CHARACTERIZATION AND CLASSIFICATION OF BRAIN TISSUE AND STROKE LESIONS IN NON-CONTRAST COMPUTED TOMOGRAPHY IMAGES OF STROKE PATIENTS USING STATISTICAL TEXTURE DESCRIPTORS AND ARTIFICIAL NEURAL NETWORK
Main Article Content
Abstract
Patients and methods: Two experienced radiologists blinded to each other inspected CT images of 164 stroke patients to identify and categorize stroke lesions into ischaemic and haemorrhagic subtypes. Four regions of interest (ROIs) in each CT slice that demonstrated the lesion; two each representing the lesion and normal tissue were selected. Statistical texture descriptors namely, co-occurrence matrix, run-length matrix, absolute gradient and histogram were calculated for them. Raw data analysis was performed to identify the parameters that best discriminate between normal brain tissue and stroke lesions. Artificial neural network (ANN) was used to classify the ROIs into normal tissue, ischaemic and haemorrhagic lesions using the radiologists’ identification and categorization as the gold standard, and further analyzed using the receiver operating characteristic curve.
Results: Three parameters in each texture class discriminated between normal tissue, ischaemic and haemorrhagic stroke lesions. The discriminating co-occurrence matrix parameters were sum average parameters namely S1-1 SumAverg, S1-0 SumAverg and S0-1 SumAverg. For the run-length matrix, short run emphasis in horizontal, 1350 and 450 directions were the discriminating features. The discriminating absolute gradient parameters were gradient non-zeros, gradient variance and gradient mean. For the histogram class, the mean, 90th and 99th percentiles were the discriminating parameters. The ANN achieved a sensitivity of 0.637, specificity 0.753, false positive rate (FPR) 0.247, and false negative rate (FNR) 0.363 with co-occurrence matrix. With run-length matrix the sensitivity was 0.544, specificity 0.607, FPR 0.393, and FNR 0.456 while with absolute gradient the sensitivity was 0.546, specificity 0.586, FPR 0.414, FNR 0.454. With histogram, the sensitivity was 0.947, specificity 0.962, FPR 0.038, and FNR 0.053.
Conclusion: The histogram texture features showed the highest sensitivity and specificity in the classification of brain tissue and stroke lesions using the artificial neural network.
Downloads
Article Details
Section
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
All articles in JRRS are published under the Creative Commons Attribution 4.0 International License (CC BY 4.0). This permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
How to Cite
References
Imarhiagbe, F. A., & Ogbeide, E. (2011). Clinical–imaging dissociation in strokes in a southern Nigerian tertiary hospital: Review of 123 cases. Nigerian Journal of Hospital Practice, 8(1–2), 3–7.
Chawla, M., Sharma, S., Swansiwamy, J., & Kishore, L. T. (2009). A method for automatic detection and classification of stroke from brain CT images. EMBC 2009 Report No. IIIT/TR/2009/188, Centre for Visual Information Technology, International Institute of Information Technology, Hyderabad, India.
Kidwell, C. S., Villablanca, J. P., & Saver, J. L. (2000). Advances in neuroimaging of acute stroke. Current Atherosclerosis Reports, 2, 126–135.
Bhat, P., & Singh, M. (2012). Classification of stroke using texture analysis on CT images. International Journal of Soft Computing and Engineering, 2(3), 527–530.
Oliveira, M. S., Fernandes, P. T., Alvelar, W. M., Santos, S. R. M., Castellano, G., & Li, L. M. (2009). Texture analysis of computed tomography images of acute ischaemic stroke patients. Brazilian Journal of Medical and Biological Research, 42(11), 1076–1099.
Castellano, G., Bonilha, L., Li, L. M., & Cendes, F. (2004). Texture analysis of medical images. Clinical Radiology, 59(12), 1061–1069.
Materka, A., & Strzelecki, M. (1998). Texture analysis methods: A review. Technical University of Lodz, Institute of Electronics, COST B11 Report, Brussels.
Waugh, S. A. (2014). The use of texture analysis in breast magnetic resonance imaging (Doctoral thesis). University of Dundee, Scotland, pp. 75–81.
Zhang, J., Tong, L., Wang, L., & Li, N. (2008). Texture analysis of multiple sclerosis: A comparative study. Magnetic Resonance Imaging, 26(8), 1160–1166.
Kassner, A., & Thornhill, R. E. (2010). Texture analysis: A review of neurologic MR imaging applications. American Journal of Neuroradiology, 31, 809–816.
Tzacheva, A. A., Najarian, K., & Brockway, J. P. (2003). Breast cancer detection in gadolinium-enhanced MR images by static region descriptors and neural networks. Journal of Magnetic Resonance Imaging, 17, 337–342.
Georgiadis, P., Cavouras, D., Kalatzis, I., Daskalakis, A., Kagadis, G. C., Sifaki, K., Malamas, M., Nikiforidis, G., & Solomou, E. (2008). Improving brain tumor characterization on MRI by probabilistic neural networks and nonlinear transformation of textural features. Computer Methods and Programs in Biomedicine, 89, 24–32.
Griner, P. F., Mayewski, R. J., Mushlin, A. I., & Greenland, P. (1981). Selection and interpretation of diagnostic tests and procedures. Annals of Internal Medicine, 94, 555–600.
Akobeng, A. K. (2006). Understanding diagnostic tests 1: Sensitivity, specificity, and predictive values. Acta Paediatrica, 96, 338–341.
Chen, D. R., Chang, R. F., & Huang, Y. L. (1999). Computer-aided diagnosis applied to ultrasound of solid breast nodules by using neural networks. Radiology, 213, 407–412.
Garra, B. S., Krasner, H., Horii, S. C., Ascher, S., Muk, S. K., & Zeman, R. K. (1993). Improving the distinction between benign and malignant breast lesions: The value of sonographic texture analysis. Ultrasound Imaging, 15, 267–285.
Krupinski, E. A. (2004). Computer-aided detection in the clinical environment: Benefits and challenges for radiologists. Radiology, 231(1), 7–9.