Multimodal MRI Image Fusion for Early Automatic Staging of Endometrial Cancer

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 patien...

Full description

Saved in:
Bibliographic Details
Main Authors: Ziyu Zheng, Ye Liu, Longxiang Feng, Peizhong Liu, Haisheng Song, Lin Wang, Fang Huang
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/9/2932
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850136436175536128
author Ziyu Zheng
Ye Liu
Longxiang Feng
Peizhong Liu
Haisheng Song
Lin Wang
Fang Huang
author_facet Ziyu Zheng
Ye Liu
Longxiang Feng
Peizhong Liu
Haisheng Song
Lin Wang
Fang Huang
author_sort Ziyu Zheng
collection DOAJ
description 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.
format Article
id doaj-art-e0ef0cc6c51d4b30bec1aaf43e213fb4
institution OA Journals
issn 1424-8220
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-e0ef0cc6c51d4b30bec1aaf43e213fb42025-08-20T02:31:08ZengMDPI AGSensors1424-82202025-05-01259293210.3390/s25092932Multimodal MRI Image Fusion for Early Automatic Staging of Endometrial CancerZiyu Zheng0Ye Liu1Longxiang Feng2Peizhong Liu3Haisheng Song4Lin Wang5Fang Huang6Informatization Construction and Management Department, Huaqiao University, Quanzhou 362021, ChinaSchool of Physics and Electronic Engineering, Northwest Normal University, Lanzhou 730070, ChinaCollege of Medicine, Huaqiao University, Quanzhou 362021, ChinaSchool of Engineering, Huaqiao University, Quanzhou 362021, ChinaSchool of Physics and Electronic Engineering, Northwest Normal University, Lanzhou 730070, ChinaDepartment of Radiology, Quanzhou First Hospital Affiliated to Fujian Medical University, Quanzhou 362000, ChinaRadiology Department, The Second Affiliated Hospital of Fujian Medical University, Quanzhou 362000, ChinaThis 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.https://www.mdpi.com/1424-8220/25/9/2932endometrial cancertransformerdeep learningMRI multi-positionearly staging
spellingShingle Ziyu Zheng
Ye Liu
Longxiang Feng
Peizhong Liu
Haisheng Song
Lin Wang
Fang Huang
Multimodal MRI Image Fusion for Early Automatic Staging of Endometrial Cancer
Sensors
endometrial cancer
transformer
deep learning
MRI multi-position
early staging
title Multimodal MRI Image Fusion for Early Automatic Staging of Endometrial Cancer
title_full Multimodal MRI Image Fusion for Early Automatic Staging of Endometrial Cancer
title_fullStr Multimodal MRI Image Fusion for Early Automatic Staging of Endometrial Cancer
title_full_unstemmed Multimodal MRI Image Fusion for Early Automatic Staging of Endometrial Cancer
title_short Multimodal MRI Image Fusion for Early Automatic Staging of Endometrial Cancer
title_sort multimodal mri image fusion for early automatic staging of endometrial cancer
topic endometrial cancer
transformer
deep learning
MRI multi-position
early staging
url https://www.mdpi.com/1424-8220/25/9/2932
work_keys_str_mv AT ziyuzheng multimodalmriimagefusionforearlyautomaticstagingofendometrialcancer
AT yeliu multimodalmriimagefusionforearlyautomaticstagingofendometrialcancer
AT longxiangfeng multimodalmriimagefusionforearlyautomaticstagingofendometrialcancer
AT peizhongliu multimodalmriimagefusionforearlyautomaticstagingofendometrialcancer
AT haishengsong multimodalmriimagefusionforearlyautomaticstagingofendometrialcancer
AT linwang multimodalmriimagefusionforearlyautomaticstagingofendometrialcancer
AT fanghuang multimodalmriimagefusionforearlyautomaticstagingofendometrialcancer