Segmenting Lung Fields in CT Image Using Legendre Moments and Active Contour

Conventional methods that perform lung segment -ation in CT slices rely on a large contrast in hounsfield units between the lung and surrounding tissues. However, the lung fields are affected by high density pathologies, and they are discontinuities in the pixel intensities, the traditional segment- ation methods can’t get the good results. Here, we present a new segmentation method of the active contour, which is constraining with respect to a set of fixed reference shapes of lung fields. This approach is based on the shapes descriptors by the legendre moments computed from the shape regions, and it can be used in some complex lung field segmentation, especially suitable for the segmentation of lung field with the juxta-pleural pulmonary nodules. Experiments illustrate that the proposed method is able to segment the lung fields in the CT images successfully.

Download Full-text

Active Contour Based Lung Field Segmentation

2009 International Conference on Intelligent Human-Machine Systems and Cybernetics ◽

10.1109/ihmsc.2009.80 ◽

2009 ◽

Cited By ~ 9

Author(s):

Jun Lai ◽

Ming Ye

Keyword(s):

Active Contour ◽

Lung Field ◽

Lung Field Segmentation

Download Full-text

Active Contour Image Segmentation Method for Training Talents 0f Computer Graphics and Image Processing Technology

IEEE Access ◽

10.1109/access.2020.3022011 ◽

2020 ◽

pp. 1-1

Author(s):

Xinghuo Ye ◽

Qianyi Wang

Keyword(s):

Image Processing ◽

Image Segmentation ◽

Computer Graphics ◽

Active Contour ◽

Processing Technology ◽

Segmentation Method ◽

Image Processing Technology

Download Full-text

Performance Evaluation of Contour Based Segmentation Methods for Ultrasound Images

Advances in Multimedia ◽

10.1155/2018/4976372 ◽

2018 ◽

Vol 2018 ◽

pp. 1-8 ◽

Cited By ~ 5

Author(s):

R. J. Hemalatha ◽

V. Vijaybaskar ◽

T. R. Thamizhvani

Keyword(s):

Active Contour ◽

Performance Metrics ◽

Ultrasound Image ◽

Medical Image Segmentation ◽

Similarity Criteria ◽

Support Vector ◽

Svm Classifier ◽

Ultrasound Images ◽

Segmentation Method ◽

Region Detection

Active contour methods are widely used for medical image segmentation. Using level set algorithms the applications of active contour methods have become flexible and convenient. This paper describes the evaluation of the performance of the active contour models using performance metrics and statistical analysis. We have implemented five different methods for segmenting the synovial region in arthritis affected ultrasound image. A comparative analysis between the methods of segmentation was performed and the best segmentation method was identified using similarity criteria, standard error, and F-test. For further analysis, classification of the segmentation techniques using support vector machine (SVM) classifier is performed to determine the absolute method for synovial region detection. With these results, localized region based active contour named Lankton method is defined to be the best segmentation method.

Download Full-text

An Automatic Segmentation Method Combining an Active Contour Model and a Classification Technique for Detecting Polycomb-group Proteinsin High-Throughput Microscopy Images

Methods in Molecular Biology - Polycomb Group Proteins ◽

10.1007/978-1-4939-6380-5_16 ◽

2016 ◽

pp. 181-197 ◽

Cited By ~ 1

Author(s):

Francesco Gregoretti ◽

Elisa Cesarini ◽

Chiara Lanzuolo ◽

Gennaro Oliva ◽

Laura Antonelli

Keyword(s):

High Throughput ◽

Active Contour ◽

Active Contour Model ◽

Automatic Segmentation ◽

Polycomb Group ◽

Segmentation Method ◽

Classification Technique ◽

Contour Model ◽

Microscopy Images

Download Full-text

Comparison of chest radiographic findings among HIV positive and negative adults with smear positive Pulmonary Tuberculosis in Dar-es-salaam

Tanzania Medical Journal ◽

10.4314/tmj.v31i1.336 ◽

2020 ◽

Vol 31 (1) ◽

pp. 48-65

Author(s):

Balowa M. Baraka ◽

Mboka Jacob ◽

Ramadhani Kazema ◽

Tumaini Nagu ◽

Emmanuel Suluba ◽

...

Keyword(s):

Pulmonary Tuberculosis ◽

Imaging Modality ◽

Left Lung ◽

Pulmonary Nodules ◽

Hiv Positive ◽

P Value ◽

Lung Field ◽

Tuberculosis Case ◽

Radiographic Findings ◽

Severe Immunosuppression

Background: Chest X-ray radiography is a widely available and cheap imaging modality used for identification of pulmonary tuberculosis (PTB) in suspected patients. Knowledge of discriminatory features of PTB among HIV infected patient is of utmost importance to improve tuberculosis case detection and consequently reduce morbidity and mortality associated with TB among HIV infected individuals. We aimed to describe chest radiographic findings among PTB patients and their association with HIV co-infection and CD4 levels among HIV positive patients.Methodology: A total of 170 newly diagnosed consented smear positive PTB patients underwent postero-anterior Chest radiographs (PA - CXR) and HIV testing. Determination of CD4 count was performed among HIV positive patients. The radiographs were interpreted using glossary of terms for thoracic radiology by two independent radiologists who were blinded to HIV diagnosis.Results: Study participants included 100 (58.9%) males and 70 (41.1%) females. Among these 54 (31.8%) had HIV/PTB co-infection. The pattern of radiographic findings among patients with PTB/HIV compared to PTB only were: pulmonary cavities 44.4% vs 61.2%, (p=0.04), alveolar consolidation 64.9% vs 81.7%, (p=0.04), upper zone consolidation 40.7% vs 57.8%, (p=0.039), middle zone consolidation 25.9% vs 44.8%, (p=0.019) and typical PTB 40.7% vs 57.8%, (p=0.039), respectively. Therefore, lesions were less likely to be observed among PTB/HIV compared to PTB only and the differences were statistically significant. When compared to PTB patients only HIV/PTB co-infected patients had more nodules on the left lung field 85.2% vs 60.9% (p=0.023); on each left lung zone upper 59.3% vs 34.4% (p=0.028); mid 77.8% vs 54.7% (p-value=0.039); lower 66.7% vs 34.4% (p=0.005) and miliary nodules 44.4% vs 15.6% (p=0.003), respectively. HIV/PTB co-infected patients with CD4 > 200 cells/μL had more mid zone consolidation (42.9% vs 15.2%, p=0.024).Conclusion: The commonest chest radiographic findings in HIV/PTB co-infected patients were pulmonary cavities and alveolar consolidation are associated with HIV negative status. HIV/PTB co-infected patients with severe immunosuppression had mid zone consolidation. Patients with severe immunosuppression showed less chest radiographic findings. HIV/PTB co-infection was highly associated with mid and lower zone pulmonary nodules and miliary nodules. Key words: PTB, HIV, CXR

Download Full-text

Lung Field Segmentation in Chest Radiographs From Boundary Maps by a Structured Edge Detector

IEEE Journal of Biomedical and Health Informatics ◽

10.1109/jbhi.2017.2687939 ◽

2018 ◽

Vol 22 (3) ◽

pp. 842-851 ◽

Cited By ~ 17

Author(s):

Wei Yang ◽

Yunbi Liu ◽

Liyan Lin ◽

Zhaoqiang Yun ◽

Zhentai Lu ◽

...

Keyword(s):

Chest Radiographs ◽

Lung Field ◽

Edge Detector ◽

Lung Field Segmentation

Download Full-text

Many Is Better Than One: An Integration of Multiple Simple Strategies for Accurate Lung Segmentation in CT Images

BioMed Research International ◽

10.1155/2016/1480423 ◽

2016 ◽

Vol 2016 ◽

pp. 1-13 ◽

Cited By ~ 6

Author(s):

Zhenghao Shi ◽

Jiejue Ma ◽

Minghua Zhao ◽

Yonghong Liu ◽

Yaning Feng ◽

...

Keyword(s):

Region Growing ◽

Disease Diagnosis ◽

Correction Method ◽

Ct Images ◽

Segmentation Method ◽

Lung Segmentation ◽

Multiple Strategies ◽

Simple Strategy ◽

Growing Strategy ◽

Ct Slices

Accurate lung segmentation is an essential step in developing a computer-aided lung disease diagnosis system. However, because of the high variability of computerized tomography (CT) images, it remains a difficult task to accurately segment lung tissue in CT slices using a simple strategy. Motived by the aforementioned, a novel CT lung segmentation method based on the integration of multiple strategies was proposed in this paper. Firstly, in order to avoid noise, the input CT slice was smoothed using the guided filter. Then, the smoothed slice was transformed into a binary image using an optimized threshold. Next, a region growing strategy was employed to extract thorax regions. Then, lung regions were segmented from the thorax regions using a seed-based random walk algorithm. The segmented lung contour was then smoothed and corrected with a curvature-based correction method on each axis slice. Finally, with the lung masks, the lung region was automatically segmented from a CT slice. The proposed method was validated on a CT database consisting of 23 scans, including a number of 883 2D slices (the number of slices per scan is 38 slices), by comparing it to the commonly used lung segmentation method. Experimental results show that the proposed method accurately segmented lung regions in CT slices.

Download Full-text