Segmentation of Lungs from Chest Radiographs using Boundary Maps and Snake Segmentation Algorithm
Jangam Ebenezer1, Maridu Bhargavi2, Syed Shareefunnisa3
1Jangam Ebenezer, Vignan’s Foundation for Science Technology and Research Deemed to be University, Vadlamudi (Andhra Pradesh), India.
2Maridu Bhargavi, Vignan’s Foundation for Science Technology and Research Deemed to be University, Vadlamudi (Andhra Pradesh), India.
3Syed Shareefunnisa, Vignan’s Foundation for Science Technology and Research Deemed to be University, Vadlamudi (Andhra Pradesh), India.
Manuscript received on 12 February 2019 | Revised Manuscript received on 02 March 2019 | Manuscript Published on 08 June 2019 | PP: 105-108 | Volume-7 Issue-5S4, February 2019 | Retrieval Number: E10200275S419/19©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: Segmentation of lungs from chest radiographs (CXRs) is an essential pre-processing step performed for disease detection. Numerous techniques were proposed by the researchers to segment lung regions from the chest x-rays. In the past three years, hybrid techniques and deep learning-based techniques were proposed to increase the accuracy of segmentation. In this paper a hybrid method is proposed and evaluated for segmentation of lungs using chan vese snake segmentation method and boundary maps. The proposed method is evaluated using the public JSRT database and Jaccard index of our method is 95.2%, which can be compared to those of other best in class strategies (95.7%). The calculation time of our technique is under 13 s for a 256 × 256 CXR when executed on a standard computer.
Keywords: Boundary Detection, Chest Radiograph, Chan-Vese, Lung Field Segmentation, Snake Segmentation.
Scope of the Article: Algorithm Engineering