LMD²F-Net: Layered Multi-Scale Dual-Branch Dual-Temporal Fusion Network for Medical Image Segmentation

Image segmentation techniques play a crucial role in medical image analysis, directly impacting disease diagnosis, treatment planning, and efficacy evaluation. Although Convolutional Neural Networks (CNNs) and transformer-based approaches have made significant progress in this area, the inherent com...

Full description

Saved in:
Bibliographic Details
Main Authors: Siyuan Ye, Yan Wei
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10767218/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846128506858110976
author Siyuan Ye
Yan Wei
author_facet Siyuan Ye
Yan Wei
author_sort Siyuan Ye
collection DOAJ
description Image segmentation techniques play a crucial role in medical image analysis, directly impacting disease diagnosis, treatment planning, and efficacy evaluation. Although Convolutional Neural Networks (CNNs) and transformer-based approaches have made significant progress in this area, the inherent complexity of medical images, which include features such as low contrast, fuzzy boundaries, and noise, makes automated segmentation tasks challenging. We propose a new architecture called LMD2F-Net, which combines MaxViT’s multi-axis attention and Swin Transformer’s global context modeling. This design enhances both local feature extraction and global context understanding. In the decoding stage, we incorporate a multi-scale spatio-temporal fusion module (MBFM) to optimize feature fusion and enhance the identification of key medical image features. Additionally, we introduce the Dual Layer Fusion (DLF) module, which bridges the encoder and decoder to efficiently fuse multi-level features via a cross-focusing mechanism. Experimental results on several challenging medical image segmentation datasets demonstrate that LMD2F-Net performs well on several evaluation metrics, particularly on key metrics such as the Dice similarity coefficient and Hausdorff distance. These findings confirm the potential of LMD2F-Net in improving the accuracy and robustness of medical image segmentation and provide a valuable reference for future research and clinical practice.
format Article
id doaj-art-f37b770a37744eb4bfc76eef61d4e0f6
institution Kabale University
issn 2169-3536
language English
publishDate 2024-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-f37b770a37744eb4bfc76eef61d4e0f62024-12-11T00:06:30ZengIEEEIEEE Access2169-35362024-01-011218307818308810.1109/ACCESS.2024.350591910767218LMD²F-Net: Layered Multi-Scale Dual-Branch Dual-Temporal Fusion Network for Medical Image SegmentationSiyuan Ye0https://orcid.org/0009-0004-5214-1451Yan Wei1https://orcid.org/0000-0001-6094-1935College of Computer and Information Science, Chongqing Normal University, Chongqing, ChinaCollege of Computer and Information Science, Chongqing Normal University, Chongqing, ChinaImage segmentation techniques play a crucial role in medical image analysis, directly impacting disease diagnosis, treatment planning, and efficacy evaluation. Although Convolutional Neural Networks (CNNs) and transformer-based approaches have made significant progress in this area, the inherent complexity of medical images, which include features such as low contrast, fuzzy boundaries, and noise, makes automated segmentation tasks challenging. We propose a new architecture called LMD2F-Net, which combines MaxViT’s multi-axis attention and Swin Transformer’s global context modeling. This design enhances both local feature extraction and global context understanding. In the decoding stage, we incorporate a multi-scale spatio-temporal fusion module (MBFM) to optimize feature fusion and enhance the identification of key medical image features. Additionally, we introduce the Dual Layer Fusion (DLF) module, which bridges the encoder and decoder to efficiently fuse multi-level features via a cross-focusing mechanism. Experimental results on several challenging medical image segmentation datasets demonstrate that LMD2F-Net performs well on several evaluation metrics, particularly on key metrics such as the Dice similarity coefficient and Hausdorff distance. These findings confirm the potential of LMD2F-Net in improving the accuracy and robustness of medical image segmentation and provide a valuable reference for future research and clinical practice.https://ieeexplore.ieee.org/document/10767218/Medical image segmentationdeep learninghybrid two-branchbitemporal fusionmulti-scale integration
spellingShingle Siyuan Ye
Yan Wei
LMD²F-Net: Layered Multi-Scale Dual-Branch Dual-Temporal Fusion Network for Medical Image Segmentation
IEEE Access
Medical image segmentation
deep learning
hybrid two-branch
bitemporal fusion
multi-scale integration
title LMD²F-Net: Layered Multi-Scale Dual-Branch Dual-Temporal Fusion Network for Medical Image Segmentation
title_full LMD²F-Net: Layered Multi-Scale Dual-Branch Dual-Temporal Fusion Network for Medical Image Segmentation
title_fullStr LMD²F-Net: Layered Multi-Scale Dual-Branch Dual-Temporal Fusion Network for Medical Image Segmentation
title_full_unstemmed LMD²F-Net: Layered Multi-Scale Dual-Branch Dual-Temporal Fusion Network for Medical Image Segmentation
title_short LMD²F-Net: Layered Multi-Scale Dual-Branch Dual-Temporal Fusion Network for Medical Image Segmentation
title_sort lmd x00b2 f net layered multi scale dual branch dual temporal fusion network for medical image segmentation
topic Medical image segmentation
deep learning
hybrid two-branch
bitemporal fusion
multi-scale integration
url https://ieeexplore.ieee.org/document/10767218/
work_keys_str_mv AT siyuanye lmdx00b2fnetlayeredmultiscaledualbranchdualtemporalfusionnetworkformedicalimagesegmentation
AT yanwei lmdx00b2fnetlayeredmultiscaledualbranchdualtemporalfusionnetworkformedicalimagesegmentation