Extraction of Airways From CT (EXACT'09)
read more
Citations
The Multimodal Brain Tumor Image Segmentation Benchmark (BRATS)
Robust Brain Extraction Across Datasets and Comparison With Publicly Available Methods
CT-Definable Subtypes of Chronic Obstructive Pulmonary Disease: A Statement of the Fleischner Society.
Medical image segmentation on GPUs – A comprehensive review
Why rankings of biomedical image analysis competitions should be interpreted with care
References
Snakes, shapes, and gradient vector flow
Comparison and Evaluation of Methods for Liver Segmentation From CT Datasets
Efficient algorithms for globally optimal trajectories
Computed tomographic measurements of airway dimensions and emphysema in smokers. Correlation with lung function.
Efficient algorithms for globally optimal trajectories
Related Papers (5)
Frequently Asked Questions (13)
Q2. What is the role of airway segmentation in lung disease?
Analysis of the airways in volumetric computed tomography (CT) scans plays an important role in the diagnosis and monitoring of lung diseases.
Q3. How many sources of leakage are there in the airway tree?
The authors found that over 66% of the submitted results have a leakage count of less than 5, with a maximum leakage volume of 1740.72 mm3.
Q4. How many branches were extracted from the scans constructed using the hard kernel?
For these scans, significantly more branches (p < 0.01)were extracted from the scan constructed using the hard kernel, average of 106 branches compared to 80 branches.
Q5. How many were selected to be included in the dataset for the challenge?
Among the contributed CT scans, 40 were selected to be included into the dataset for the challenge, which were further divided into a training set and a test set.
Q6. What is the average branch count of the scans?
From the available paired inspiration and expiration scans (case 21, 22 and 37, 38), segmentations of the inspiration scans include more correct branches but also more leakage than their expiration counterparts, where inspiration scans exhibits an average branch count of 145 branches and leakage volume of 942 mm3 as compared to 76 branches and 115 mm3 from expiration scans.
Q7. What is the purpose of this paper?
The aim of this paper is to develop a framework for evaluating airway extraction algorithms in a standardized manner and to establish a database with reference segmentations that can be used for future algorithm development.
Q8. How many slices were used to inspect the branches?
To enable visual inspection of extracted branches, each of the branches was presented to the trained observers using a fixed number of slices through the branch at different positions and orientations.
Q9. How many slices were extracted from the reformatted view?
The first four slices were taken perpendicular to the centerline, distributed evenly from the start to the end of the centerline.
Q10. What is the average branch count and tree length for each case?
The highest branch count and tree length detected for each case range from 64.6% to 94.3% and 62.6% to 90.4% respectively, with the average measures for each team no higher than 77%.
Q11. What was the exact airway shape and dimensions?
The exact airway shape and dimensions were not taken into account; branches were considered to be correct as long as there was no significant leakage outside the airway walls.
Q12. What is the average branch count and tree length for each scan?
Results showed that no algorithm is capable of extracting more than 77% of the reference, in terms of both branch count and tree length, on average, indicating that better results may be achieved by combining results from different algorithms.
Q13. What was the process of obtaining the branches at the next level?
Propagation stops when multiple disconnected components were detected in the front, whereupon the process was repeated on the individual split fronts to obtain the branches at the next level.