%0 Journal Article
%T Research on Automated Accurate Segmentation Algorithm of Double Kidney in Renal Dynamic Imaging Based on Improved UNet
%A Yujie Hao
%A Yuxing Zhang
%A Changbei Shi
%A Xiaorui Shi
%A Ping Zhu
%A Shuling Zhou
%J Open Journal of Radiology
%P 63-75
%@ 2164-3032
%D 2025
%I Scientific Research Publishing
%R 10.4236/ojrad.2025.152007
%X Objective: Renal dynamic imaging, as an important tool for assessing renal function, is commonly used to test the perfusion and excretory functions of the kidney. In clinical diagnosis, accurate segmentation of renal regions is crucial for subsequent quantitative analysis and functional assessment. Currently, clinical outlining of renal dynamic renal regions still relies on manual labor. The purpose of this study is to construct an automated, accurate segmentation algorithm model for renal dynamic dual kidney regions. Methods: In this paper, an automated, accurate segmentation algorithm based on a non-local triple attention UNet network structure is proposed. The algorithm utilizes a deep convolutional neural network and a non-local triple attention mechanism for feature extraction and multi-scale fusion of renal dynamic imaging images to achieve accurate segmentation of renal dynamic imaging dual kidney regions. Results: By comparing the segmentation with other segmentation algorithms on the renal dynamic imaging dataset, the experimental results show that the algorithm model of this study is better than the standard Unet and Attention UNet segmentation algorithms in terms of the indicators such as mean Intersection over Union (mIoU), mean Pixel Accuracy (mPA), and so on. Conclusion: The algorithmic model in this study is able to automate the accurate segmentation of the double kidney region in renal dynamic images and demonstrates its effectiveness and robustness in automated segmentation of renal dynamic imaging.
%K Renal Dynamic Imaging
%K Dual Kidney Segmentation
%K Deep Learning
%K Nonlocal Attention
%K UNet
%U http://www.scirp.org/journal/PaperInformation.aspx?PaperID=143622