Classification of tuberculosis with SURF spatial pyramid features

Tuberculosis is threatening and hinders the socioeconomic development of countries burdened with TB cases. 75% of TB cases are documented in the productive age group of 15–54 years. The definitive diagnoses methods are timely expensive and lack sensitivity in recognizing all TB cases and in all stages. The development of CAD systems (Computer Aided Detection) will facilitate mass screening. In this work, we experimented the use of spatial pyramid of Speed-up Robust Features (SURF) in diagnosing TB. Though dense information representing the lung anatomy imply substantial generalization, the empirical results suggest otherwise. The SURF descriptors are extracted from a grid windows of several sizes and concatenated together. The SVM classifier with sigmoid kernel achieved AUC score of 89% in grid size of 64 pixels compared to only 73% in the concatenated spatial pyramid features.

[1]  Luis Pedro Coelho,et al.  Mahotas: Open source software for scriptable computer vision , 2012, ArXiv.

[2]  Bram van Ginneken,et al.  Automatic Segmentation of Lung Fields in Chest Radiographs , 1999, MICCAI.

[3]  W. Cheung,et al.  The effect of age on the presentation of patients with tuberculosis. , 1995, Tubercle and lung disease : the official journal of the International Union against Tuberculosis and Lung Disease.

[4]  Trevor Hastie,et al.  Multi-class AdaBoost ∗ , 2009 .

[5]  T. Williams,et al.  Update: the radiographic features of pulmonary tuberculosis. , 1986, AJR. American journal of roentgenology.

[6]  Bram van Ginneken,et al.  Segmentation of anatomical structures in chest radiographs using supervised methods: a comparative study on a public database , 2006, Medical Image Anal..

[7]  Clement J. McDonald,et al.  Automatic Tuberculosis Screening Using Chest Radiographs , 2014, IEEE Transactions on Medical Imaging.

[8]  Stefan Jaeger,et al.  Two public chest X-ray datasets for computer-aided screening of pulmonary diseases. , 2014, Quantitative imaging in medicine and surgery.

[9]  Yu-Ting Kuo,et al.  Zone-based analysis for automated detection of abnormalities in chest radiographs. , 2011, Medical physics.

[10]  L. Gabbasova,et al.  Global tuberculosis report (2014) , 2014 .

[11]  James D. Chalmers,et al.  Clinical Tuberculosis , 2015, Breathe.

[12]  B. van Ginneken,et al.  Computer-aided detection (CAD) of lung nodules and small tumours on chest radiographs. , 2009, European journal of radiology.

[13]  Bram van Ginneken,et al.  Clavicle segmentation in chest radiographs , 2012, Medical Image Anal..

[14]  Giuseppe Coppini,et al.  A computer-aided diagnosis approach for emphysema recognition in chest radiography. , 2013, Medical Engineering and Physics.

[15]  Cordelia Schmid,et al.  Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).