An Efficient Lung Disease Identification and Segmentation Based On Contour Extraction

Author(s):

Olivia Russel , CCET, Oddanchatram, Dindigul,Tamilnadu.; T.Cithra, CCET, Oddanchatram, Dindigul,Tamilnadu.; A. Praveena, CCET, Oddanchatram, Dindigul,Tamilnadu.; Uma maheswari, CCET, Oddanchatram, Dindigul,Tamilnadu.; Murugeswari, CCET, Oddanchatram, Dindigul,Tamilnadu.

Keywords:

Computed Tomography (CT), SVM classifier, Toboggan algorithm, Region growing, XCLBP

Abstract:

The classification and identification of the disease in medical images were helpful in biomedical applications. The process of segmentation of the diseased portion in the lung lobe images were done based on Toboggan algorithm. The lung lobes were segmented from the input images based on gradient estimation following original Toboggan algorithm. If the segmented lung lobes were disease affected means then the identification of disease location is done. The classification process is employed using SVM classifier with the help of features extracted from lung lobes using XCSLBP texture identification. From the gradient estimated lung lesion inside the segmented lung lobes were extracted based on the improved Toboggan algorithm. Contours were extracted over the identified lung lesion regions. The overall performance of the process were measured based on the performance metrics. The accuracy obtained here is 99.74% and sensitivity is about 100%.

Other Details:

Manuscript Id	:	IJSTEV2I10063
Published in	:	Volume : 2, Issue : 10
Publication Date	:	01/05/2016
Page(s)	:	260-267

Download Article