MAAR-Net: Multi-scale attention-assisted residual neural network for renal microvascular structure segmentation
PLOS One · 04.03.2026 · 21 (3) · e0342752
DOI: 10.1371/journal.pone.0342752 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS One, online erschienen am 04.03.2026. Verfasst von Tingting Wang und 10 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiationtherapy, General Hospital of Northern Theater Command, Shenyang, Liaoning, China. Hauptthemen laut MEDLINE: Kidney, Microvessels, Image Processing, Computer-Assisted, Neural Networks, Computer. Die Arbeit nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Application Research of Functionalized extracellular Matrix Polymer Materials in the Treatment of Radiation-induced Skin Injury.
Abstract (Originalsprache)
Renal disease represents a significant public health concern, with renal microvascular lesions playing a crucial role in disease progression. Accurate segmentation of this microvasculature is therefore essential for precise pathologic evaluation. While deep learning offers substantial opportunities in medical image segmentation, the complex structure of renal microvessels poses a considerable challenge. Existing models often struggle to achieve high segmentation accuracy while maintaining branch continuity, suppressing background interference, and delineating tissue boundaries. To address these challenges, we propose a novel deep learning architecture termed the Multiscale Attention-Assisted Residual Neural Network (MAAR-Net). Built upon a U-Net encoder-decoder backbone, MAAR-Net integrates multiscale residual blocks and a high-semantic feature extraction layer to expand the receptive field and enrich semantic information. Depth-separable convolutional attention blocks are incorporated into skip connections to enhance the capture of global and local features, thereby refining segmentation performance. Additional segmentation branches are included to aggregate multi-receptive-field information, further improving segmentation efficiency. Our experiments, conducted on the HuBMAP dataset of 2D PAS-stained kidney histology images, demonstrate the effectiveness of MAAR-Net. The model achieves an Intersection over Union (IoU) of 0.5063 and an F1-score of 0.6751, outperforming other mainstream segmentation models. To facilitate clinical deployment, the optimized model is subsequently compressed via structured pruning to reduce size and increase speed, followed by quantification to lower computational resource consumption. These optimizations ensure the model’s suitability for real-time performance in practical diagnostic applications, independent of dedicated workstations or cloud servers. The results collectively validate the robustness and practical utility of our approach for accurate renal microvessel segmentation in real-world scenarios.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Department of Radiationtherapy, General Hospital of Northern Theater Command, Shenyang, Liaoning, China.
- Department of Oncology, General Hospital of Northern Theater Command, Shenyang, Liaoning, China.
ORCID-Profile: Tingting Wang
Förderung
- Application Research of Functionalized extracellular Matrix Polymer Materials in the Treatment of Radiation-induced Skin Injury
Zitieren
APA
Wang, T., Lin, B., Jiang, T., Wang, H., Yang, D., Shang, F., Li, L., Li, Y., Zhao, M., Xu, Y., & Yan, Y. (2026). MAAR-Net: Multi-scale attention-assisted residual neural network for renal microvascular structure segmentation. PLOS One, 21(3), e0342752. https://doi.org/10.1371/journal.pone.0342752
Vancouver
Wang T, Lin B, Jiang T, Wang H, Yang D, Shang F, et al. MAAR-Net: Multi-scale attention-assisted residual neural network for renal microvascular structure segmentation. PLOS One. 2026;21(3):e0342752. doi:10.1371/journal.pone.0342752
BibTeX
@article{Wang2026,
author = {Wang, Tingting and Lin, Baoguang and Jiang, Tong and Wang, Hengjiao and Yang, Defu and Shang, Feng and Li, Long and Li, Ying and Zhao, Mengyan and Xu, Ying and Yan, Ying},
title = {MAAR-Net: Multi-scale attention-assisted residual neural network for renal microvascular structure segmentation},
journal = {PLOS One},
year = {2026},
volume = {21},
number = {3},
pages = {e0342752},
doi = {10.1371/journal.pone.0342752}
}
EUVIMED