This paper proposes a new segmentation method for the delimitation of the lung parenchyma in thorax Computed-Tomography (CT) datasets, which will be used as pre-processing step in the CAD (Computer Assisted Detection) system for lung nodule detection that is being developed by the MAGIC-5 (Medical Applications in a Grid Infrastructure Connection) Collaboration. Once finished, the CAD software will run in an integrated “grid” environment, where the potentiality of distributed resources for both data and computation will be exploited. The algorithm is fully automated and three-dimensional (3D). Its most innovative part - to the best of our knowledge - is the segmentation of the external airways (trachea and bronchi), obtained by 3D region growing with wavefront simulation and suitable stop conditions. Another original element is the technique used to check and solve the problem of the apparent ‘fusion’ between the lungs, caused by partial volume effects. A general overview of the algorithm is given, with some details of the innovative parts. The results of its application to a database of about 130 high-resolution low-dose images are discussed.
Data provided are for informational purposes only. Although carefully collected, accuracy cannot be guaranteed. The impact factor represents a rough estimation of the journal's impact factor and does not reflect the actual current impact factor. Publisher conditions are provided by RoMEO. Differing provisions from the publisher's actual policy or licence agreement may be applicable.
"They focused on demarcating the overlapped left and right lungs. A completely automated algorithm for lung segmentation operating in three dimensions was presented  that use region growing algorithm and wavefront simulation. The technique did not work well when lungs are not contained exactly in the middle of slice. "
[Show abstract][Hide abstract] ABSTRACT: Lung segmentation is regarded as foundation for Computer Aided Diagnosis (CAD) of lung diseases. Computed Tomography scan and CAD facilitate researchers to implement cutting-edge image processing techniques for identifying lung cancer and likelihood of other lung diseases including bronchitis, and emphysema. An automated lung segmentation scheme is proposed in this paper that segments lungs from other body organs contained in CT scan, with special emphasis on disjoint in lungs which have not been attempted before. The scheme uses Otsu algorithm and Connected Component Analysis algorithm for initial segmentation. To refine the initial results and avoid under-segmentation and over-segmentation, morphological operations along with bitwise logical AND, OR operations are applied. One of the challenges for lung segmentation algorithms is the overlap of left and right lungs. The algorithm uses Otsu thresholding for segmenting conjoint of right and left lungs. Solution to this exceptional case is also proposed in which there is disjoint in a particular lung due to overlap of anatomical structures. To segment this type of lungs, the method computes centroid of objects. The proposed methodology is tested on the database of Cornell University, USA, which includes 15 test scans containing 2920 slices. The results indicate a successful segmentation of 2757 slices including left and right lung overlap case and the case in which lung is contained in parts.
Full-text · Article · Mar 2013 · European Journal of Scientific Research