Related Experiment Video
Updated: Jun 28, 2026
08:05
Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia
Published on: December 19, 2020
Semi-automatic reference standard construction for quantitative evaluation of lung CT registration.
K Murphy1, B van Ginneken, J P W Pluim
1University Medical Center, Utrecht, The Netherlands.
Medical Image Computing and Computer-Assisted Intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention
|November 6, 2008
Summary
This study introduces an efficient algorithm for creating thoracic CT reference standards. It uses semi-automatic landmark matching to improve the accuracy of computed tomography (CT) scan registration.
Area of Science:
- Medical imaging
- Computer-aided diagnosis
- Radiology
Background:
- Accurate registration of thoracic computed tomography (CT) scans is crucial for longitudinal studies and treatment planning.
- Manual landmark identification and matching can be time-consuming and prone to inter-observer variability.
Purpose of the Study:
- To develop an efficient semi-automatic algorithm for constructing a detailed reference standard for thoracic CT registration.
- To reduce the manual effort and improve the consistency of landmark-based registration.
Main Methods:
- A fully automatic algorithm detects 100 well-distributed landmarks in one thoracic CT scan.
- An observer interface allows manual identification of corresponding landmarks in a second scan.
- Learned scan relationships enable automatic matching of remaining landmarks after minimal manual input.
Main Results:
- The algorithm demonstrates efficient semi-automatic construction of a detailed reference standard.
- Inter-observer differences confirm the accuracy of the landmark matching process.
- The reference standard's applicability was validated on 19 CT scan pairs across two registration datasets.
Conclusions:
- The presented algorithm offers an efficient method for creating accurate thoracic CT reference standards.
- Semi-automatic landmark matching significantly aids in improving CT scan registration accuracy.
- This approach enhances the reliability and applicability of thoracic CT analysis.
