MRI的脑部肿瘤分割及其三维重建
|
摘要
脑部肿瘤精确分割和三维重建的研究对脑部肿瘤疾病的诊断具有重要意义.提出一种全自动的脑肿瘤分割方法,该方法首先利用人脑结构信息的对称性,通过区域生长法实现脑肿瘤的粗略分割,然后将粗分割区域作为初始水平集轮廓,利用改进的测地线活动轮廓(geodesic active contours, GAC)模型进一步精确分割.经实验分析可知,该模型具有良好的分割灰度不均匀的弱边缘能力.最后对分割出的脑部肿瘤序列图像进行面绘制重建及其可视化,以此为脑肿瘤研究提供更多维度的信息.
Analysis on the accurate segmentation and 3D reconstruction of brain tumors are important for the diagnosis of brain tumor diseases. This paper presents an automatic segmentation method for brain tumors. According to the symmetry of human brain structure information, a rough segmentation of brain tumor can firstly be realized by region growing method, and then taken as the initial level set contour for the further accurate segmentation by means of geodesic active contour(GAC) model. Experimental analysis shows that the model has good weak-edge ability on segmenting uneven gray scale. Finally,surface rendering, reconstruction and visualization of the segmented brain tumor sequence images are carried out to provide more dimensional information for brain tumor research.
Analysis on the accurate segmentation and 3D reconstruction of brain tumors are important for the diagnosis of brain tumor diseases. This paper presents an automatic segmentation method for brain tumors. According to the symmetry of human brain structure information, a rough segmentation of brain tumor can firstly be realized by region growing method, and then taken as the initial level set contour for the further accurate segmentation by means of geodesic active contour(GAC) model. Experimental analysis shows that the model has good weak-edge ability on segmenting uneven gray scale. Finally,surface rendering, reconstruction and visualization of the segmented brain tumor sequence images are carried out to provide more dimensional information for brain tumor research.
引文
[1] Joseph R P, Singh C S, Manikandan M. Brain tumor MRI image segmentation and detection in image processing[J]. Internation Journal of Research in Engineering and Technology, 2014,3(1):1-5.
[2]戴修斌,邓黄健,刘代富,刘可,周青蓉.利用群体CT计划图像的多任务前列腺自动分割[J].应用科学学报, 2017, 35(1):99-106.Dai X B, Deng H J, Liu D F, Liu K, Zhou Q R. Using the group image automatic segmentation of multitasking prostate CT plan[J]. Journal of Applied Sciences, 2017, 35(1):99-106.(in Chinese)
[3] Gupta M, Gayatri K S, Harika K. Brain tumor segmentation by integrating symmetric property with region growing approach[C]//IEEE India Conference. IEEE, 2015:1-5.
[4] Ben R A, Benzarti F, Amiri H. Segmentation of brain MRI using active contour model[J].International Journal of Imaging Systems&Technology, 2017, 27(1):3-11.
[5] Pydi V, Josyula S B. Detection of brain tumor using PCA with SVM[J]. International Journal of Research in Computer and Communication Technology, 2015, 4(8):535-539.
[6] Bendib M M, Merouani H F, Diaba F. Automatic segmentation of brain MRI through stationary wavelet transform and random forests[J]. Pattern Analysis&Applications, 2015,18(4):829-843.
[7] Pereira S, Pinto A, Alves V, Silva C A. Brain tumor segmentation using convolutional neural networks in MRI images[J]. IEEE Transactions on Medical Imaging, 2016, 35(5):1240-1251.
[8] Sustersic T, Peulic M, Filipovic N, Peulic A. Application of active contours method in assessment of optimal approach trajectory to brain tumor[C]//International Conference on Bioinformatics and Bioengineering. IEEE, 2015:1-4.
[9] Dodin P, Martel-Pelletier J, Pelletier J P, Abram F. A fully automated human knee3D MRI bone segmentation using the ray casting technique[J]. Medical&Biological Engineering&Computing, 2011, 49(12):1413-1424.
[10] Neves A M A, Ferreira A J M, Carrera E, Roque C M C, Cinefra M. A quasi-3D sinusoidal shear deformation theory for the static and free vibration analysis of functionally graded plates[J]. Composites Part B Engineering, 2012, 43(2):711-725.
[11]刘思奇,张来峰,范立成,盛小明.基于医学图像序列面绘制的骨组织快速成型方法[J].计算机应用, 2017, 37(5):1456-1459.Liu S Q, Zhang L F, Fan L C, Sheng X M. Based on medical image sequence of bone tissue rapid prototyping method[J]. Journal of Computer Applications, 2017, 37(5):1456-1459.(in Chinese)
[12] Gai L I. The comparison research of MC algorithm and MT algorithm[J]. Modern Computer,2007, 251:19-23.
[13]李丹仪,李卫锋,廖庆敏.基于对称信息和主动轮廓模型的脑肿瘤分割系统[J].清华大学学报(自然科学版), 2013(7):995-1000.Li D Y, Li W F, Liao Q M. Based on the asymmetric information and active contour model of brain tumor segmentation system[J]. Journal of Tsinghua University(Science and Technology),2013(7):995-1000.(in Chinese)
[14] Zabir I, Paul S, Rayhan M A, Sarker T, Fattah A S, Shahnaz C. Automatic brain tumor detection and segmentation from multi-modal MRI images based on region growing and level set evolution[C]//IEEE International Wie Conference on Electrical and Computer Engineering.IEEE, 2016:503-506.
[15] Caselles V, Kimmel R, Sapiro G. Geodesic active contours[J]. International Journal of Computer Vision, 1997, 22(1):61-79.
[2]戴修斌,邓黄健,刘代富,刘可,周青蓉.利用群体CT计划图像的多任务前列腺自动分割[J].应用科学学报, 2017, 35(1):99-106.Dai X B, Deng H J, Liu D F, Liu K, Zhou Q R. Using the group image automatic segmentation of multitasking prostate CT plan[J]. Journal of Applied Sciences, 2017, 35(1):99-106.(in Chinese)
[3] Gupta M, Gayatri K S, Harika K. Brain tumor segmentation by integrating symmetric property with region growing approach[C]//IEEE India Conference. IEEE, 2015:1-5.
[4] Ben R A, Benzarti F, Amiri H. Segmentation of brain MRI using active contour model[J].International Journal of Imaging Systems&Technology, 2017, 27(1):3-11.
[5] Pydi V, Josyula S B. Detection of brain tumor using PCA with SVM[J]. International Journal of Research in Computer and Communication Technology, 2015, 4(8):535-539.
[6] Bendib M M, Merouani H F, Diaba F. Automatic segmentation of brain MRI through stationary wavelet transform and random forests[J]. Pattern Analysis&Applications, 2015,18(4):829-843.
[7] Pereira S, Pinto A, Alves V, Silva C A. Brain tumor segmentation using convolutional neural networks in MRI images[J]. IEEE Transactions on Medical Imaging, 2016, 35(5):1240-1251.
[8] Sustersic T, Peulic M, Filipovic N, Peulic A. Application of active contours method in assessment of optimal approach trajectory to brain tumor[C]//International Conference on Bioinformatics and Bioengineering. IEEE, 2015:1-4.
[9] Dodin P, Martel-Pelletier J, Pelletier J P, Abram F. A fully automated human knee3D MRI bone segmentation using the ray casting technique[J]. Medical&Biological Engineering&Computing, 2011, 49(12):1413-1424.
[10] Neves A M A, Ferreira A J M, Carrera E, Roque C M C, Cinefra M. A quasi-3D sinusoidal shear deformation theory for the static and free vibration analysis of functionally graded plates[J]. Composites Part B Engineering, 2012, 43(2):711-725.
[11]刘思奇,张来峰,范立成,盛小明.基于医学图像序列面绘制的骨组织快速成型方法[J].计算机应用, 2017, 37(5):1456-1459.Liu S Q, Zhang L F, Fan L C, Sheng X M. Based on medical image sequence of bone tissue rapid prototyping method[J]. Journal of Computer Applications, 2017, 37(5):1456-1459.(in Chinese)
[12] Gai L I. The comparison research of MC algorithm and MT algorithm[J]. Modern Computer,2007, 251:19-23.
[13]李丹仪,李卫锋,廖庆敏.基于对称信息和主动轮廓模型的脑肿瘤分割系统[J].清华大学学报(自然科学版), 2013(7):995-1000.Li D Y, Li W F, Liao Q M. Based on the asymmetric information and active contour model of brain tumor segmentation system[J]. Journal of Tsinghua University(Science and Technology),2013(7):995-1000.(in Chinese)
[14] Zabir I, Paul S, Rayhan M A, Sarker T, Fattah A S, Shahnaz C. Automatic brain tumor detection and segmentation from multi-modal MRI images based on region growing and level set evolution[C]//IEEE International Wie Conference on Electrical and Computer Engineering.IEEE, 2016:503-506.
[15] Caselles V, Kimmel R, Sapiro G. Geodesic active contours[J]. International Journal of Computer Vision, 1997, 22(1):61-79.