Abstract
Medical image segmentation is a key initial step in several therapeutic applications. While most of the automatic segmentation models are supervised, which require a well-annotated paired dataset, we introduce a novel annotation-free ...
Highlights
- We proposed a self-supervised pipeline that does not require any manual annotation at the pixel level for segmentation.
FBA-Net: Foreground and Background Aware Contrastive Learning for Semi-Supervised Atrium Segmentation
Medical Image Learning with Limited and Noisy Data
Abstract
Medical image segmentation of gadolinium enhancement magnetic resonance imaging (GE MRI) is an important task in clinical applications. However, manual annotation is time-consuming and requires specialized expertise. Semi-supervised segmentation ...

Comments

Information & Contributors

Information

Published In

cover image Guide Proceedings

Medical Image Computing and Computer Assisted Intervention – MICCAI 2021: 24th International Conference, Strasbourg, France, September 27–October 1, 2021, Proceedings, Part I

Sep 2021

781 pages

ISBN:978-3-030-87192-5

DOI:10.1007/978-3-030-87193-2

Editors:
Marleen de Bruijne
Erasmus MC - University Medical Center Rotterdam, Rotterdam, The Netherlands
,
Philippe C. Cattin
University of Basel, Allschwil, Switzerland
,
Stéphane Cotin
Inria Nancy Grand Est, Villers-lès-Nancy, France
,
Nicolas Padoy
ICube, Université de Strasbourg, CNRS, Strasbourg, France
,
Stefanie Speidel
National Center for Tumor Diseases (NCT/UCC), Dresden, Germany
,
Yefeng Zheng
Tencent Jarvis Lab, Shenzhen, China
,
Caroline Essert
ICube, Université de Strasbourg, CNRS, Strasbourg, France

© Springer Nature Switzerland AG 2021.

Publisher

Springer-Verlag

Berlin, Heidelberg

Publication History

Published: 27 September 2021

Author Tags

Qualifiers

Article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

2
Total Citations
View Citations
0
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 30 Jan 2025

Other Metrics

View Author Metrics

Citations

Cited By

Wu XZhong TLiang SWang LLi GZhang Y(2023)Collaborative Modality Generation and Tissue Segmentation for Early-Developing Macaque Brain MR ImagesMedical Image Computing and Computer Assisted Intervention – MICCAI 202310.1007/978-3-031-43901-8_45(470-480)Online publication date: 8-Oct-2023
https://dl.acm.org/doi/10.1007/978-3-031-43901-8_45
Alefsen MVorontsov EKadoury S(2023)M-GenSeg: Domain Adaptation for Target Modality Tumor Segmentation with Annotation-Efficient SupervisionMedical Image Computing and Computer Assisted Intervention – MICCAI 202310.1007/978-3-031-43901-8_14(141-151)Online publication date: 8-Oct-2023
https://dl.acm.org/doi/10.1007/978-3-031-43901-8_14

View Options

View options

Figures

Tables

Media

View Table of Conten