Lung Field Segmentation of X-ray Images by Normalized Gradient Gaussian Filter and Snake Segmentation

The delineation of bone structures is a crucial step in Chest X-ray image analysis. In the case of lung field segmentation, the main approach after the localization of bone structures is either their individual analysis or their suppression. We prove that a very fast and approximate identification of bone points that are most probably located inside the lung area can help in the segmentation of the lung fields, without the need for bone structure suppression. We introduce a deformation-tolerant region growing procedure. In a two-step approach, a sparse representation of the rib cage is guided to several support points on the lung border. We studied and dealt with the presence of other bone structures that interfere with the lung field. Our method demonstrated very robust behavior even with highly deformed lung appearances, and it achieved state-of-the-art performance in segmentations for the vast majority of evaluated CXR images. Our region growing approach based on the automatically detected rib cage points achieved an average Dice similarity score of 0.92 on the Montgomery County Chest X-ray dataset. We are confident that bone seed points can robustly mark a high-quality lung area while remaining unaffected by different lung shapes and abnormal structures.

Download Full-text

Relation between the Lung Capacity, Oximetric Rebreath Test and Lung Field Area as Measured on the Chest X-ray Films in Three Phases of Respiration in Normal Subjects, the Aged and Patients with Chronic Pulmonary Emphysema

Japanese Circulation Journal ◽

10.1253/jcj.28.693 ◽

1964 ◽

Vol 28 (9) ◽

pp. 693-703

Author(s):

SHIGEKI WATANABE

Keyword(s):

Pulmonary Emphysema ◽

Normal Subjects ◽

Lung Field ◽

X Ray ◽

Lung Capacity ◽

Chest X Ray ◽

Chronic Pulmonary Emphysema ◽

Field Area ◽

Three Phases

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

Integrated lung field segmentation of injured region with anatomical structure analysis by failure–recovery algorithm from chest CT images

Biomedical Signal Processing and Control ◽

10.1016/j.bspc.2013.10.005 ◽

2014 ◽

Vol 12 ◽

pp. 28-38 ◽

Cited By ~ 14

Author(s):

Yuma Iwao ◽

Toshiyuki Gotoh ◽

Seiichiro Kagei ◽

Tae Iwasawa ◽

Marcos de Sales Guerra Tsuzuki

Keyword(s):

Structure Analysis ◽

Ct Images ◽

Chest Ct ◽

Anatomical Structure ◽

Failure Recovery ◽

Lung Field ◽

Recovery Algorithm ◽

Injured Region ◽

Lung Field Segmentation

Download Full-text

Active shape model aided by selective thresholding for lung field segmentation in chest radiographs

2009 9th International Conference on Information Technology and Applications in Biomedicine ◽

10.1109/itab.2009.5394326 ◽

2009 ◽

Cited By ~ 3

Author(s):

Dimitris K. Iakovidis ◽

Michalis Savelonas

Keyword(s):

Chest Radiographs ◽

Active Shape Model ◽

Lung Field ◽

Shape Model ◽

Active Shape ◽

Lung Field Segmentation

Download Full-text

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

Advanced Materials Research ◽

10.4028/www.scientific.net/amr.433-440.3564 ◽

2012 ◽

Vol 433-440 ◽

pp. 3564-3569

Author(s):

Jun Lai ◽

Ke Xu

Keyword(s):

Active Contour ◽

Pulmonary Nodules ◽

Lung Field ◽

Segmentation Method ◽

Hounsfield Units ◽

Lung Segment ◽

Fixed Reference ◽

Legendre Moments ◽

Ct Slices ◽

Lung Field Segmentation

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