Abstract
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 [2], 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.
Chapter PDF
Similar content being viewed by others
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
Boehme, C.C., Nabeta, P., Hillemann, D., Nicol, M.P., Shenai, S., Krapp, F., Allen, J., Tahirli, R., Blakemore, R., Rustomjee, R., Milovic, A., Jones, M., O’Brien, S.M., Persing, D.H., Ruesch-Gerdes, S., Gotuzzo, E., Rodrigues, C., Alland, D., Perkins, M.D.: Rapid Molecular Detection of Tuberculosis and Rifampin Resistance. New England J. of Med. 363(11), 1005–1015 (2010)
Breslauer, D.N., Maamari, R.N., Switz, N.A., Lam, W.A., Fletcher, D.A.: Mobile Phone Based Clinical Microscopy for Global Health Applications. PLoS One 4(7), e6320 (2009)
Cattamanchi, A., Davis, J.L., Worodria, W., den Boon, S., Yoo, S., Matovu, J., Kiidha, J., Nankya, F., Kyeyune, R., Byanyima, P., Andama, A., Joloba, M., Osmond, D.H., Hopewell, P.C., Huang, L.: Sensitivity and Specificity of Fluorescence Microscopy for Diagnosing Pulmonary Tuberculosis in a High HIV Prevalence Setting. Int. J. Tuberc. Lung Dis. 13(9), 1130–1136 (2010)
Dalal, N., Triggs, B.: Histograms of Oriented Gradients for Human Detection. In: CVPR, pp. 886–893 (2005)
Chang, C.C., Lin, C.J.: LIBSVM: A Library for Support Vector Machines. ACM Trans. on Intell. Sys. and Tech. 2(3), 27:1–27:27 (2011)
Cortes, C., Vapnik, V.: Support-vector networks. Mach. Learn. 20(3), 273–297 (1995)
Costa, M.G., Costa Filho, C.F., Sena, J.F., Salem, J., de Lima, M.O.: Automatic Identification of Mycobacterium Tuberculosis with Conventional Light Microscopy. In: 30th Ann. Int. IEEE EMBS Conf., pp. 382–385 (2008)
Evans, C.A.: GeneXpert-A Game-Changer for Tuberculosis Control? PLoS Med. 8, e1001064 (2011)
Forero, M.G., Cristóbal, G., Desco, M.: Automatic Identification of Mycobacterium Tuberculosis by Gaussian Mixture Models. J. of Microscopy 223(2), 120–132 (2006)
Global Tuberculosis Control: WHO Report 2011 (2011), http://www.who.int/tb/publications/global_report/
Hu, M.K.: Visual Pattern Recognition by Moment Invariants. IRE Trans. on Info. Theory 8(2), 179–187 (1962)
Khutlang, R., Krishnan, S., Dendere, R., Whitelaw, A., Veropoulos, K., Learmonth, G., Douglas, T.S.: Classification of Mycobacterium Tuberculosis in Images of ZN-Stained Sputum Smears. IEEE Trans. on Info. Tech. in Biomed. 14(4), 949–957 (2010)
Kivihya-Ndugga, L.E.A., van Cleeff, M.R.A., Githui, W.A., Nganga, L.W., Kibuga, D.K., Odhiambo, J.A., Klatser, P.R.: A Comprehensive Comparison of Ziehl-Neelsen and Fluorescence Microscopy for the Diagnosis of Tuberculosis in a Resource-Poor Urban Setting. Int. J. Tuberc. Lung Dis. 7(12), 1163–1171 (2003)
Kubica, G.P.: Mycobacterium Tuberculosis Bacteria Using Acid-Fast Ziehl-Neelsen Stain; magnified 1000x. Public Health Image Library, Centers for Disease Control and Prevention, Atlanta (1979)
Otsu, N.: A Threshold Selection Method from Gray-Level Histograms. IEEE Trans. on Systems, Man and Cybernetics 9(1), 62–66 (1979)
Platt, J.C.: Probabilistic Outputs for Support Vector Machines and Comparisons to Regularized Likelihood Methods. In: Advances in Large Margin Classifiers, pp. 61–74 (1999)
Fan, R.E., Chang, K.W., Hsieh, C.J., Wang, X.R., Lin, C.J.: LIBLINEAR: A Library for Large Linear Classification. JMLR 9, 1871–1874 (2008)
Veropoulos, K.: Machine learning approaches to medical decision making. U. of Bristol (2001)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Chang, J. et al. (2012). Automated Tuberculosis Diagnosis Using Fluorescence Images from a Mobile Microscope. In: Ayache, N., Delingette, H., Golland, P., Mori, K. (eds) Medical Image Computing and Computer-Assisted Intervention – MICCAI 2012. MICCAI 2012. Lecture Notes in Computer Science, vol 7512. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-33454-2_43
Download citation
DOI: https://doi.org/10.1007/978-3-642-33454-2_43
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-33453-5
Online ISBN: 978-3-642-33454-2
eBook Packages: Computer ScienceComputer Science (R0)