Related Experiment Video
Updated: Aug 3, 2025
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
Published on: July 5, 2024
Automatic Kidney Segmentation Method Based on an Enhanced Generative Adversarial Network
Tian Shan1,2,3, Yuhan Ying1,2,3, Guoli Song1,2
1State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, China.
Abstract:
When deciding on a kidney tumor's diagnosis and treatment, it is critical to take its morphometry into account. It is challenging to undertake a quantitative analysis of the association between kidney tumor morphology and clinical outcomes due to a paucity of data and the need for the time-consuming manual measurement of imaging variables. To address this issue, an autonomous kidney segmentation technique, namely SegTGAN, is proposed in this paper, which is based on a conventional generative adversarial network model. Its core framework includes a discriminator network with multi-scale feature extraction and a fully convolutional generator network made up of densely linked blocks. For qualitative and quantitative comparisons with the SegTGAN technique, the widely used and related medical image segmentation networks U-Net, FCN, and SegAN are used. The experimental results show that the Dice similarity coefficient (DSC), volumetric overlap error (VOE), accuracy (ACC), and average surface distance (ASD) of SegTGAN on the Kits19 dataset reach 92.28%, 16.17%, 97.28%, and 0.61 mm, respectively. SegTGAN outscores all the other neural networks, which indicates that our proposed model has the potential to improve the accuracy of CT-based kidney segmentation.
Insights
This study introduces SegTGAN, an automated kidney segmentation method using generative adversarial networks. SegTGAN significantly improves the accuracy of kidney tumor morphometry analysis from CT scans.
Area of Science:
- Medical Imaging
- Artificial Intelligence
- Oncology
Background:
- Accurate kidney tumor morphometry is crucial for diagnosis and treatment planning.
- Manual measurement of imaging variables for quantitative analysis is time-consuming and data-limited.
Purpose of the Study:
- To develop an autonomous kidney segmentation technique, SegTGAN, to overcome limitations in quantitative analysis of kidney tumor morphology.
- To improve the accuracy of CT-based kidney segmentation for better clinical outcomes.
Main Methods:
- Proposed SegTGAN, a generative adversarial network-based autonomous kidney segmentation technique.
- SegTGAN features a discriminator network with multi-scale feature extraction and a fully convolutional generator network with dense blocks.
- Compared SegTGAN with U-Net, FCN, and SegAN using the Kits19 dataset.
Main Results:
- SegTGAN achieved a Dice similarity coefficient (DSC) of 92.28%, volumetric overlap error (VOE) of 16.17%, accuracy (ACC) of 97.28%, and average surface distance (ASD) of 0.61 mm on the Kits19 dataset.
- SegTGAN outperformed other evaluated neural networks in segmentation accuracy.
- Demonstrated the potential of SegTGAN to enhance CT-based kidney segmentation.
Conclusions:
- SegTGAN offers a promising solution for automated and accurate kidney segmentation.
- The proposed model can aid in quantitative analysis of kidney tumor morphology, potentially improving clinical decision-making.
- Further development of SegTGAN could advance precision in kidney cancer diagnosis and treatment.
