2004
DOI: 10.1007/978-3-540-27868-9_58
|View full text |Cite
|
Sign up to set email alerts
|

Lung Segmentation on Postero-anterior Digital Chest Radiographs Using Active Contours

Abstract: Abstract.A computerized pulmonary segmentation based on the detection of oriented edges was performed in postero-anterior (PA) digital radiography (DR) images. To further improve detection of lung contours, a method based on the use of active contours models was developed. First, the technique calculates a set of reference lines to determine the relative position of the lungs in the image. Then, vertical and horizontal rectangular regions of interest (ROIs) are studied to identify the preliminary edge. These p… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
4
1

Citation Types

0
7
0

Year Published

2008
2008
2016
2016

Publication Types

Select...
3
1

Relationship

0
4

Authors

Journals

citations
Cited by 4 publications
(7 citation statements)
references
References 23 publications
0
7
0
Order By: Relevance
“…the average grey-level of its rows, per column, is estimated. Radiographic image profiles have been proved valuable in several radiographic image analysis tasks [1], [4], [6], [7], [10] as they provide a simple though effective means to navigating through a radiograph by using only one-dimensional information and elementary signal processing techniques. The proposed methodology utilizes horizontal profiles of subsequent image samples in order to obtain spatial instances of the radiograph from which the spinal cord and the ribcage boundaries are detectable even if the patient is bent.…”
Section: ) Spinal Cord Detection and Feature Points Of The Outer Lefmentioning
confidence: 99%
See 2 more Smart Citations
“…the average grey-level of its rows, per column, is estimated. Radiographic image profiles have been proved valuable in several radiographic image analysis tasks [1], [4], [6], [7], [10] as they provide a simple though effective means to navigating through a radiograph by using only one-dimensional information and elementary signal processing techniques. The proposed methodology utilizes horizontal profiles of subsequent image samples in order to obtain spatial instances of the radiograph from which the spinal cord and the ribcage boundaries are detectable even if the patient is bent.…”
Section: ) Spinal Cord Detection and Feature Points Of The Outer Lefmentioning
confidence: 99%
“…The boundaries of the lung fields are approximated by consecutive intuitively manipulated parametric curves. In contrast to the supervised state of the art methodologies [5], [15], it features unsupervised operation, it is not limited by patients' positioning as most other rule-based approaches do [6]- [ 10] and unlike edge-based methods [18] it is tolerant to boundary discontinuities which may arise from severe consolidations or low image quality.…”
Section: Introductionmentioning
confidence: 99%
See 1 more Smart Citation
“…Since the beginning of the 1960s, a variety of computational approaches to the detection of the lung field boundaries in plain chest radiographs have been proposed. These include rule-based methodologies [6][7][8][9][10][11][12], neural network, Markov random fields and other pattern classification approaches [1,13,14], active contour models [15], active shape and active appearance models [16] and graph cuts [17].…”
Section: Introductionmentioning
confidence: 99%
“…The studies [6][7][8][9][10][11] indicate that the detection performance of most rule-based methodologies can degrade if the quality of the radiograph is poor or if the positioning of the patient deviates from the standard. Recently, a rule-based approach coping with the issue of positioning has been proposed in [12].…”
Section: Introductionmentioning
confidence: 99%