EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

MFNet: Meta‐learning based on frequency‐space mix for MRI segmentation in nasopharyngeal carcinoma

Yin Li, Qi Chen, Hao Li, Song Wang, Nutan Chen, Ting Han, Kai Wang, Qingqing Yu, Zhantao Cao, Jun Tang iD

Journal of Cellular and Molecular Medicine · 2024-05 · 28 (9)

DOI: 10.1111/jcmm.18355 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Cellular and Molecular Medicine, online erschienen am 29.04.2024. Verfasst von Yin Li und 9 weiteren Autor:innen. Beteiligte Einrichtung: Department of Otorhinolaryngology, The First People's Hospital of Foshan, Foshan, China. Hauptthemen laut MEDLINE: Magnetic Resonance Imaging, Nasopharyngeal Carcinoma, Nasopharyngeal Neoplasms. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Foshan Science and Technology Innovation Project, Second Affiliated Hospital of Anhui Medical University Clinical Research Development Program.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Deep learning techniques have been applied to medical image segmentation and demonstrated expert‐level performance. Due to the poor generalization abilities of the models in the deployment in different centres, common solutions, such as transfer learning and domain adaptation techniques, have been proposed to mitigate this issue. However, these solutions necessitate retraining the models with target domain data and annotations, which limits their deployment in clinical settings in unseen domains. We evaluated the performance of domain generalization methods on the task of MRI segmentation of nasopharyngeal carcinoma (NPC) by collecting a new dataset of 321 patients with manually annotated MRIs from two hospitals. We transformed the modalities of MRI, including T1WI, T2WI and CE‐T1WI, from the spatial domain to the frequency domain using Fourier transform. To address the bottleneck of domain generalization in MRI segmentation of NPC, we propose a meta‐learning approach based on frequency domain feature mixing. We evaluated the performance of MFNet against existing techniques for generalizing NPC segmentation in terms of Dice and MIoU. Our method evidently outperforms the baseline in handling the generalization of NPC segmentation. The MF‐Net clearly demonstrates its effectiveness for generalizing NPC MRI segmentation to unseen domains (Dice = 67.59%, MIoU = 75.74% T1W1). MFNet enhances the model's generalization capabilities by incorporating mixed‐feature meta‐learning. Our approach offers a novel perspective to tackle the domain generalization problem in the field of medical imaging by effectively exploiting the unique characteristics of medical images.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Magnetic Resonance ImagingNasopharyngeal CarcinomaNasopharyngeal NeoplasmsHumansDeep LearningImage Processing, Computer-AssistedFemaleMaleAlgorithms

Stichwörter der Autor:innen

data augmentationdomain generalizationfeature miximage segmentationnasopharyngeal carcinoma

Autor:innen und Institutionen

  • Department of Otorhinolaryngology, The First People's Hospital of Foshan, Foshan, China.
  • Department of Radiology, The Second Affiliated Hospital of Anhui Medical University, Hefei, China.
  • Department of Infectious Diseases, The First People's Hospital of Changde City, Xiangya School of Medicine, Central South University, Changde, China.
  • University of Electronic Science and Technology of China, Chengdu, China.
  • Machine Learning Research Lab, Volkswagen Group, Munich, Germany.
  • Department of Radiology, The First People's Hospital of Foshan, Foshan, China.

ORCID-Profile: Jun Tang

Förderung

  • Foshan Science and Technology Innovation Project
  • Second Affiliated Hospital of Anhui Medical University Clinical Research Development Program

Zitieren

APA

Li, Y., Chen, Q., Li, H., Wang, S., Chen, N., Han, T., Wang, K., Yu, Q., Cao, Z., & Tang, J. (2024). MFNet: Meta‐learning based on frequency‐space mix for MRI segmentation in nasopharyngeal carcinoma. Journal of Cellular and Molecular Medicine, 28(9). https://doi.org/10.1111/jcmm.18355

Vancouver

Li Y, Chen Q, Li H, Wang S, Chen N, Han T, et al. MFNet: Meta‐learning based on frequency‐space mix for MRI segmentation in nasopharyngeal carcinoma. Journal of Cellular and Molecular Medicine. 2024;28(9). doi:10.1111/jcmm.18355

BibTeX
@article{Li2024,
  author = {Li, Yin and Chen, Qi and Li, Hao and Wang, Song and Chen, Nutan and Han, Ting and Wang, Kai and Yu, Qingqing and Cao, Zhantao and Tang, Jun},
  title = {MFNet: Meta‐learning based on frequency‐space mix for MRI segmentation in nasopharyngeal carcinoma},
  journal = {Journal of Cellular and Molecular Medicine},
  year = {2024},
  volume = {28},
  number = {9},
  doi = {10.1111/jcmm.18355}
}
Kostenlos starten →