Assessing airway dimensions and attenuation from CT images is useful in thestudy of diseases affecting the airways such as Chronic Obstructive PulmonaryDisease (COPD).
Measurements can be compared between patients and over time ifspecific airway segments can be identified and measures performedin corresponding segments.
manually finding correspondingsegments and performing such measurements is time consuming and difficult.The purposeof the developed and validated system is to enable...
Methods and Materials
Airway tree segmentation The fully automatic segmentation process begins by detecting a seed pointwithin the trachea as a black circular region within the top slice.
From thisseed point the airway centreline tree is then iterativelyextended by searching for locally optimal paths that most resemblethe airway centrelines based on a statistical model derived from a trainingset.
An initial segmentation of the airway lumen is then grown in a tubularfashion around the centreline.
The method is...
The segmentation method has been used on 9711 low dose CT images from theDanish Lung Cancer Screening Trial (DLCST).
Manual inspection of thumbnailimages revealed gross errors in a total of 44 images.
29 were missing branchesat the lobar level and only 15 had obvious false positives.
A thoroughinspection of 10 randomly selected images,
revealed the method extracted 174branches on average and only 3.79% of the found centreline (excluding tracheaand main bronchi) to be partially incorrect (Lo...
The presented system is able to segment the airway wall surfaces in CT images,identify segmental bronchi,
and match segments in multiple scans of the samesubject.
This allows accurate,
reproducible and completely automatic analysisof airways in clinical studies of COPD.
Extraction with Locally Optimal Paths,
Medical Image Computing and
pp 51-58. Petersen,
Optimal Graph Based Segmentation Using Flow Lines with Application to AirwayWall Segmentation,
Information Processing in Medical Imaging,
Jens Petersen is with the Image Group at the Department of Computer Science at the University of Copenhagen,
Denmark; firstname.lastname@example.org. Aasa Feragen is with the Image Group at the Department of Computer Science at the University of Copenhagen,
She is also with theMachine Learning and Computational Biology Research Group at the Max Planck institutefor Developmental Biology and Max Planck Institute for Intelligent Systems,
Germany. Megan Owen is with...