Multimodal MRI Image Fusion for Early Automatic Staging of Endometrial Cancer
Sensors · 2025
DOI: 10.3390/s25092932 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, 2025. Verfasst von Ziyu Zheng und 6 weiteren Autor:innen. Beteiligte Einrichtung: Informatization Construction and Management Department, Huaqiao University, Quanzhou 362021, China. Hauptthemen laut MEDLINE: Endometrial Neoplasms, Magnetic Resonance Imaging, Multimodal Imaging. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Joint Funds for the innovation of science and Technology, Fu jian province.
Abstract (Originalsprache)
This magnetic resonance imaging multimodal fusion study aims to automate the staging of endometrial cancer using deep learning and to compare the diagnostic performance of deep learning with that of radiologists in the staging of endometrial cancer. This study retrospectively investigated 122 patients with pathologically confirmed early EC from January 1, 2025 to December 31, 2021. Of these patients, 68 were in the International Federation of Gynecology and Obstetrics (FIGO) stage IA, and 54 were in FIGO stage IB. Based on the Swin transformer model and its proprietary SW-MSA (shift window multiple self-coherence) module, magnetic resonance imaging (MRI) images in each of the three planes (sagittal, coronal, and transverse) are cropped, enhanced, and classified, and fusion experiments in the three planes are performed simultaneously. Selecting one plane for the experiment, the accuracy of IA and IB classification was 0.988 in the sagittal, 0.96 in the coronal, and 0.94 in the transverse position, and classification accuracy after the fusion of three planes reached 1. Finally, the automatic classification method based on the Swin transformer has an accuracy of 1, a recall of 1, and a specificity of 1 for early EC classification. In this study, the multimodal fusion approach accurately classified early EC. It was comparable to what a radiologist would perform and simpler and more precise than previous methods that required segmenting followed by staging.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Informatization Construction and Management Department, Huaqiao University, Quanzhou 362021, China.
- School of Physics and Electronic Engineering, Northwest Normal University, Lanzhou 730070, China.
- College of Medicine, Huaqiao University, Quanzhou 362021, China.
- School of Engineering, Huaqiao University, Quanzhou 362021, China.
- Department of Radiology, Quanzhou First Hospital Affiliated to Fujian Medical University, Quanzhou 362000, China.
- Radiology Department, The Second Affiliated Hospital of Fujian Medical University, Quanzhou 362000, China.
ORCID-Profile: Longxiang Feng, Peizhong Liu
Förderung
- Joint Funds for the innovation of science and Technology, Fu jian province
Zitieren
APA
Zheng, Z., Liu, Y., Feng, L., Liu, P., Song, H., Wang, L., & Huang, F. (2025). Multimodal MRI Image Fusion for Early Automatic Staging of Endometrial Cancer. Sensors. https://doi.org/10.3390/s25092932
Vancouver
Zheng Z, Liu Y, Feng L, Liu P, Song H, Wang L, et al. Multimodal MRI Image Fusion for Early Automatic Staging of Endometrial Cancer. Sensors. 2025. doi:10.3390/s25092932
BibTeX
@article{Zheng2025,
author = {Zheng, Ziyu and Liu, Ye and Feng, Longxiang and Liu, Peizhong and Song, Haisheng and Wang, Lin and Huang, Fang},
title = {Multimodal MRI Image Fusion for Early Automatic Staging of Endometrial Cancer},
journal = {Sensors},
year = {2025},
doi = {10.3390/s25092932}
}
EUVIMED