M2FNet: multi-modality multi-level fusion network for segmentation of acute and sub-acute ischemic stroke

Abstract Ischemic stroke, a leading cause of death and disability, necessitates accurate detection and automatic segmentation of lesions. While diffusion weight imaging is crucial, its single modality limits the detection of subtle lesions and artifacts. To address this, we propose a multi-modality,...

Full description

Saved in:
Bibliographic Details
Main Authors: Shannan Chen, Xuanhe Zhao, Yang Duan, Ronghui Ju, Peizhuo Zang, Shouliang Qi
Format: Article
Language:English
Published: Springer 2025-04-01
Series:Complex & Intelligent Systems
Subjects:
Online Access:https://doi.org/10.1007/s40747-025-01861-5
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850154609666949120
author Shannan Chen
Xuanhe Zhao
Yang Duan
Ronghui Ju
Peizhuo Zang
Shouliang Qi
author_facet Shannan Chen
Xuanhe Zhao
Yang Duan
Ronghui Ju
Peizhuo Zang
Shouliang Qi
author_sort Shannan Chen
collection DOAJ
description Abstract Ischemic stroke, a leading cause of death and disability, necessitates accurate detection and automatic segmentation of lesions. While diffusion weight imaging is crucial, its single modality limits the detection of subtle lesions and artifacts. To address this, we propose a multi-modality, multi-level fusion network (M2FNet) that aggregates salient features from different modalities across various levels. Our method uses a multi-modal independent encoder to extract modality-specific features from images of different modalities, thereby preserving key details and ensuring rich features. In order to suppress noise while ensuring the best preservation of modality-specific information, we effectively integrate features of different modalities through a cross-modal encoder fusion module. In addition, a cross-modal decoder fusion module and a multi-modality joint loss are designed to further improve the fusion of high-level and low-level features in the up-sampling stage, dynamically utilizing complementary information from multiple modalities to improve segmentation accuracy. To verify the effectiveness of our proposed method, M2FNet was validated on two public magnetic resonance imaging ischemic stroke lesion segmentation benchmark datasets. Whether single or multi-modality, M2FNet performed better than ten other baseline methods. This highlights the effectiveness of M2FNet in multi-modality segmentation of ischemic stroke lesions, making it a promising and powerful quantitative analysis tool for rapid and accurate diagnostic support. The codes of M2FNet are available at https://github.com/ShannanChen/MMFNet .
format Article
id doaj-art-6d6c8ff23899460b965e70c7b01a0a8e
institution OA Journals
issn 2199-4536
2198-6053
language English
publishDate 2025-04-01
publisher Springer
record_format Article
series Complex & Intelligent Systems
spelling doaj-art-6d6c8ff23899460b965e70c7b01a0a8e2025-08-20T02:25:16ZengSpringerComplex & Intelligent Systems2199-45362198-60532025-04-0111612410.1007/s40747-025-01861-5M2FNet: multi-modality multi-level fusion network for segmentation of acute and sub-acute ischemic strokeShannan Chen0Xuanhe Zhao1Yang Duan2Ronghui Ju3Peizhuo Zang4Shouliang Qi5College of Medicine and Biological Information Engineering, Northeastern UniversityCollege of Medicine and Biological Information Engineering, Northeastern UniversityDepartment of Radiology, General Hospital of Northern Theater CommandDepartment of Radiology, The People’s Hospital of Liaoning ProvinceDepartment of Cerebrovascular Disease Treatment Center, The People’s Hospital of Liaoning ProvinceCollege of Medicine and Biological Information Engineering, Northeastern UniversityAbstract Ischemic stroke, a leading cause of death and disability, necessitates accurate detection and automatic segmentation of lesions. While diffusion weight imaging is crucial, its single modality limits the detection of subtle lesions and artifacts. To address this, we propose a multi-modality, multi-level fusion network (M2FNet) that aggregates salient features from different modalities across various levels. Our method uses a multi-modal independent encoder to extract modality-specific features from images of different modalities, thereby preserving key details and ensuring rich features. In order to suppress noise while ensuring the best preservation of modality-specific information, we effectively integrate features of different modalities through a cross-modal encoder fusion module. In addition, a cross-modal decoder fusion module and a multi-modality joint loss are designed to further improve the fusion of high-level and low-level features in the up-sampling stage, dynamically utilizing complementary information from multiple modalities to improve segmentation accuracy. To verify the effectiveness of our proposed method, M2FNet was validated on two public magnetic resonance imaging ischemic stroke lesion segmentation benchmark datasets. Whether single or multi-modality, M2FNet performed better than ten other baseline methods. This highlights the effectiveness of M2FNet in multi-modality segmentation of ischemic stroke lesions, making it a promising and powerful quantitative analysis tool for rapid and accurate diagnostic support. The codes of M2FNet are available at https://github.com/ShannanChen/MMFNet .https://doi.org/10.1007/s40747-025-01861-5Ischemic strokeMagnetic resonance imagingMulti-modality fusionDeep learningSegmentation
spellingShingle Shannan Chen
Xuanhe Zhao
Yang Duan
Ronghui Ju
Peizhuo Zang
Shouliang Qi
M2FNet: multi-modality multi-level fusion network for segmentation of acute and sub-acute ischemic stroke
Complex & Intelligent Systems
Ischemic stroke
Magnetic resonance imaging
Multi-modality fusion
Deep learning
Segmentation
title M2FNet: multi-modality multi-level fusion network for segmentation of acute and sub-acute ischemic stroke
title_full M2FNet: multi-modality multi-level fusion network for segmentation of acute and sub-acute ischemic stroke
title_fullStr M2FNet: multi-modality multi-level fusion network for segmentation of acute and sub-acute ischemic stroke
title_full_unstemmed M2FNet: multi-modality multi-level fusion network for segmentation of acute and sub-acute ischemic stroke
title_short M2FNet: multi-modality multi-level fusion network for segmentation of acute and sub-acute ischemic stroke
title_sort m2fnet multi modality multi level fusion network for segmentation of acute and sub acute ischemic stroke
topic Ischemic stroke
Magnetic resonance imaging
Multi-modality fusion
Deep learning
Segmentation
url https://doi.org/10.1007/s40747-025-01861-5
work_keys_str_mv AT shannanchen m2fnetmultimodalitymultilevelfusionnetworkforsegmentationofacuteandsubacuteischemicstroke
AT xuanhezhao m2fnetmultimodalitymultilevelfusionnetworkforsegmentationofacuteandsubacuteischemicstroke
AT yangduan m2fnetmultimodalitymultilevelfusionnetworkforsegmentationofacuteandsubacuteischemicstroke
AT ronghuiju m2fnetmultimodalitymultilevelfusionnetworkforsegmentationofacuteandsubacuteischemicstroke
AT peizhuozang m2fnetmultimodalitymultilevelfusionnetworkforsegmentationofacuteandsubacuteischemicstroke
AT shouliangqi m2fnetmultimodalitymultilevelfusionnetworkforsegmentationofacuteandsubacuteischemicstroke