RMIS-Net: a fast medical image segmentation network based on multilayer perceptron
Medical image segmentation, a pivotal component in diagnostic workflows and therapeutic decision-making, plays a critical role in clinical applications ranging from pathological diagnosis to surgical navigation and treatment evaluation. To address the persistent challenges of computational complexit...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
PeerJ Inc.
2025-05-01
|
| Series: | PeerJ Computer Science |
| Subjects: | |
| Online Access: | https://peerj.com/articles/cs-2882.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850272253074210816 |
|---|---|
| author | Binbin Zhang Guoliang Xu Yiying Xing Nanjie Li Deguang Li |
| author_facet | Binbin Zhang Guoliang Xu Yiying Xing Nanjie Li Deguang Li |
| author_sort | Binbin Zhang |
| collection | DOAJ |
| description | Medical image segmentation, a pivotal component in diagnostic workflows and therapeutic decision-making, plays a critical role in clinical applications ranging from pathological diagnosis to surgical navigation and treatment evaluation. To address the persistent challenges of computational complexity and efficiency limitations in existing methods, we propose RMIS-Net—an innovative lightweight segmentation network with three core components: a convolutional layer for preliminary feature extraction, a shift-based fully connected layer for parameter-efficient spatial modeling, and a tokenized multilayer perceptron for global context capture. This architecture achieves significant parameter reduction while enhancing local feature representation through optimized shift operations. The network incorporates layer normalization and dropout regularization to ensure training stability, complemented by Gaussian error linear unit (GELU) activation functions for improved non-linear modeling. To further refine segmentation precision, we integrate residual connections for gradient flow optimization, a Dice loss function for class imbalance mitigation, and bilinear interpolation for accurate mask reconstruction. Comprehensive evaluations on two benchmark datasets (2018 Data Science Bowl for cellular structure segmentation and ISIC-2018 for lesion boundary delineation) demonstrate RMIS-Net’s superior performance, achieving state-of-the-art metrics including an average F1-score of 0.91 and mean intersection-over-union of 0.82. Remarkably, the proposed architecture requires only 0.03 s per image inference while achieving 27× parameter compression, 10× acceleration in inference speed, and 53× reduction in computational complexity compared to conventional approaches, establishing new benchmarks for efficient yet accurate medical image analysis. |
| format | Article |
| id | doaj-art-5df5b0f9c6554bb9bd4adddbc9e14b1d |
| institution | OA Journals |
| issn | 2376-5992 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | PeerJ Inc. |
| record_format | Article |
| series | PeerJ Computer Science |
| spelling | doaj-art-5df5b0f9c6554bb9bd4adddbc9e14b1d2025-08-20T01:51:54ZengPeerJ Inc.PeerJ Computer Science2376-59922025-05-0111e288210.7717/peerj-cs.2882RMIS-Net: a fast medical image segmentation network based on multilayer perceptronBinbin Zhang0Guoliang Xu1Yiying Xing2Nanjie Li3Deguang Li4College of Sciences, Shihezi University, Shihezi, ChinaSchool of Information Engineering, Luoyang Normal University, Luoyang, ChinaCollege of Sciences, Shihezi University, Shihezi, ChinaSchool of Information Engineering, Luoyang Normal University, Luoyang, ChinaSchool of Information Engineering, Luoyang Normal University, Luoyang, ChinaMedical image segmentation, a pivotal component in diagnostic workflows and therapeutic decision-making, plays a critical role in clinical applications ranging from pathological diagnosis to surgical navigation and treatment evaluation. To address the persistent challenges of computational complexity and efficiency limitations in existing methods, we propose RMIS-Net—an innovative lightweight segmentation network with three core components: a convolutional layer for preliminary feature extraction, a shift-based fully connected layer for parameter-efficient spatial modeling, and a tokenized multilayer perceptron for global context capture. This architecture achieves significant parameter reduction while enhancing local feature representation through optimized shift operations. The network incorporates layer normalization and dropout regularization to ensure training stability, complemented by Gaussian error linear unit (GELU) activation functions for improved non-linear modeling. To further refine segmentation precision, we integrate residual connections for gradient flow optimization, a Dice loss function for class imbalance mitigation, and bilinear interpolation for accurate mask reconstruction. Comprehensive evaluations on two benchmark datasets (2018 Data Science Bowl for cellular structure segmentation and ISIC-2018 for lesion boundary delineation) demonstrate RMIS-Net’s superior performance, achieving state-of-the-art metrics including an average F1-score of 0.91 and mean intersection-over-union of 0.82. Remarkably, the proposed architecture requires only 0.03 s per image inference while achieving 27× parameter compression, 10× acceleration in inference speed, and 53× reduction in computational complexity compared to conventional approaches, establishing new benchmarks for efficient yet accurate medical image analysis.https://peerj.com/articles/cs-2882.pdfMedical image segmentationMultilayer perceptronResidual connectionsDice loss functionGELU activation function |
| spellingShingle | Binbin Zhang Guoliang Xu Yiying Xing Nanjie Li Deguang Li RMIS-Net: a fast medical image segmentation network based on multilayer perceptron PeerJ Computer Science Medical image segmentation Multilayer perceptron Residual connections Dice loss function GELU activation function |
| title | RMIS-Net: a fast medical image segmentation network based on multilayer perceptron |
| title_full | RMIS-Net: a fast medical image segmentation network based on multilayer perceptron |
| title_fullStr | RMIS-Net: a fast medical image segmentation network based on multilayer perceptron |
| title_full_unstemmed | RMIS-Net: a fast medical image segmentation network based on multilayer perceptron |
| title_short | RMIS-Net: a fast medical image segmentation network based on multilayer perceptron |
| title_sort | rmis net a fast medical image segmentation network based on multilayer perceptron |
| topic | Medical image segmentation Multilayer perceptron Residual connections Dice loss function GELU activation function |
| url | https://peerj.com/articles/cs-2882.pdf |
| work_keys_str_mv | AT binbinzhang rmisnetafastmedicalimagesegmentationnetworkbasedonmultilayerperceptron AT guoliangxu rmisnetafastmedicalimagesegmentationnetworkbasedonmultilayerperceptron AT yiyingxing rmisnetafastmedicalimagesegmentationnetworkbasedonmultilayerperceptron AT nanjieli rmisnetafastmedicalimagesegmentationnetworkbasedonmultilayerperceptron AT deguangli rmisnetafastmedicalimagesegmentationnetworkbasedonmultilayerperceptron |