Related Experiment Video
Updated: May 2, 2026
13:45
Hybrid µCT-FMT imaging and image analysis
Published on: June 4, 2015
13.1K
A cascaded FAS-UNet+ framework with iterative optimization strategy for segmentation of organs at risk
Hui Zhu1,2,3, Shi Shu1,4, Jianping Zhang5,6
1School of Mathematics and Computational Science, Xiangtan University, Xiangtan, 411105, China.
Medical & Biological Engineering & Computing
|October 4, 2024
Summary
This study introduces a novel cascaded FAS-UNet+ framework for accurate organ at risk (OAR) segmentation in thoracic radiation therapy. The method significantly improves segmentation accuracy for lung and esophageal cancer treatments.
Area of Science:
- Medical imaging
- Artificial intelligence in healthcare
- Radiotherapy planning
Background:
- Accurate segmentation of organs at risk (OARs) in the thorax is crucial for effective lung and esophageal cancer radiation therapy.
- Automatic OAR segmentation remains challenging due to organ variability, complex shapes, and low contrast in medical images.
Purpose of the Study:
- To develop an advanced deep learning framework for precise OAR segmentation in thoracic CT images.
- To address the limitations of existing methods in handling organ variability and low contrast.
Main Methods:
- Proposed a cascaded FAS-UNet+ framework integrating convolutional neural networks and nonlinear multi-grid theory.
- Employed an enhanced iteration block for multiscale feature extraction and a cascade module for refining segmentation.
- Utilized an iterative optimization strategy, data augmentation, and a weighted ensemble technique for improved performance.
Main Results:
- The cascaded FAS-UNet+ framework achieved high accuracy on the SegTHOR dataset.
- Demonstrated significant improvements in Dice score (e.g., 95.22% for aorta) and Hausdorff Distance (e.g., 0.1024 for aorta).
Conclusions:
- The proposed cascaded FAS-UNet+ framework offers a robust and accurate solution for thoracic OAR segmentation.
- This advancement has the potential to enhance the precision and safety of radiation therapy for thoracic cancers.
