Automated Tuberculosis Diagnosis Using Fluorescence Images from a Mobile Microscope

In low-resource areas, the most common method of tuberculosis (TB) diagnosis is visual identification of rod-shaped TB bacilli in microscopic images of sputum smears. We present an algorithm for automated TB detection using images from digital microscopes such as CellScope, a novel, portable device capable of brightfield and fluorescence microscopy. Automated processing on such platforms could save lives by bringing healthcare to rural areas with limited access to laboratory-based diagnostics. Our algorithm applies morphological operations and template matching with a Gaussian kernel to identify candidate TB-objects. We characterize these objects using Hu moments, geometric and photometric features, and histograms of oriented gradients and then perform support vector machine classification. We test our algorithm on a large set of CellScope images (594 images corresponding to 290 patients) from sputum smears collected at clinics in Uganda. Our object-level classification performance is highly accurate, with average precision of 89.2% +/- 2.1%. For slide-level classification, our algorithm performs at the level of human readers, demonstrating the potential for making a significant impact on global healthcare.

[1]  Gabriel Cristóbal,et al.  Identification of tuberculosis bacteria based on shape and color , 2004, Real Time Imaging.

[2]  C. Campbell,et al.  Automated identification of tubercle bacilli in sputum. A preliminary investigation. , 1999, Analytical and quantitative cytology and histology.

[3]  Asa L Tapley,et al.  Mobile Digital Imaging-based Microscopy for Tuberculosis Diagnosis , 2012 .

[4]  David G. Lowe,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004, International Journal of Computer Vision.

[5]  Konstantinos Veropoulos,et al.  Medical Decision Making , 2011, Yamada's Textbook of Gastroenterology.

[6]  Marly G. F. Costa,et al.  Automatic identification of mycobacterium tuberculosis with conventional light microscopy , 2008, 2008 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[7]  P. Rousseeuw.  Silhouettes: a graphical aid to the interpretation and validation of cluster analysis , 1987 .

[8]  Carlton A. Evans,et al.  GeneXpert—A Game-Changer for Tuberculosis Control? , 2011, PLoS medicine.

[9]  S. Dorman,et al.  New diagnostic tests for tuberculosis: bench, bedside, and beyond. , 2010, Clinical infectious diseases : an official publication of the Infectious Diseases Society of America.

[10]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[11]  Global Tuberculosis Programme.  Global tuberculosis control : WHO report , 1997 .

[12]  Demetri Psaltis,et al.  Optofluidic microscopy--a method for implementing a high resolution optical microscope on a chip. , 2006, Lab on a chip.

[13]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[14]  Nasser M. Nasrabadi,et al.  Pattern Recognition and Machine Learning , 2006, Technometrics.

[15]  David N Breslauer,et al.  Mobile Phone Based Clinical Microscopy for Global Health Applications , 2009, PloS one.

[16]  Howard Carter,et al.  A PRELIMINARY INVESTIGATION , 2010 .

[17]  D. Osmond,et al.  Sensitivity and specificity of fluorescence microscopy for diagnosing pulmonary tuberculosis in a high HIV prevalence setting. , 2009, The international journal of tuberculosis and lung disease : the official journal of the International Union against Tuberculosis and Lung Disease.

[18]  Jitendra Malik,et al.  Recognition using regions , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[19]  Ming-Kuei Hu,et al.  Visual pattern recognition by moment invariants , 1962, IRE Trans. Inf. Theory.

[20]  Digambar Behera,et al.  Global tuberculosis control 2010 , 2012 .

[21]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[22]  Amy L. Gryshuk,et al.  Cell-Phone-Based Platform for Biomedical Device Development and Education Applications , 2011, PloS one.

[23]  Tania S. Douglas,et al.  Classification of Mycobacterium tuberculosis in Images of ZN-Stained Sputum Smears , 2010, IEEE Transactions on Information Technology in Biomedicine.

[24]  Paul R Klatser,et al.  A comprehensive comparison of Ziehl-Neelsen and fluorescence microscopy for the diagnosis of tuberculosis in a resource-poor urban setting. , 2003, The international journal of tuberculosis and lung disease : the official journal of the International Union against Tuberculosis and Lung Disease.

[25]  John Platt,et al.  Probabilistic Outputs for Support vector Machines and Comparisons to Regularized Likelihood Methods , 1999 .

[26]  Subhransu Maji,et al.  Classification using intersection kernel support vector machines is efficient , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[27]  Jean Ponce,et al.  Computer Vision: A Modern Approach , 2002 .

[28]  Keinosuke Fukunaga,et al.  Introduction to Statistical Pattern Recognition , 1972 .

[29]  Andrea Vedaldi,et al.  Objects in Context , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[30]  M F Beg,et al.  Image processing techniques for identifying Mycobacterium tuberculosis in Ziehl-Neelsen stains. , 2008, The international journal of tuberculosis and lung disease : the official journal of the International Union against Tuberculosis and Lung Disease.

[31]  Chih-Jen Lin,et al.  LIBLINEAR: A Library for Large Linear Classification , 2008, J. Mach. Learn. Res..

[32]  M Desco,et al.  Automatic identification of Mycobacterium tuberculosis by Gaussian mixture models , 2006, Journal of microscopy.

[33]  Eduardo Gotuzzo,et al.  Rapid molecular detection of tuberculosis and rifampin resistance. , 2010, The New England journal of medicine.

[34]  N. Otsu.  A threshold selection method from gray level histograms , 1979 .

[35]  Keinosuke Fukunaga,et al.  Introduction to statistical pattern recognition (2nd ed.) , 1990 .

[36]  Cristian Sminchisescu,et al.  Object Recognition by Sequential Figure-Ground Ranking , 2011, International Journal of Computer Vision.

[37]  Derek Tseng,et al.  Lensfree microscopy on a cellphone. , 2010, Lab on a chip.

[38]  Christopher J. C. Burges,et al.  A Tutorial on Support Vector Machines for Pattern Recognition , 1998, Data Mining and Knowledge Discovery.

[39]  Alexei A. Efros,et al.  Recognition by association via learning per-exemplar distances , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.