CLASIFICACIÓN DE TUMORES CEREBRALES EN IMÁGENES DE RESONANCIA MAGNÉTICA MEDIANTE PARTICIONAMIENTO DE REGIONES Y BÚSQUEDA HEURÍSTICA (MAGNETIC RESONANCE IMAGE BASED BRAIN TUMOR CLASSIFICATION THROUGH REGION PARTITIONING AND HEURISTIC SEARCH)
Resumen
En este trabajo se presenta un clasificador tradicional de tres tipos de tumores cerebrales (meningioma, glioma y pituitario) basado en imágenes de resonancia magnética. Para conseguirlo se extrajeron características de intensidad, textura y forma a la región tumoral de interés (ROI), así como a la ROI aumentada y particionada en anillos; posteriormente los vectores de características fueron enviados a selectores de características cómo el índice discriminante de Fisher, métodos de empaquetamiento y un algoritmo genético para comparar el rendimiento con distintos clasificadores tradicionales. Los resultados obtenidos muestran que el uso de un algoritmo genético para la selección de características y búsqueda de parámetros brinda un mejor rendimiento, permitiendo mejorar la clasificación reportada en la literatura utilizando el mismo conjunto de datos y clasificadores tradicionales. Es decir, se obtiene una exactitud de clasificación de 92.35% utilizando una máquina de soporte vectorial, con características de la ROI y partición en anillos.
Palabras Clave: Clasificación de tumores cerebrales, Algoritmo genético, Aumento y particionamiento de región tumoral, Imagen de resonancia magnética.
Abstract
In this work a conventional classifier of three types of brain tumors (meningioma, glioma and pituitary) based on magnetic resonance images is presented. To achieve it, features of intensity, texture and shape were extracted from the tumor region of interest (ROI), as well as from the increased ROI and partitioned into rings; They were subsequently subjected to feature selectors such as Fisher's discriminant index, wrapper methods, and a genetic algorithm to compare performance with different conventional classifiers. The obtained results show that the use of a genetic algorithm for feature selection and parameter search provides better performance, allowing to improve those reported in the literature using the same data set and conventional classifiers. A classification accuracy of 92.35% is obtained with a support vector machine, using features extracted from the ROI and the augmented and partitioned ROI.
Keywords: Brain tumor classification, Genetic algorithm, Tumor augmented and partitioned region, Magnetic resonance imaging.
Texto completo:
560-577 PDFReferencias
Abiwinanda, N., Hanif, M., Hesaputra, S. T., Handayani, A., & Mengko, T. R. (2018). Brain Tumor Classification Using Convolutional Neural Network. World Congress on Medical Physics and Biomedical Engineering 2018, 183–189.
Afshar, P., Mohammadi, A., & Plataniotis, K. N. (2018). Brain Tumor Type Classification via Capsule Networks. 2018 25th IEEE International Conference on Image Processing (ICIP).
Angulakshmi, M. y Lakshmi Priya, G. (2017). Automated brain tumour segmentation techniques - a review. International Journal of Imaging Systems and Technology, 27(1), 66-77.
Betancourt, G. A. (2005). Las máquinas de soporte vectorial (SVMs). Scientia et technica, 11(27), 67-72.
Cheng, J., Huang, W., Cao, S., Yang, R., Yang, W., Yun, Z., Wang, Z., y Feng, Q. (2015). Enhanced performance of brain tumor classification via tumor region augmentation and partition. PLOS ONE, 10(10), e0140381.
Gou, J., Du, L., Zhang, Y., & Xiong, T. (2012). A new distance-weighted k-nearest neighbor classifier. Journal of Information & Computational Science, 9(6), 1429-1436.
Haralick, R. M., Shanmugam, K., y Dinstein, I. (1973). Textural features for image classification. IEEE Transactions on Systems, Man, and Cybernetics, SMC-3(6), 610-621.
Ismael, M. R., y Abdel-Qader, I. (2018). Brain tumor classification via statistical features and back-propagation neural network. In 2018 IEEE International Conference on Electro/Information Technology (EIT), 0252-0257.
Kim, H. C., y Ghahramani, Z. (2012). Bayesian classifier combination. In Artificial Intelligence and Statistics (pp. 619-627). PMLR.
Kohavi, R., y John, G. H. (1997). Wrappers for feature subset selection. Artificial Intelligence, 97(1–2), 273–324.
Kumar, M., Husain, M., Upreti, N., y Gupta, D. (2010). Genetic algorithm: Review and application. International Journal of Information Technology and Knowledge Management, 2(2), 451-454.
Kumar, T. S., Rashmi, K., Ramadoss, S., Sandhya, L. K., y Sangeetha, T. J. (2017). Brain tumor detection using SVM classifier. In 2017 Third International Conference on Sensing, Signal Processing and Security (ICSSS), 318-323. IEEE.
Kumar, V., y Minz, S. (2014). Feature selection: a literature review. SmartCR, 4(3), 211-229.
Lala, A., Gupta, J. K., y Shringirishi, M. (2013). Implementation on K-means Clustering and Fuzzy C-means Algorithm For Brain Tumor Segmentation. International Journal of Computer Engineering & Science, 3(1), 27-33.
Liu, Z. (2011). A method of SVM with normalization in intrusion detection. Procedia Environmental Sciences, 11, 256-262.
Mufarroha, F. A., Utaminingrum, F., & Mahmudy, W. F. (2017). Segmentation Algorithm to Determine Group for Hand Gesture Recognition. Journal of Telecommunication, Electronic and Computer Engineering (JTEC), 9(2-8), 13-17.
Qurat-Ul-Ain, G. L., Kazmi, S. B., Jaffar, M. A., y Mirza, A. M. (2010). Classification and segmentation of brain tumor using texture analysis. Recent advances in artificial intelligence, knowledge engineering and data bases, 147-155.
Rehman, A., Naz, S., Razzak, M. I., Akram, F., y Imran, M. (2020). A deep learning-based framework for automatic brain tumors classification using transfer learning. Circuits, Systems, and Signal Processing, 39(2), 757-775.
Rish, I. (2001). An empirical study of the naive Bayes classifier. In IJCAI 2001 workshop on empirical methods in artificial intelligence (Vol. 3, No. 22, pp. 41-46).
Rodriguez-Galiano, V. F., Ghimire, B., Rogan, J., Chica-Olmo, M., y Rigol-Sanchez, J. P. (2012). An assessment of the effectiveness of a random forest classifier for land-cover classification. ISPRS Journal of Photogrammetry and Remote Sensing, 67, 93-104.
Saman, S., y Narayanan, S. J. (2019). Survey on brain tumor segmentation and feature extraction of MR images. International Journal of Multimedia Information Retrieval, 8(2), 79-99.
Sharif, M., Tanvir, U., Munir, E. U., Khan, M. A., y Yasmin, M. (2018). Brain tumor segmentation and classification by improved binomial thresholding and multi-features selection. Journal of Ambient Intelligence and Humanized Computing, 1-20.
Zulpe, N., y Pawar, V. (2012). GLCM textural features for brain tumor classification. International Journal of Computer Science Issues (IJCSI), 9(3), 354-359.
URL de la licencia: https://creativecommons.org/licenses/by/3.0/deed.es
Pistas Educativas está bajo la Licencia Creative Commons Atribución 3.0 No portada. 
TECNOLÓGICO NACIONAL DE MÉXICO / INSTITUTO TECNOLÓGICO DE CELAYA
Antonio García Cubas Pte #600 esq. Av. Tecnológico, Celaya, Gto. México
Tel. 461 61 17575 Ext 5450 y 5146
pistaseducativas@itcelaya.edu.mx