Lung segmentation on standard and mobile chest radiographs using oriented Gaussian derivatives filter

Abstract

BackgroundUnsupervised lung segmentation method is one of the mandatory processes in order to develop a Content Based Medical Image Retrieval System (CBMIRS) of CXR. The purpose of the study is to present a robust solution for lung segmentation of standard and mobile chest radiographs using fully automated unsupervised method.MethodsThe novel method is based on oriented Gaussian derivatives filter with seven orientations, combined with Fuzzy C-Means (FCM) clustering and thresholding to refine the lung region. In addition, a new algorithm to automatically generate a threshold value for each Gaussian response is also proposed. The algorithms are applied to both PA and AP chest radiographs from both public JSRT dataset and our private datasets from collaborative hospital. Two pre-processing blocks are introduced to standardize the images from different machines. Comparisons with the previous works found in the literature on JSRT dataset shows that our method gives a reasonably good result. We also compare our algorithm with other unsupervised methods to provide fairly comparative measures on the performances for all datasets.ResultsPerformance measures (accuracy, F-score, precision, sensitivity and specificity) for the segmentation of lung in public JSRT dataset are above 0.90 except for the overlap measure is 0.87. The standard deviations for all measures are very low, from 0.01 to 0.06. The overlap measure for the private image database is 0.81 (images from standard machine) and 0.69 (images from two mobile machines). The algorithm is fully automated and fast, with the average execution time of 12.5 s for 512 by 512 pixels resolution.ConclusionsOur proposed method is fully automated, unsupervised, with no training or learning stage is necessary to segment the lungs taken using both a standard machine and two different mobile machines. The proposed pre-processing blocks are significantly useful to standardize the radiographs from mobile machines. The algorithm gives good performance measures, robust, and fast for the application of the CBMIRS.

Computer-aided detection in chest radiography based on artificial intelligence: a survey

“…Rule-based algorithms segment the lung region using rules based on the location, intensity, texture, shape, and relationships with other anatomies [33], including thresholding, edge detection, region growth, mathematical morphology operations, geometric models matching methods, etc. [34–38]. Typical examples based on deformable model segmentation are the active shape model (ASM) [39], the active appearance model (AAM) [40], and improvements to both [41–44].…”

Artificial Intelligence-Based Diagnosis of Cardiac and Related Diseases

“…Anatomical structure segmentation of the chest can be divided into two groups of conventional handcrafted features and deep feature-based methods. Starting from the baseline of handcrafted features-based methods that just consider the single class lung segmentation [2] using local features, researchers have mainly focussed on the general image processing-based methods for the chest anatomy segmentation, as presented in studies [25][26][27][28][29][30][31][32][33][34][35][36][37][38][39]. As this study is based on multiclass deep learning-based semantic segmentation, we mainly focus on learned feature-based literature.…”

Study for Assessing the Advancement of Imaging Techniques in Chest Radiographic Images

“…Exactly similar work is once recreated by Devi and Viveka [23], which is completely equivalent to work done by Candemir et al [22]. Ahmad et al [24] have introduced a unique segmentation process based on the CBIR technique. The uniqueness of this method is implementation of Fuzzy C-Means clustering.…”