Related Experiment Video
Updated: Dec 27, 2025
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
Published on: July 5, 2024
Self-channel-and-spatial-attention neural network for automated multi-organ segmentation on head and neck CT images
Shuiping Gou1, Nuo Tong1,2, Sharon Qi2
1Key Lab of Intelligent Perception and Image Understanding of Ministry of Education, Xidian University, Xi'an, Shaanxi 710071, People's Republic of China.
Abstract:
Accurate segmentation of organs at risk (OARs) is necessary for adaptive head and neck (H&N) cancer treatment planning, but manual delineation is tedious, slow, and inconsistent. A self-channel-and-spatial-attention neural network (SCSA-Net) is developed for H&N OAR segmentation on CT images. To simultaneously ease the training and improve the segmentation performance, the proposed SCSA-Net utilizes the self-attention ability of the network. Spatial and channel-wise attention learning mechanisms are both employed to adaptively force the network to emphasize the meaningful features and weaken the irrelevant features simultaneously. The proposed network was first evaluated on a public dataset, which includes 48 patients, then on a separate serial CT dataset, which contains ten patients who received weekly diagnostic fan-beam CT scans. On the second dataset, the accuracy of using SCSA-Net to track the parotid and submandibular gland volume changes during radiotherapy treatment was quantified. The Dice similarity coefficient (DSC), positive predictive value (PPV), sensitivity (SEN), average surface distance (ASD), and 95% maximum surface distance (95SD) were calculated on the brainstem, optic chiasm, optic nerves, mandible, parotid glands, and submandibular glands to evaluate the proposed SCSA-Net. The proposed SCSA-Net consistently outperforms the state-of-the-art methods on the public dataset. Specifically, compared with Res-Net and SE-Net, which is constructed from squeeze-and-excitation block equipped residual blocks, the DSC of the optic nerves and submandibular glands is improved by 0.06, 0.03 and 0.05, 0.04 by the SCSA-Net. Moreover, the proposed method achieves statistically significant improvements in terms of DSC on all and eight of nine OARs over Res-Net and SE-Net, respectively. The trained network was able to achieve good segmentation results on the serial dataset, but the results were further improved after fine-tuning of the model using the simulation CT images. For the parotids and submandibular glands, the volume changes of individual patients are highly consistent between the automated and manual segmentation (Pearson's correlation 0.97-0.99). The proposed SCSA-Net is computationally efficient to perform segmentation (sim 2 s/CT).
Insights
A new SCSA-Net model accurately segments organs at risk in head and neck cancer CT scans, improving treatment planning efficiency and consistency. This automated segmentation significantly outperforms existing methods, offering faster and more reliable results.
Area of Science:
- Medical Imaging
- Artificial Intelligence
- Radiotherapy
Background:
- Accurate segmentation of organs at risk (OARs) is crucial for adaptive head and neck (H&N) cancer treatment planning.
- Manual delineation of OARs is time-consuming, labor-intensive, and prone to inter-observer variability.
Purpose of the Study:
- To develop and evaluate a Self-Channel-and-Spatial-Attention Neural Network (SCSA-Net) for automated H&N OAR segmentation on CT images.
- To assess the performance of SCSA-Net in tracking organ volume changes during radiotherapy and compare it with existing methods.
Main Methods:
- A novel SCSA-Net architecture incorporating self-attention mechanisms for adaptive feature emphasis was designed.
- The network was trained and evaluated on public and serial CT datasets, including multiple OARs.
- Segmentation performance was quantified using Dice Similarity Coefficient (DSC), Positive Predictive Value (PPV), Sensitivity (SEN), Average Surface Distance (ASD), and 95% Maximum Surface Distance (95SD).
Main Results:
- SCSA-Net demonstrated superior performance compared to state-of-the-art methods (Res-Net, SE-Net) on a public dataset, with significant DSC improvements for multiple OARs.
- The model achieved accurate segmentation on serial CT scans, with volume changes of parotid and submandibular glands showing high consistency (Pearson's correlation 0.97-0.99) with manual segmentation.
- Fine-tuning with simulation CT images further enhanced segmentation accuracy on serial data.
Conclusions:
- SCSA-Net offers an efficient and accurate automated solution for H&N OAR segmentation, addressing the limitations of manual delineation.
- The method shows potential for real-time monitoring of organ volume changes during radiotherapy, enhancing adaptive treatment planning.
- SCSA-Net provides a computationally efficient (approx. 2 seconds/CT) and reliable tool for improving H&N cancer radiotherapy.
