Application of Artificial Neural Network for Diagnosis of Cerebrospinal Meningitis

  • A. M. Abubakar Department of Electrical and Electronics Engineering, University of Lagos, Nigeria
  • K. A. Abdulsalam Department of Electrical and Electronics Engineering, University of Lagos, Nigeria
  • J. A. Adebisi
Keywords: Multi-layer Artificial Neural Network, Artificial Intelligence, Meningitis


The non-systemization of meningitis diagnosis procedures introduces varying degrees of subjectivity at different stages in the process. This reduces final objectivity of accuracy and increases diagnosis time. To reduce the effects of these shortcomings, an Artificial Intelligence (AI) method for automatic diagnosis of meningitis from gram-stained sputum smear microscopy images, using image processing techniques and Artificial Neural Network (ANN) is presented in this research. An intelligent method of meningitis diagnosis through the application of ANN using image processing techniques was achieved through blood samples collected from the patient and placed in a special dish for microorganism growth observation particularly bacteria. Extraction of image data for cerebrospinal fluid (CSF) sample from the patients were also investigated for meningitis. Segmentation by cascade adaptive threshold-based approach was used to segment meningitis bacilli by pixel intensity value due to gram-staining. A multi-layer (ML) ANN with scaled conjugate gradient descent back propagation training algorithm was used to finally classify the presence or absence of TB bacilli in the pre-processed input image.
MATLAB image processing and Neural Network Toolboxes was used to simulate the procedure. Results of the ANN classifier gave a Mean Square Error (MSE) of 0.025 and accuracy of 94.7%. These results showed that image processing can help to detect the presence or absence of meningitis bacilli in gram-stained CSF smear samples.


Abdulsalam K.A., Adegbenro O., and Akinbulire T.O. ‘Recurrent Neural Network Model for Forecasting Electricity Demand in Nigeria’, Journal of Engineering Research, Volume 21 No. 1 March 2016
Ali A. El-Solh, Chiu-Bin Hsiao, Susan Goodnough, Joseph Serghani, and Brydon J. B. Grant, (1999) Prediction Active Pulmonary Tuberculosis using Artificial Neural Network. Journal of clinical investigation, CHEST 1999, Vol. 116: No 04 pp 968-973.
Baum Eric B. and Haussler David (1989), ‘What Size Net Gives Valid Generalisation’, Neural Computation, MIT Press, Vol. 1 No.1, pp 151-160.
Bishop, C. M. (1995). Neural Network for Pattern Recognition. Clarendon Press Oxford. Oxford University Press.
Blahuta J., Soukup T., Čermák P. (2011), “The image recognition of brain stem ultrasound Images with using a neural network based on PCA” Issue 2, Volume 5, International Journal of Applied Mathematics and Informatics.
Centers for disease control and prevention Retrieved: 12th February, 2017.
Encyclopedia Britannica, (2012) Chicago.
Er, O. Temurtas, E. Tarmukula, A. O. (2010). Tuberculosis Diagnosis using ANNs. Journal of Medical Systems. Vol: 34, No. 03 pp 229 – 305.
Gonzalez R. C, Woods R. E. (2002). Digital Image Processing, second edition. Prentice Hall, Upper Saddle River, NJ.
Graupe, D. (2013) Principles of Artificial Neural Network, Advanced series on circuits and systems series. 3rd Edition, vol, 7. World scientific publishing Ltd, Chicago, USA.
Haykin Simon (1999), ‘Neural Networks: A Comprehensive Foundation’, Prentice Hall Int’l, 2nd ed, 1-897.
Heaton Jeff (2011), ‘Introduction to Mathematics of Neural Networks’, Heaton Research Inc. History of Meningitis Retrieved: March, 2017.
Howard Demuth and Mark Beale (2011). Neural Network Toolbox User’s guide. In: MATLAB® R2011a. The Math Works Inc.
Ibnu Siena, Kusworo Adi, Rahmat Gernowo and Nelly Mirnasari (2012), Development algorithm for TB identification using colour segmentation and Neural Network. International journal of Video and Image processing and Network security. INVIPNS – IJENS, Vol: 12, No 04 pp 9-13
Orhan, E., Nejat, Y. and Temurta, F. (2010). Chest Disease Diagnosis Using Artificial Neural Network. Expert system with applications. Vol 37, pp 7648-7655. Elsevier Health Sciences.
Paulo J.G., Lisboa, Emmanuel C. Ifeachor, Piotr S. Szczepaial (1999) ‘Artificial Neural Network in Biomedicine’ Published by Intech, Printed in India
Pennwalt, M. (2007). Aminu Kano Teaching Hospital Meningitis reference laboratory standard Operating Procedure. Institute of human Virology, Nigeria Action project Facility.
Suzuki, K. (2011), ‘Pixel based Artificial Neural Network in Computer – Aided Diagnosis’, Artificial Neural Network Methodological advances and Biomedical Applications. Retrieved 3rd June, 2017. Trend of major diseases outbreak in Africa Retrieved 17th April, 2017.
Veropolous, K. (2001) Machine learning approaches to medical decision making. Ph.D thesis, Department of Computer Science, University of Bristol, UK.
Voice of Meningitis: Retrieved 12th march, 2017.
What is Artificial Neural Network? From Retrieved 17th April, 2017.
Wilamowski, B.M. (2003). Neural Network Architectures and learning. Proc. of ICIT 2003, Maribor- Slovenia. pp. 1-10.
World Health Organization (WHO), (2017) Global Meningitis control a short updates 2017 report.
How to Cite
Abubakar, A. M., Abdulsalam, K. A., & Adebisi, J. A. (2020). Application of Artificial Neural Network for Diagnosis of Cerebrospinal Meningitis. Journal of Engineering Research, 24(2), 12-25. Retrieved from