EUVIMEDDescubrir EUVIMED
Open access · CC BY-NC-ND 4.0

Unsupervised shape‐and‐texture‐based generative adversarial tuning of pre‐trained networks for carotid segmentation from 3D ultrasound images

Zhaozheng Chen, Mingjie Jiang, Bernard Chiu

Medical Physics · 2024-10 · 51 (10) · 7240-7256

DOI: 10.1002/mp.17291 ↗

At a glance

Journal article in Medical Physics, published online on 2024-07-15. Written by Zhaozheng Chen and 2 co-authors. Institution: Department of Electrical Engineering, City University of Hong Kong, Hong Kong SAR, China. Major MEDLINE topics: Imaging, Three-Dimensional, Carotid Arteries, Ultrasonography, Neural Networks, Computer. Cited 10 times so far (Crossref); 74 references. The full text is freely available (open access, CC BY-NC-ND 4.0). Funded by: Research Grants Council, University Grants Committee, Innovation and Technology Commission, InnoHK at Hong Kong Centre for Cerebro-cardiovascular Health Engineering (COCHE).

ResumenSubjectsDatos bibliográficosCiteRelated studies

Abstract (original language)

Background

Vessel‐wall volume and localized three‐dimensional ultrasound (3DUS) metrics are sensitive to the change of carotid atherosclerosis in response to medical/dietary interventions. Manual segmentation of the media‐adventitia boundary (MAB) and lumen‐intima boundary (LIB) required to obtain these metrics is time‐consuming and prone to observer variability. Although supervised deep‐learning segmentation models have been proposed, training of these models requires a sizeable manually segmented training set, making larger clinical studies prohibitive.

Purpose

We aim to develop a method to optimize pre‐trained segmentation models without requiring manual segmentation to supervise the fine‐tuning process.

Methods

We developed an adversarial framework called the unsupervised shape‐and‐texture generative adversarial network (USTGAN) to fine‐tune a convolutional neural network (CNN) pre‐trained on a source dataset for accurate segmentation of a target dataset. The network integrates a novel texture‐based discriminator with a shape‐based discriminator, which together provide feedback for the CNN to segment the target images in a similar way as the source images. The texture‐based discriminator increases the accuracy of the CNN in locating the artery, thereby lowering the number of failed segmentations. Failed segmentation was further reduced by a self‐checking mechanism to flag longitudinal discontinuity of the artery and by self‐correction strategies involving surface interpolation followed by a case‐specific tuning of the CNN. The U‐Net was pre‐trained by the source dataset involving 224 3DUS volumes with 136, 44, and 44 volumes in the training, validation and testing sets. The training of USTGAN involved the same training group of 136 volumes in the source dataset and 533 volumes in the target dataset. No segmented boundaries for the target cohort were available for training USTGAN. The validation and testing of USTGAN involved 118 and 104 volumes from the target cohort, respectively. The segmentation accuracy was quantified by Dice Similarity Coefficient (DSC), and incorrect localization rate (ILR). Tukey's Honestly Significant Difference multiple comparison test was employed to quantify the difference of DSCs between models and settings, where was considered statistically significant.

Results

USTGAN attained a DSC of % in LIB and % in MAB, improving from the baseline performance of % in LIB ( p ) and % in MAB ( p ). Our approach outperformed six state‐of‐the‐art domain‐adaptation models (MAB: , LIB: ). The proposed USTGAN also had the lowest ILR among the methods compared (LIB: 2.5%, MAB: 1.7%).

Conclusion

Our framework improves segmentation generalizability, thereby facilitating efficient carotid disease monitoring in multicenter trials and in clinics with less expertise in 3DUS imaging.

Subjects

MeSH terms (MEDLINE)

Imaging, Three-DimensionalCarotid ArteriesUltrasonographyNeural Networks, ComputerHumansImage Processing, Computer-AssistedUnsupervised Machine Learning

Author keywords

carotid artery segmentationgenerative adversarial network (GAN)three‐dimensional ultrasound (3DUS) imagesunsupervised domain adaptation

Authors and institutions

  • Department of Electrical Engineering, City University of Hong Kong, Hong Kong SAR, China.
  • Department of Physics & Computer Science, Wilfrid Laurier University, Waterloo, Ontario, Canada.

Funding

  • Research Grants Council, University Grants Committee
  • Innovation and Technology Commission
  • InnoHK at Hong Kong Centre for Cerebro-cardiovascular Health Engineering (COCHE)

Cite

APA

Chen, Z., Jiang, M., & Chiu, B. (2024). Unsupervised shape‐and‐texture‐based generative adversarial tuning of pre‐trained networks for carotid segmentation from 3D ultrasound images. Medical Physics, 51(10), 7240-7256. https://doi.org/10.1002/mp.17291

Vancouver

Chen Z, Jiang M, Chiu B. Unsupervised shape‐and‐texture‐based generative adversarial tuning of pre‐trained networks for carotid segmentation from 3D ultrasound images. Medical Physics. 2024;51(10):7240-7256. doi:10.1002/mp.17291

BibTeX
@article{Chen2024,
  author = {Chen, Zhaozheng and Jiang, Mingjie and Chiu, Bernard},
  title = {Unsupervised shape‐and‐texture‐based generative adversarial tuning of pre‐trained networks for carotid segmentation from 3D ultrasound images},
  journal = {Medical Physics},
  year = {2024},
  volume = {51},
  number = {10},
  pages = {7240--7256},
  doi = {10.1002/mp.17291}
}
Start for free →