Automatic Lung Nodule Detection on CT Image Using Region Growing
Aswathy S. Nair1, Jisu Elsa Jacob2
1Aswathy S. Nair, M.Tech. Student, SCT College of Engineering, Pappanamcode, Trivandrum (Kerala), India.
2Jisu Elsa Jacob, Asst. Prof., SCT College of Engineering, Pappanamcode, Trivandrum (Kerala), India.
Manuscript received on 15 June 2015 | Revised Manuscript received on 25 June 2015 | Manuscript Published on 30 June 2015 | PP: 157-159 | Volume-4 Issue-5, June 2015 | Retrieval Number: E4120064515/15©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Computer aided detection and diagnosis (CAD) has been widely used for detecting Lung disorders. Lung nodule is an abnormality that may leads to lung cancer characterized by a small round or oval shaped growth on the lung which appears as a white shadow in the CT scan. Lung nodule detection can be done by performing nodule segmentation through thresholding and morphological operation. The segmentation process consists of four stages: Thorax extraction, Lung extraction, morphological operation and structure identification. In the thorax extraction stage all the artifacts external to the patient’s body are discarded and is performed using region growing algorithm to separate the thorax from full CT image. Lung extraction stage is responsible for the identification of lung parenchyma. Morphological operation is done to separate the structure within the parenchyma. Finally the nodule is identified in the structure identification stage using 2-D geometrical features and texture features.
Keywords: Computer Aided Diagnosis (CAD), Segmentation, Computed Tomography (CT), Region Growing.
Scope of the Article: Could Computing