Reconocimiento de materias gris y blanca en segmentación de imágenes cerebrales utilizando un perceptrón multicapa y superpíxeles
Bryan Louis Medina, Julio Cesar Martinez-Romo, Francisco Javier Luna-Rosas, David Asael Gutierrez-Hernandez, Miguel Mora-Gonzalez
Descargar artículo
Información básica
Volumen
V57 - N1 / 2024 Especial: RIAO OPTILAS 2023
Referencia
51169
DOI
http://dx.doi.org/10.7149/OPA.57.1.51169
Idioma
English
Etiquetas
Base de datos de imágenes cerebrales, segmentación de imágenes, k-medias, imágenes por resonancia magnética, perceptrón multicapa, superpíxeles
Resumen
La correcta segmentación de los tejidos cerebrales en imágenes de resonancia magnética ayuda al desarrollo de diagnósticos de mayor precisión. Se propone un modelo que permite la segmentación de tejidos blandos en imágenes de resonancia magnética cerebral, donde se discriminan entre sustancia gris, sustancia blanca y fondo de la imagen. Para segmentar las imágenes se utilizó el algoritmo de agrupamiento iterativo lineal simple de superpíxeles, además de utilizar una red neuronal artificial del tipo perceptrón multicapa para la clasificación de las partes blandas de las imágenes. Para medir la calidad de la clasificación en la segmentación se utilizó el coeficiente de Sorensen-Dice, así como también se compararon los resultados de la metodología propuesta contra el algoritmo k-medias. La metodología propuesta alcanzó un coeficiente de Sorensen-Dice de 0.921 y 0.963, para sustancia gris y blanca, respectivamente, para imágenes con 0% de ruido, mientras que las k-medias solo alcanzaron 0.911 y 0.958 en las mismas condiciones. En imágenes con un 9% de ruido, la diferencia fue aún mayor con una clasificación entre sustancia gris y blanca de 0.863 y 0.937, respectivamente, mientras que para el algoritmo k-medias disminuyó a 0.805 y 0.901, respectivamente. Cuando la imagen se divide en superpíxeles, la estructura de las regiones del cerebro se conserva mejor que otras metodologías como k-medias. Por tanto, la red neuronal trabaja individualmente en la clasificación con cada superpíxel. Se demostró que una red de perceptrones multicapa se puede utilizar como clasificador de precisión del tejido cerebral en imágenes de resonancia magnética
Referencias
C.M. Bishop, Pattern recognition and machine learning, Springer (2006).
J.D. Bronzino, Biomedical Engineering Handbook Vol. 2, 2nd ed., CRC Press LLC (2000).
R.C. Gonzalez & R.E. Woods, Digital image processing, 4th ed., Pearson (2018).
S. Warfield et al., “Automatic identification of gray matter structures from MRI to improve the segmentation of white matter lesions,” J. Image Guid. Surg. 1(6), 326-38 (1995).
V. Le Thuc et al., “Method to segment the brain automatically applied to a magnetic resonance imaging sequence,” Opt. Eng. 42(7), 1976-1992 (2003).
H.J. Huppertz et al., “Enhanced visualization of blurred gray–white matter junctions in focal cortical dysplasia by voxel-based 3D MRI analysis,” Epilepsy Research 67(1-2), 35-50 (2005).
E.A. Zanaty, “Determination of gray matter (GM) and white matter (WM) volume in brain magnetic resonance images (MRI),” International Journal of Computer Applications 45(3), 16-22 (2012).
S. Amiri et al., “An Automated MR Image Segmentation System Using Multi-layer Perceptron Neural Network,” J. Biomed. Phys. Eng. 3(4), 115-122 (2013).
S. Jia and C. Zhang, "Fast and robust image segmentation using an superpixel based FCM algorithm," Proc. of International Conference on Image Processing (ICIP), 947-951 (2014).
Y. Kong, Y. Deng and Q. Dai, "Discriminative Clustering and Feature Selection for Brain MRI Segmentation," IEEE Signal Processing Letters 22(5), 573-577 (2015).
P.E. Adjei et al., “Brain Tumor Segmentation using SLIC Superpixels and Optimized Thresholding Algorithm,” International Journal of Computer Applications 181(20), 1-5 (2018).
M.F. Rachmadi et al., “Segmentation of white matter hyperintensities using convolutional neural networks with global spatial information in routine clinical brain MRI with none or mild vascular pathology,” Comput. Med. Imaging Graph. 66, 28-43 (2018).
T. Imtiaz et al., "Automated Brain Tumor Segmentation Based on Multi-Planar Superpixel Level Features Extracted From 3D MR Images," IEEE Access 8, 25335-25349 (2020).
G. Uçar & E. Dandıl, “Automatic detection of white matter hyperintensities via mask region-based convolutional neural networks using magnetic resonance images,” Chapter 8 in Deep Learning for Medical Applications with Unique Data, D. Gupta, U. Kose, A. Khanna, Valentina Emilia Balas, Eds., Academic Press (2022).
M. Singh et al., "Segmentation of functional MRI by K-means clustering," IEEE Transactions on Nuclear Science 43(3), 2030-2036 (1996).
A. Afifi, “A Hybrid Technique Based on Combining Fuzzy K-means Clustering and Region Growing for Improving Gray Matter and White Matter Segmentation,” International Journal of Advanced Computer Science and Applications 3(7), 030716 (2012).
K. Somasundaram and T. Genish, “Binarization of MRI with Intensity Inhomogeneity using K-Means Clustering for Segmenting Hippocampus,” The International Journal of Multimedia & Its Applications 5, 11-19 (2013).
J. Liu and L. Guo, "A New Brain MRI Image Segmentation Strategy Based on K-means Clustering and SVM," Proc. of 7th International Conference on Intelligent Human-Machine Systems and Cybernetics, 270-273 (2015).
J. Liu and L. Guo, "An Improved K-means Algorithm for Brain MRI Image Segmentation," Proc. of 3rd International Conference on Mechatronics, Robotics and Automation, 1087-1090 (2015).
V. Deepa, C.C. Benson & V.L. Lajish, “Gray Matter and White Matter Segmentation from MRI Brain Images Using Clustering Methods,” International Research Journal of Engineering and Technology 2(8), 913-921 (2015).
A. Naveen and T. Velmurugan, “Identification of Calcification in MRI Brain Images by k-Means Algorithm,” Indian Journal of Science and Technology 8(29), 1-7 (2015).
I. Mehidi, D.E. Chouaib Belkhiat and D. Jabri, "An Improved Clustering Method Based on K-Means Algorithm for MRI Brain Tumor Segmentation," Proc. of 6th International Conference on Image and Signal Processing and their Applications (ISPA), 1-6 (2019).
J. Qiao et al., “Data on MRI brain lesion segmentation using K-means and Gaussian Mixture Model-Expectation Maximization,” Data in Brief 27, 104628 (2019).
G.R. Nitta et al., “Dominant gray level based K-means algorithm for MRI images,” Health Technol. 10, 281–287 (2020).
J.S.U. Rahman, S.K. Selvaperumal & R. Logeswaran, “Hybrid method of MRI brain segmentation using fuzzy k-means,” European Journal of Molecular & Clinical Medicine 7(11), 9144-9155 (2021).
P.H. Bandeira Diniz et al., “Detection of white matter lesion regions in MRI using SLIC0 and convolutional neural network,” Computer Methods and Programs in Biomedicine 167, 49-63 (2018).
J.V. Manjón et al., “MRI white matter lesion segmentation using an ensemble of neural networks and overcomplete patch-based voting,” Computerized Medical Imaging and Graphics 69, 43-51 (2018).
P. Moeskops et al., “Evaluation of a deep learning approach for the segmentation of brain tissues and white matter hyperintensities of presumed vascular origin in MRI,” NeuroImage: Clinical 17, 251– 262 (2018).
R. Balakrishnan, M.C. Valdés Hernández, A.J. Farrall, “Automatic segmentation of white matter hyperintensities from brain magnetic resonance images in the era of deep learning and big data – A systematic review,” Computerized Medical Imaging and Graphics 88, 101867 (2021).
J. Brownlee, Deep learning for time series forecasting: predict the future with MLPs, CNNs and LSTMs in Python, Machine Learning Mastery (2018).
C.M. Bishop, Neural networks for pattern recognition, Oxford University Press (1995).
W.K. Pratt, Digital image processing, 3th ed., John Wiley & Sons, Inc. (2001).
USCViterbi School of Engineering, image dataset Volume 3: Miscellaneous https://sipi.usc.edu/database/database.php?volume=misc&image=10#top
R. Achanta et al., “SLIC superpixels compared to state-of-the-art superpixel methods,” IEEE transactions on pattern analysis and machine intelligence 34(11), 2274-2282 (2012).
C.A. Cocosco et al., “BrainWeb: Online Interface to a 3D MRI Simulated Brain Database,” Proc. of 3rd International Conference on Functional Mapping of the Human Brain 5(4), part 2/4, S425 (1997).
PyPI. Deepbrain 0.1, (2018)https://pypi.org/project/deepbrain
B. Goyal et al., “Noise issues prevailing in various types of medical images,” Biomedical & Pharmacology Journal 11(3), 1227-1237 (2018).
T.A. Sorensen, “A method of establishing groups of equal amplitude in plant sociology based on similarity of species content and its application to analyses of the vegetation on Danish commons,” Biologiske Skrifter (Nr4), 1-34 (1948).
M.P.R. Zamudio Arteaga, Segmentación de imágenes de resonancia magnética mediante operaciones morfológicas y campos markovianos de medidas gaussianas, BSc thesis, Fac. Science, Univ. A. San Luis Potosí, Mexico (2018).
D.P. Kingma and J. Ba, “Adam: A Method for Stochastic Optimization,” https://arxiv.org/abs/1412.6980