Novel coarse-to-fine dual scale technique for tuberculosis cavity detection in chest radiographs

Xu, Tao; Cheng, Irene; Long, Richard; Mandal, Mrinal

doi:10.1186/1687-5281-2013-3

Cited by 50 publications

(30 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This method is the first automatic algorithm that detects tuberculosis accurately but uses a global adaptive threshold in such a way that automatic initialization cannot place the initial contour within the cavity, leaving a cavity. Xu et al [89] classified tuberculosis cavities by combining texture and geometric features. First, rough feature classification was performed using Gaussian model-based template matching (GTM), LBP, and directional gradient histogram (HOG) methods to extract cavity candidates from CXR images.…”

Section: Specific Disease Detectionmentioning

confidence: 99%

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

et al. 2018

View full text Add to dashboard Cite

As the most common examination tool in medical practice, chest radiography has important clinical value in the diagnosis of disease. Thus, the automatic detection of chest disease based on chest radiography has become one of the hot topics in medical imaging research. Based on the clinical applications, the study conducts a comprehensive survey on computer-aided detection (CAD) systems, and especially focuses on the artificial intelligence technology applied in chest radiography. The paper presents several common chest X-ray datasets and briefly introduces general image preprocessing procedures, such as contrast enhancement and segmentation, and bone suppression techniques that are applied to chest radiography. Then, the CAD system in the detection of specific disease (pulmonary nodules, tuberculosis, and interstitial lung diseases) and multiple diseases is described, focusing on the basic principles of the algorithm, the data used in the study, the evaluation measures, and the results. Finally, the paper summarizes the CAD system in chest radiography based on artificial intelligence and discusses the existing problems and trends.

show abstract

Section: Specific Disease Detectionmentioning

confidence: 99%

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

et al. 2018

View full text Add to dashboard Cite

show abstract

“…If we compare our results with the state of the art, [14][15][16] we achieved higher overlap on a substantially larger number of CXRs (100) containing 126 cavities than what has been reported in the literature (on 50 and 20 cavities). Analysis of the manual segmentations revealed that there were multiple cases where the human readers exhibited large disagreement.…”

Section: Discussionmentioning

confidence: 50%

“…Shen et al did not report the accuracy of their contour segmentation of the cavities. Another automatic cavity detection system was presented by Xu et al 14 based on a coarse-to-fine dual scale methodology, where simpler features, such as Gaussianbased matching and local binary patterns, were applied at a coarse scale, while complex features, such as circularity and Kullback-Leibler divergence measures, were applied on a finer scale for the cavity classification. This method was validated on 35 CXRs containing 50 cavities and reported an average Tanimoto overlapping degree of 67.1%.…”

Section: Introductionmentioning

confidence: 99%

Cavity contour segmentation in chest radiographs using supervised learning and dynamic programming

et al. 2014

View full text Add to dashboard Cite

The proposed cavity segmentation technique produced results with a good degree of overlap with manual expert segmentations. The evaluation measures demonstrated that the results approached the results of the experienced chest radiologists, in terms of overlap measure and contour distance measures. Automatic cavity segmentation can be employed in TB clinics for treatment monitoring, especially in resource limited settings where radiologists are not available.

show abstract

“…The particular organ which attacked by toberculosis is the lung, which is known as lung tuberculosis [1]. Early detection is urgently needed during the treatment on TB lung patient.…”

Section: Introductionmentioning

confidence: 99%

Infiltrate Object Extraction in X-ray Image by Using Math-Morphology Method and Feature Region Analysis

Santony

Na’am

2016

International Journal on Advanced Science, Engineering and Information Technology

View full text Add to dashboard Cite

Abstract-Infiltrate is often called as pulmonary vlek for there are white spotteds on the lung. White spotted could be in form of liquid, condensation, or uncircumcised. The liquid is emerge from blood or suppuration. To detect the existence of infiltrate on the lung, it could be done by doing X-ray Thorax checkup. To observe the infiltrate on x-ray thorax image is unable to be seen by every people, but it is done by experts such as radiologists or the pulmonary experts by doing conscientious research. The research was done by extracting the infiltrate object on x-ray thorax image of tuberculosis patient to clarify the object. The research stage that was done on x-ray thorax image is by detecting the object with segmentation morphology process which consist of dilation and erosion morphology, and side detection by decreasing the value of dilation and erosion morphology. The next stage is extracting the infiltrate object by using binarization and feature region analysis to ommit the unspotted part and determine the infiltrate object from the amount of existing objects. The result of infiltrate object extraction, then, is being calculated for both number and width of each side of lung by using feature region analysis. The result indicates that infiltrate object extraction is able to show an image with the explicit infiltrate object. The result trials of 40 x-ray thorax image on tuberculosis patients proved that the well-extracted images are able to be determined whether on its position, total, and width of infiltrates on lung. The trials of 2 x-ray thorax image on healthy patients are also done as comparisons, and the result indicates that there is no infiltrate objects on both sides of lung.

show abstract

Novel coarse-to-fine dual scale technique for tuberculosis cavity detection in chest radiographs

Cited by 50 publications

References 26 publications

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

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

Cavity contour segmentation in chest radiographs using supervised learning and dynamic programming

Infiltrate Object Extraction in X-ray Image by Using Math-Morphology Method and Feature Region Analysis

Contact Info

Product

Resources

About