AUTOMATED DIAGNOSIS OF NORMAL AND PATHOLOGICAL CT BRAIN IMAGES FOR TISSUE CHARACTERIZATION USING DEEP LEARNING TECHNIQUES
Main Article Content
Keywords
Texture analysis, computed tomography (CT) scans, tissue characterization, CT imaging, artificial neural network (ANN), PCA, LDA, NDA and POE+ACC.
Abstract
Introduction: The mortality rate attributed to brain abnormalities has shown a significant upward trend in recent years. Early diagnosis is essential in decreasing mortality rates and to provide effective treatment. Texture analysis, consisting of a variety of mathematical techniques plays an important role in analyzing the spatial organization of different tissues and organs.
Objectives: The primary objective of the study was to systematically categorize and analyze brain abnormalities via quantitative texture analysis using computed tomography scans as a computer-aided diagnosis system
Methods: 138 diseased and 20 normal CT scan images of brain were used to make a comparison between normal and diseased brain. Classification of brain tissue was achieved through the ANN (one-training class) method with POE+ACC feature selection method and LDA, NDA and PCA feature reduction methods.
Results: ANN-1class shows accuracy of 92.37% to separate data into different groups. It was observed that PCA yields the best classification results while NDA have higher misclassification rates.
Conclusion: These findings suggest that integrating machine learning techniques offers a promising pathway for improving diagnostic accuracy and patient care in radiology. MaZda software successfully classifies different diseases into distinct clusters; differentiate them from each other as well as from the normal individual brain.
References
[2] N. Gosset, A. A. Bankier, and R. L. Eisenberg, "Tree-in-bud pattern," American Journal of Roentgenology, vol. 193, no. 6, pp. W472-W477, 2009.
[3] B. A. Skourt, A. El Hassani, and A. Majda, "Lung CT image segmentation using deep neural networks," Procedia Computer Science, vol. 127, pp. 109-113, 2018.
[4] G. Vara et al., "Assessment of Bone Mineral Density from Lumbosacral MRI: A Retrospective Study with Texture Analysis Radiomics," Applied Sciences, vol. 13, no. 10, p. 6305, 2023.
[5] M. Ahmad, M. S. Naweed, and M. Nisa, "Application of texture analysis in the assessment of chest radiographs," International Journal of Video & Image Processing and Network Security, vol. 9, no. 9, pp. 291-297, 2009.
[6] E. Scalco and G. Rizzo, "Texture analysis of medical images for radiotherapy applications," The British journal of radiology, vol. 90, no. 1070, p. 20160642, 2017.
[7] A. Depeursinge et al., "A classification framework for lung tissue categorization," in Medical Imaging 2008: PACS and Imaging Informatics, 2008, vol. 6919, pp. 77-88: SPIE.
[8] A. Jović, K. Brkić, and N. Bogunović, "A review of feature selection methods with applications," in 2015 38th international convention on information and communication technology, electronics and microelectronics (MIPRO), 2015, pp. 1200-1205: Ieee.
[9] L. I. Smith, "A tutorial on principal components analysis," 2002.
[10] M. Nisa, S. A. Buzdar, M. A. Javid, M. S. Ahmad, A. Ikhlaq, and S. Riaz, "Machine vision-based Statistical texture analysis techniques for characterization of liver tissues using CT images," JPMA. The Journal of the Pakistan Medical Association, vol. 72, no. 9, pp. 1760-1765, 2022.
[11] C. H. Park and H. Park, "Nonlinear discriminant analysis using kernel functions and the generalized singular value decomposition," SIAM journal on matrix analysis and applications, vol. 27, no. 1, pp. 87-102, 2005.
[12] M. Nisa, S. A. Buzdar, K. Khan, and M. S. Ahmad, "Deep convolutional neural network based analysis of liver tissues using computed tomography images," Symmetry, vol. 14, no. 2, p. 383, 2022.
[13] A. Padma and D. R. Sukanesh, "Automatic diagnosis of abnormal tumor region from brain computed tomography images using wavelet based statistical texture features," arXiv preprint arXiv:1109.1067, 2011.
[14] M. Singh, V. Garg, and P. Bhat, "Early detection of stroke using texture analysis," Indian Journal of Forensic Medicine & Toxicology, vol. 13, no. 3, 2019.
[15] A. Padma and N. Giridharan, "Performance comparison of texture feature analysis methods using PNN classifier for segmentation and classification of brain CT images," International Journal of Imaging Systems and Technology, vol. 26, no. 2, pp. 97-105, 2016.
Article Sidebar
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
All articles published in JPTCP are licensed under Copyright Creative Commons Attribution-NonCommercial 4.0 International License.
Amna Kaynat
Department of Physics, Government Sadiq College Women University, Bahawalpur, 63100, Pakistan
Mehrun Nisa
Senior Registrar, Bahawal Victoria Hospital, Bahawalpur, 63100, Pakistan,
Sania Liaqat
Department of Physics, Government Sadiq College Women University, Bahawalpur, 63100, Pakistan
Ayesha Fatima
Department of Physics, Government Sadiq College Women University, Bahawalpur, 63100, Pakistan
Hafiz Muhammad Amir Jamil
Senior Registrar, Bahawal Victoria Hospital, Bahawalpur, 63100, Pakistan,
Muhammad Saeed Ahmad
Department of Computer Science & Information Technology, Government Sadiq College Women University, Bahawalpur, 63100, Pakistan,
Fatima Hussain
Department of Physics, Government Sadiq College Women University, Bahawalpur, 63100, Pakistan
Malik Younas Imran
Medical Physics Department, Bahawalpur Institute of Nuclear Medicine & Oncology (BINO), Bahawalpur, Pakistan