EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Radiomics Harmonization in Ultrasound Images for Cervical Cancer Lymph Node Metastasis Prediction Using Cycle-GAN

Zeshuo Zhao, Yuning Qin, Kai Shao, Yapeng Liu, Yangyang Zhang, Heng Li, Wenlong Li, Jiayi Xu, Jicheng Zhang, Boda Ning, Xianwen Yu, Xiance Jin iD und 1 weitere

Technology in Cancer Research & Treatment · 2024

DOI: 10.1177/15330338241302237 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Technology in Cancer Research & Treatment, 2024. Verfasst von Zeshuo Zhao und 12 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiotherapy Center, The First Affiliated Hospital of Wenzhou Medical University, Wenzhou 325000, China. Hauptthemen laut MEDLINE: Ultrasonography, Uterine Cervical Neoplasms, Lymphatic Metastasis. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Wenzhou Municipal Science and Technology Bureau, Natural Science Foundation of Zhejiang Province, Zhejiang Provincial Health Science and Technology Program.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Ultrasound (US) based radiomics is susceptible to variations in scanners, sonographers.

Objective

To retrospectively investigate the feasibility of an adapted cycle generative adversarial networks (CycleGAN) in the style transfer to improve US based radiomics in the prediction of lymph node metastasis (LNM) with images from multiple scanners for patients with early cervical cancer (ECC).

Methods

The CycleGAN was firstly trained to transfer paired US phantom images from one US device to another one; the model was then further trained and tested with clinical US images of ECC by transferring images from four US devices to one specific device; finally, the adapted model was tested with its effects on the radiomics feature harmonization and accuracy of LNM prediction in US based radiomics for ECC patients.

Results

Phantom study demonstrated an increased radiomics harmonization using CycleGAN with an average Pearson correlation coefficient of 0.60 and 0.81 for radiomics features extracted from original and generated images in correlation with the target phantom images, respectively. Additionally, the image quality metric Peak Signal-to-Noise Ratio (PSNR) was increased from 11.18 for the original images to 15.45 for the generated image. Clinical US images of 169 ECC patients were enrolled for style transfer model training and validation. The area under curve (AUC) of LNM prediction radiomics models with features extracted from generated images of different style transfer models ranged from 0.73 to 0.85. The AUC was improved from 0.78 with features extracted from original images to 0.85 with style transferred images.

Conclusions

The adapted CycleGAN network is able to increase the radiomics feature harmonization for images from different ultrasound equipment based on image domain and improve the LNM prediction accuracy for ECC.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

UltrasonographyUterine Cervical NeoplasmsLymphatic MetastasisHumansFemalePhantoms, ImagingRetrospective StudiesMiddle AgedImage Processing, Computer-AssistedAdultLymph NodesROC CurveNeural Networks, ComputerAlgorithmsRadiomics

Stichwörter der Autor:innen

generative adversarial networksharmonizationlymph node metastasisradiomicsultrasound

Autor:innen und Institutionen

  • Department of Radiotherapy Center, The First Affiliated Hospital of Wenzhou Medical University, Wenzhou 325000, China.
  • School of Basic Medical Science, Wenzhou Medical University, Wenzhou, 325000, China.
  • Department of Medical Engineering, The First Affiliated Hospital of Wenzhou Medical University, Wenzhou 325000, China.

ORCID-Profile: Xiance Jin

Förderung

  • Wenzhou Municipal Science and Technology Bureau
  • Natural Science Foundation of Zhejiang Province
  • Zhejiang Provincial Health Science and Technology Program

Zitieren

APA

Zhao, Z., Qin, Y., Shao, K., Liu, Y., Zhang, Y., Li, H., Li, W., Xu, J., Zhang, J., Ning, B., Yu, X., Jin, X., & Jin, J. (2024). Radiomics Harmonization in Ultrasound Images for Cervical Cancer Lymph Node Metastasis Prediction Using Cycle-GAN. Technology in Cancer Research & Treatment. https://doi.org/10.1177/15330338241302237

Vancouver

Zhao Z, Qin Y, Shao K, Liu Y, Zhang Y, Li H, et al. Radiomics Harmonization in Ultrasound Images for Cervical Cancer Lymph Node Metastasis Prediction Using Cycle-GAN. Technology in Cancer Research & Treatment. 2024. doi:10.1177/15330338241302237

BibTeX
@article{Zhao2024,
  author = {Zhao, Zeshuo and Qin, Yuning and Shao, Kai and Liu, Yapeng and Zhang, Yangyang and Li, Heng and Li, Wenlong and Xu, Jiayi and Zhang, Jicheng and Ning, Boda and Yu, Xianwen and Jin, Xiance and Jin, Juebin},
  title = {Radiomics Harmonization in Ultrasound Images for Cervical Cancer Lymph Node Metastasis Prediction Using Cycle-GAN},
  journal = {Technology in Cancer Research & Treatment},
  year = {2024},
  doi = {10.1177/15330338241302237}
}
Kostenlos starten →