MRFA-Net: Kidney Segmentation Method Based on Multi-Scale Feature Fusion and Residual Full Attention
Source abstract
Abstract
For the characterization of the kidney segmentation task, this paper proposes a self-supervised kidney segmentation method based on multi-scale feature fusion and residual full attention, named MRFA-Net. In this study, we introduce the multi-scale feature fusion module to extract multi-scale information of kidneys from abdominal CT slices; additionally, the residual full-attention convolution module is designed to handle the multi-scale information of kidneys by introducing a full-attention mechanism, thus improving the segmentation results of kidneys. The Dice coefficient on the Kits19 dataset reaches 0.972. The experimental results demonstrate that the proposed method achieves good segmentation performance compared to other algorithms, effectively enhancing the accuracy of kidney segmentation.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Neural Network Applications · Medical Image Segmentation Techniques · Advanced X-ray and CT Imaging
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming 650500, China
Faculty of Modern Agricultural Engineering, Kunming University of Science and Technology, Kunming 650500, China
Yunnan Province Key Laboratory of Computer, Kunming 650500, China
Funding
National Natural Science Foundation of China (NNSF)
References (37)
Show source-provided references
1. Blood pressure and decline in kidney function: Findings from the Systolic Hypertension in the Elderly Program (SHEP)10.1097/01.ASN.0000031805.09178.37 ↗
2. Silva’s diagnostic renal pathology10.1038/ki.2009.392 ↗
3. Research Progress of Renal Function Assessment by CT
4. A single number for advocacy and communication-worldwide more than 850 million individuals have kidney diseases10.1093/ndt/gfz174 ↗
5. Study on the incidence of chronic kidney disease in a specific region
6. The Relationship Between Uric Acid, Allopurinol, Cardiovascular Events, and Kidney Disease Progression: A Step Forward10.1053/j.ajkd.2015.01.001 ↗
7. Evaluation of artificial intelligence combined with low-dose CT of the lung in the diagnosis of novel coronavirus pneumonia
8. Nadimi-Shahraki, M.H., Taghian, S., Mirjalili, S., and Abualigah, L. (2022). Binary Aquila Optimizer for Selecting Effective Features from Medical Data: A COVID-19 Case Study. Mathematics, 10.10.3390/math10111929 ↗
9. Segmentation of the Prostate, Its Zones, Anterior Fibromuscular Stroma, and Urethra on the MRIs and Multimodality Image Fusion Using U-Net Model. Quant10.21037/qims-22-115 ↗
10. Shehata, M., Mahmoud, A., Soliman, A., Khalifa, F., Ghazal, M., Abou El-Ghar, M., El-Melegy, M., and El-Baz, A. (2018). 3D kidney segmentation from abdominal diffusion MRI using an appearance-guided deformable boundary. PLoS ONE, 13.10.1371/journal.pone.0200082 ↗
11. Construction and application of a web-side 3D organ model visualization system containing anatomical differences in Chinese population
12. Heller, N., Sathianathen, N., Kalapara, A., Walczak, E., Moore, K., Kaluzniak, H., Rosenberg, J., Blake, P., Rengel, Z., and Oestreich, M. (2019). The kits19 challenge data: 300 kidney tumor cases with clinical context, ct semantic segmentations, and surgical outcomes. arXiv.
13. Xie, S., Girshick, R., Dollár, P., Tu, Z., and He, K. (2017, January 21–26). Aggregated residual transformations for deep neural networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/CVPR.2017.634 ↗
14. Ronneberger, O., Fischer, P., and Brox, T. (2015, January 5–9). U-net: Convolutional networks for biomedical image segmentation. Proceedings of the 18th International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI 2015), Munich, Germany.10.1007/978-3-319-24574-4_28 ↗
15. Pohle, R., and Toennies, K.D. (2001, January 5–7). A New Approach for Model-Based Adaptive Region Growing in Medical Image Analysis. Proceedings of the 9th International Conference on Computer Analysis of Images and Patterns (CAIP 2001), Warsaw, Poland.10.1007/3-540-44692-3_30 ↗
16. Belgherbi, A., Hadjidj, I., and Bessaid, A. (2014). Morphological segmentation of the kidneys from abdominal ct images. J. Mech. Med. Biol., 14.10.1142/S0219519414500730 ↗
17. A semi-automated “blanket” method for renal segmentation from non-contrast T1-weighted MR images10.1007/s10334-015-0504-5 ↗
18. Medical image analysis using convolutional neural networks: A review10.1007/s10916-018-1088-1 ↗
19. Computer vision and machine learning for medical image analysis: Recent advances, challenges, and way forward
20. da Cruz, L.B., Araújo, J.D., Ferreira, J.L., Diniz, J.O., Silva, A.C., de Almeida, J.D., de Paiva, A.C., and Gattass, M. (2020). Kidney segmentation from computed tomography images using deep neural network. Comput. Biol. Med., 123.10.1016/j.compbiomed.2020.103906 ↗
21. Imagenet classification with deep convolutional neural networks10.1145/3065386 ↗
22. SERU: A cascaded SE-ResNeXT U-Net for kidney and tumor segmentation10.1002/cpe.5738 ↗
23. Hu, J., Shen, L., and Sun, G. (2018, January 18–23). Squeeze-and-excitation networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00745 ↗
24. Feng, W., Liu, J., Guan, Z., He, Z., Chen, G., and Dai, Y. (2022, January 1–3). Renal Ultrasound Image Segmentation Based on U-Net and Generative Adversarial Nets. Proceedings of the 2022 7th Asia-Pacific Conference on Intelligent Robot Systems (ACIRS), Tianjin, China.10.1109/ACIRS55390.2022.9845575 ↗
25. Goodfellow, I., Pouget-Abadie, J., Mirza, M., and Xu, B. (2014). Generative adversarial nets. arXiv.
26. Khan, A., Khan, M., Gueaieb, W., El Saddik, A., De Masi, G., and Karray, F. (2024, January 1–10). CamoFocus: Enhancing Camouflage Object Detection With Split-Feature Focal Modulation and Context Refinement. Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, Waikoloa, HI, USA.10.1109/WACV57701.2024.00146 ↗
27. Lin, T.Y., Dollár, P., Girshick, R., He, K., Hariharan, B., and Belongie, S. (2017, January 21–26). Feature pyramid networks for object detection. Proceedings of the IEEE Conference on Computer Vision and pattern Recognition, Honolulu, HI, USA.10.1109/CVPR.2017.106 ↗
28. Deconvolution and Checkerboard Artifacts
29. Cao, Y., Xu, J., Lin, S., Wei, F., and Hu, H. (2020, January 13–19). GCNet: Non-Local Networks Meet Squeeze-Excitation Networks and Beyond. Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW), Seattle, WA, USA.10.1109/ICCVW.2019.00246 ↗
30. Song, Q., Mei, K., and Huang, R. (2021, January 2–9). AttaNet: Attention-augmented network for fast and accurate scene parsing. Proceedings of the AAAI Conference on Artificial Intelligence, Hongkong, China.10.1609/aaai.v35i3.16359 ↗
31. Fu, J., Liu, J., Tian, H., Li, Y., Bao, Y., Fang, Z., and Lu, H. (2019, January 15–20). Dual attention network for scene segmentation. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.10.1109/CVPR.2019.00326 ↗
32. Song, Q., Li, J., Li, C., Guo, H., and Huang, R. (March, January 22). Fully attentional network for semantic segmentation. Proceedings of the AAAI Conference on Artificial Intelligence, Online.
33. Fully Convolutional Networks for Semantic Segmentatio10.1109/TPAMI.2016.2572683 ↗
34. Kidney tumor segmentation based on FR2PAttU-Net model10.3389/fonc.2022.853281 ↗
35. Chattopadhyay, S., and Basak, H. (2020). Multi-scale attention u-net (msaunet): A modified u-net architecture for scene segmentation. arXiv.
36. George, Y. (2021). International Challenge on Kidney and Kidney Tumor Segmentation, Springer.
37. Türk, F., Lüy, M., and Barışçı, N. (2020). Kidney and renal tumor segmentation using a hybrid V-Net-Based model. Mathematics, 8.10.3390/math8101772 ↗