Related Experiment Video
Updated: Oct 12, 2025
08:05
Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia
Published on: December 19, 2020
14.4K
[Effect of Automatic Extraction Accuracy by Different Image Reconstruction Methods Using a Three-dimensional Image
Chiaki Suzuki1,2, Jin Nakano1, Kosuke Matsubara3
1Department of Radiological Technology, Seirei Mikatahara Hospital, Seirei Social Welfare Community.
Nihon Hoshasen Gijutsu Gakkai Zasshi
|November 22, 2021
Summary
Deep learning reconstruction (DLR) offers superior pulmonary vessel visualization for lung surgery planning. This advanced method enhances accuracy in preoperative computed tomography angiography, improving surgical outcomes.
Area of Science:
- Medical Imaging
- Radiology
- Thoracic Surgery
Background:
- Pulmonary segmentectomy requires precise preoperative imaging for accurate surgical planning.
- Optimizing computed tomography (CT) angiography reconstruction is crucial for visualizing pulmonary vasculature.
Purpose of the Study:
- To identify the optimal image reconstruction algorithm for preoperative CT angiography in pulmonary segmentectomy.
- To compare filtered back projection, iterative reconstruction, and deep learning reconstruction (DLR) methods.
Main Methods:
- Evaluated four reconstruction algorithms: filtered back projection, hybrid iterative reconstruction, model-based iterative reconstruction, and DLR.
- Assessed CT numbers, vessel extraction ratios, and misclassification ratios in 20 patients.
Main Results:
- Deep learning reconstruction (DLR) demonstrated significantly higher vessel extraction ratios for pulmonary arteries (96.7%) and veins (90.8%).
- Misclassification ratios were highest for vessels near the superior vena cava due to similar CT numbers across all methods.
Conclusions:
- DLR provides superior pulmonary blood vessel extraction rates and reduced misclassification in automated analysis.
- This method enhances the accuracy of preoperative imaging for pulmonary segmentectomy.
