Lupsix: A Cascade Framework for Lung Parenchyma Segmentation in Axial CT Images

Abstract

Lung imaging and computer aided diagnosis (CAD) play a critical role in detection of lung diseases. The most significant partof a lung based CAD is to fulfil the parenchyma segmentation, since disease information is kept in the parenchyma texture. For this purpose,parenchyma segmentation should be accurately performed to find the necessary diagnosis to be used in the treatment. Besides, lungparenchyma segmentation remains as a challenging task in computed tomography (CT) owing to the handicaps oriented with the imagingand nature of parenchyma. In this paper, a cascade framework involving histogram analysis, morphological operations, mean shiftsegmentation (MSS) and region growing (RG) is proposed to perform an accurate segmentation in thorax CT images. In training data, 20axial CT images are utilized to define the optimum parameter values, and 150 images are considered as test data to objectively evaluatethe performance of system. Five statistical metrics are handled to carry out the performance assessment, and a literature comparison isrealized with the state-of-the-art techniques. As a result, parenchyma tissues are segmented with success rates as 98.07% (sensitivity),99.72% (specificity), 99.3% (accuracy), 98.59% (Dice similarity coefficient) and 97.23% (Jaccard) on test dataset.