LRU-Net: lightweight and multiscale feature extraction for localization of ACL tears region in MRI images
IntroductionAnterior cruciate ligament (ACL) injuries hold significant clinical importance, making the development of accurate and efficient diagnostic tools essential. Deep learning has emerged as an effective method for detecting ACL tears. However, current models often struggle with multiscale an...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-07-01
|
| Series: | Frontiers in Physiology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fphys.2025.1611267/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849718077534502912 |
|---|---|
| author | Xiaojun Si Liang Yan Cui Shi Yang Xu |
| author_facet | Xiaojun Si Liang Yan Cui Shi Yang Xu |
| author_sort | Xiaojun Si |
| collection | DOAJ |
| description | IntroductionAnterior cruciate ligament (ACL) injuries hold significant clinical importance, making the development of accurate and efficient diagnostic tools essential. Deep learning has emerged as an effective method for detecting ACL tears. However, current models often struggle with multiscale and boundary-sensitive tear patterns and tend to be computationally intensive.MethodsWe present LRU-Net, a lightweight residual U-Net designed for ACL tear segmentation. LRU-Net integrates an advanced attention mechanism that emphasizes gradients and leverages the anatomical position of the ACL, thereby improving boundary sensitivity. Furthermore, it employs a dynamic feature extraction module for adaptive multiscale feature extraction. A dense decoder featuring dense connections enhances feature reuse.ResultsIn experimental evaluations, LRU-Net achieves a Dice Coefficient Score of 97.93% and an Intersection over Union (IoU) of 96.40%.DiscussionIt surpasses benchmark models such as Attention-Unet, Attention-ResUnet, InceptionV3-Unet, Swin-UNet, Trans-UNet and Rethinking ResNets. With a reduced computational footprint, LRU-Net provides a practical and highly accurate solution for the clinical analysis of ACL tears. |
| format | Article |
| id | doaj-art-833e58bd225b460abd6f79f2d3e6192f |
| institution | DOAJ |
| issn | 1664-042X |
| language | English |
| publishDate | 2025-07-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Physiology |
| spelling | doaj-art-833e58bd225b460abd6f79f2d3e6192f2025-08-20T03:12:27ZengFrontiers Media S.A.Frontiers in Physiology1664-042X2025-07-011610.3389/fphys.2025.16112671611267LRU-Net: lightweight and multiscale feature extraction for localization of ACL tears region in MRI imagesXiaojun Si0Liang Yan1Cui Shi2Yang Xu3Department of Information Center, Affiliated Hospital of Nantong University, Nantong, ChinaDepartment of Orthopedics, Nantong Rici Hospital Affiliated to Yangzhou University, Nantong, Jiangsu, ChinaDepartment of Respiratory Medicine, Nantong Rici Hospital Affiliated to Yangzhou University, Nantong, ChinaDepartment of Information Center, Affiliated Hospital of Nantong University, Nantong, ChinaIntroductionAnterior cruciate ligament (ACL) injuries hold significant clinical importance, making the development of accurate and efficient diagnostic tools essential. Deep learning has emerged as an effective method for detecting ACL tears. However, current models often struggle with multiscale and boundary-sensitive tear patterns and tend to be computationally intensive.MethodsWe present LRU-Net, a lightweight residual U-Net designed for ACL tear segmentation. LRU-Net integrates an advanced attention mechanism that emphasizes gradients and leverages the anatomical position of the ACL, thereby improving boundary sensitivity. Furthermore, it employs a dynamic feature extraction module for adaptive multiscale feature extraction. A dense decoder featuring dense connections enhances feature reuse.ResultsIn experimental evaluations, LRU-Net achieves a Dice Coefficient Score of 97.93% and an Intersection over Union (IoU) of 96.40%.DiscussionIt surpasses benchmark models such as Attention-Unet, Attention-ResUnet, InceptionV3-Unet, Swin-UNet, Trans-UNet and Rethinking ResNets. With a reduced computational footprint, LRU-Net provides a practical and highly accurate solution for the clinical analysis of ACL tears.https://www.frontiersin.org/articles/10.3389/fphys.2025.1611267/fullACL (anterior cruciate ligament)MRI imagedeep learningsegmenationattentionlightweight |
| spellingShingle | Xiaojun Si Liang Yan Cui Shi Yang Xu LRU-Net: lightweight and multiscale feature extraction for localization of ACL tears region in MRI images Frontiers in Physiology ACL (anterior cruciate ligament) MRI image deep learning segmenation attention lightweight |
| title | LRU-Net: lightweight and multiscale feature extraction for localization of ACL tears region in MRI images |
| title_full | LRU-Net: lightweight and multiscale feature extraction for localization of ACL tears region in MRI images |
| title_fullStr | LRU-Net: lightweight and multiscale feature extraction for localization of ACL tears region in MRI images |
| title_full_unstemmed | LRU-Net: lightweight and multiscale feature extraction for localization of ACL tears region in MRI images |
| title_short | LRU-Net: lightweight and multiscale feature extraction for localization of ACL tears region in MRI images |
| title_sort | lru net lightweight and multiscale feature extraction for localization of acl tears region in mri images |
| topic | ACL (anterior cruciate ligament) MRI image deep learning segmenation attention lightweight |
| url | https://www.frontiersin.org/articles/10.3389/fphys.2025.1611267/full |
| work_keys_str_mv | AT xiaojunsi lrunetlightweightandmultiscalefeatureextractionforlocalizationofacltearsregioninmriimages AT liangyan lrunetlightweightandmultiscalefeatureextractionforlocalizationofacltearsregioninmriimages AT cuishi lrunetlightweightandmultiscalefeatureextractionforlocalizationofacltearsregioninmriimages AT yangxu lrunetlightweightandmultiscalefeatureextractionforlocalizationofacltearsregioninmriimages |