ASD-Net: a novel U-Net based asymmetric spatial-channel convolution network for precise kidney and kidney tumor image segmentation
Medical & Biological Engineering & Computing · 2024
DOI: 10.1007/s11517-024-03025-y ↗Kurz gefasst
Fachartikel in der Zeitschrift Medical & Biological Engineering & Computing, 2024. Verfasst von Zhanlin Ji und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Artificial Intelligence, North China University of Science and Technology, Tangshan, 063009, People's Republic of China. Hauptthemen laut MEDLINE: Kidney Neoplasms, Kidney, Neural Networks, Computer, Image Processing, Computer-Assisted. Die Arbeit wurde bisher 44-mal zitiert (Crossref) und nennt 55 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Key Technologies Research and Development Program, Tsinghua Precision Medicine Foundation, Bulgarian National Science Fund.
Abstract (Originalsprache)
Early intervention in tumors can greatly improve human survival rates. With the development of deep learning technology, automatic image segmentation has taken a prominent role in the field of medical image analysis. Manually segmenting kidneys on CT images is a tedious task, and due to the diversity of these images and varying technical skills of professionals, segmentation results can be inconsistent. To address this problem, a novel ASD-Net network is proposed in this paper for kidney and kidney tumor segmentation tasks. First, the proposed network employs newly designed Adaptive Spatial-channel Convolution Optimization (ASCO) blocks to capture anisotropic information in the images. Then, other newly designed blocks, i.e., Dense Dilated Enhancement Convolution (DDEC) blocks, are utilized to enhance feature propagation and reuse it across the network, thereby improving its segmentation accuracy. To allow the network to segment complex and small kidney tumors more effectively, the Atrous Spatial Pyramid Pooling (ASPP) module is incorporated in its middle layer. With its generalized pyramid feature, this module enables the network to better capture and understand context information at various scales within the images. In addition to this, the concurrent spatial and channel squeeze & excitation (scSE) attention mechanism is adopted to better comprehend and manage context information in the images. Additional encoding layers are also added to the base (U-Net) and connected to the original encoding layer through skip connections. The resultant enhanced U-Net structure allows for better extraction and merging of high-level and low-level features, further boosting the network’s ability to restore segmentation details. In addition, the combined Binary Cross Entropy (BCE)-Dice loss is utilized as the network's loss function. Experiments, conducted on the KiTS19 dataset, demonstrate that the proposed ASD-Net network outperforms the existing segmentation networks according to all evaluation metrics used, except for recall in the case of kidney tumor segmentation, where it takes the second place after Attention-UNet. Graphical Abstract
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Artificial Intelligence, North China University of Science and Technology, Tangshan, 063009, People's Republic of China.
- Department of Computing, Xi'an Jiaotong-Liverpool University, Suzhou, People's Republic of China.
- School of Biomedical Engineering, Shenzhen University Health Science Center, Shenzhen, Guangdong, 518060, People's Republic of China. zhangxueji@szu.edu.cn.
- Telecommunications Research Centre (TRC), University of Limerick, Limerick, V94 T9PX, Ireland. ivan.ganchev@ul.ie.
- Department of Computer Systems, University of Plovdiv "Paisii Hilendarski", Plovdiv, 4000, Bulgaria. ivan.ganchev@ul.ie.
- Institute of Mathematics and Informatics, Bulgarian Academy of Sciences, Sofia, 1040, Bulgaria. ivan.ganchev@ul.ie.
Förderung
- Key Technologies Research and Development Program
- Tsinghua Precision Medicine Foundation
- Bulgarian National Science Fund
- Telecommunications Research Centre (TRC) of University of Limerick, Ireland
- University of Limerick
Zitieren
APA
Ji, Z., Mu, J., Liu, J., Zhang, H., Dai, C., Zhang, X., & Ganchev, I. (2024). ASD-Net: a novel U-Net based asymmetric spatial-channel convolution network for precise kidney and kidney tumor image segmentation. Medical & Biological Engineering & Computing. https://doi.org/10.1007/s11517-024-03025-y
Vancouver
Ji Z, Mu J, Liu J, Zhang H, Dai C, Zhang X, et al. ASD-Net: a novel U-Net based asymmetric spatial-channel convolution network for precise kidney and kidney tumor image segmentation. Medical & Biological Engineering & Computing. 2024. doi:10.1007/s11517-024-03025-y
BibTeX
@article{Ji2024,
author = {Ji, Zhanlin and Mu, Juncheng and Liu, Jianuo and Zhang, Haiyang and Dai, Chenxu and Zhang, Xueji and Ganchev, Ivan},
title = {ASD-Net: a novel U-Net based asymmetric spatial-channel convolution network for precise kidney and kidney tumor image segmentation},
journal = {Medical & Biological Engineering & Computing},
year = {2024},
doi = {10.1007/s11517-024-03025-y}
}
EUVIMED