Abstract
Lung segmentation in high-resolution computed tomography (HRCT) images is necessary before the computer-aided diagnosis (CAD) of interstitial lung disease (ILD). Traditional methods are less intelligent and have lower accuracy of segmentation. This paper develops a novel automatic segmentation model using radiomics with a combination of hand-crafted features and deep features. The study uses ILD Database-MedGIFT from 128 patients with 108 annotated image series and selects 1946 regions of interest (ROI) of lung tissue patterns for training and testing. First, images are denoised by Wiener filter. Then, segmentation is performed by fusion of features that are extracted from the gray-level co-occurrence matrix (GLCM) which is a classic texture analysis method and U-Net which is a standard convolutional neural network (CNN). The final experiment result for segmentation in terms of dice similarity coefficient (DSC) is 89.42%, which is comparable to the state-of-the-art methods. The training performance shows the effectiveness for a combination of texture and deep radiomics features in lung segmentation.
Highlights
Interstitial lung disease (ILD) is a generic term of the clinicopathological entities that are composed by an inhomogeneous group of diseases based on the pathological basic changes of diffuse lung parenchyma, alveolar inflammation, and interstitial fibrosis [1]
In order to illustrate the effectivity of the proposed method, we compared it with the following methods: (1) gray-level co-occurrence matrix (GLCM) [8], (2) U-Net [29], (3) fully convolutional networks (FCNs) [37], and (4) GU: GLCM + U-Net
U-Net is better than FCN, illustrating that our method can improve the performance by comparing it with the conventional deep learning method
Summary
Interstitial lung disease (ILD) is a generic term of the clinicopathological entities that are composed by an inhomogeneous group of diseases based on the pathological basic changes of diffuse lung parenchyma, alveolar inflammation, and interstitial fibrosis [1]. Four main categories of features may be showed at HRCTfor ILD: reticular pattern, nodular patterns, increased lung attenuation, and decreased lung attenuation [5, 6]. Due to the capability of radiologists, level of facilities, and nonspecific lung lesion patterns, it leads to high unpredictability in HRCT interpretations. There are challenges in segmentation of HRCT images for ILD: (1) several noises always occurring in HRCT images resulting in fuzzy edges; (2) depending on low-middle-high level features to distinguish the similar areas; and (3) essential requirements for accuracy of the segmentation algorithm
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
