Automated cavity detection of infectious pulmonary tuberculosis in chest radiographs

The presence of cavities in the upper lung zones is an important indicator of highly infectious Tuberculosis (TB). Diagnoses performed by the radiologists are labor intensive and of high inter-reader variation. After analyzing the existing computer-aided detection techniques, we propose an fully automated TB cavity detection system which combines a 2D Gaussian-model-based template matching (GTM) for candidates detection with Hessian-matrix-based image enhancement (HIE) for the following cavity segmentation and feature extraction. Experimental results demonstrate that our approach outperforms the existing TB cavity detection technique with higher accuracy and lower false positive rate.

[1]  Hiroshi Fujita,et al.  Automated lesion detection methods for 2D and 3D chest X-ray images , 1999, Proceedings 10th International Conference on Image Analysis and Processing.

[2]  Tao Xu,et al.  An Improved Fluid Vector Flow for Cavity Segmentation in Chest Radiographs , 2010, 2010 20th International Conference on Pattern Recognition.

[3]  Jayaram K. Udupa,et al.  Scale-based diffusive image filtering preserving boundary sharpness and fine structures , 2001, IEEE Transactions on Medical Imaging.

[4]  Ehsan Samei,et al.  Recent advances in chest radiography. , 2006, Radiology.

[5]  Brendt Wohlberg,et al.  Invariant template matching with tangent vectors , 2007 .

[6]  Yi-Hsien Lin,et al.  Template matching using the parametric template vector with translation, rotation and scale invariance , 2008, Pattern Recognit..

[7]  Anup Basu,et al.  A Hybrid Knowledge-Guided Detection Technique for Screening of Infectious Pulmonary Tuberculosis From Chest Radiographs , 2010, IEEE Transactions on Biomedical Engineering.

[8]  Richard Long,et al.  Introducing the sixth edition of the Canadian Tuberculosis Standards. , 2007, The Canadian journal of infectious diseases & medical microbiology = Journal canadien des maladies infectieuses et de la microbiologie medicale.

[9]  Laurens Hogeweg,et al.  Computer-aided diagnosis in chest radiography: beyond nodules. , 2009, European journal of radiology.

[10]  Guido Gerig,et al.  Three-dimensional multi-scale line filter for segmentation and visualization of curvilinear structures in medical images , 1998, Medical Image Anal..

[11]  P. Mortensen.  EPIDEMIOLOGY , 2012, Schizophrenia Research.

[12]  Guido Gerig,et al.  3D Multi-scale line filter for segmentation and visualization of curvilinear structures in medical images , 1997, CVRMed.

[13]  Ronald M. Summers,et al.  Automated detection of blob structures by Hessian analysis and object scale , 2010, 2010 IEEE International Conference on Image Processing.