基于WRN-PPNet的多模态MRI脑肿瘤全自动分割
|
摘要
多模态磁共振成像脑肿瘤图像存在灰度不均匀、组织类别多样等缺陷,导致脑肿瘤分割难度大、精度低,且已有脑肿瘤分割算法多为半自动分割算法。为此,建立一种端到端的全自动脑肿瘤分割模型。对脑肿瘤三维图像切片化以获得大量二维切片图像,将训练集的切片图像标准化后直接输入该分割模型,然后用训练好的模型正确分割出脑部神经胶质瘤区域,并采用Dice系数、灵敏度系数以及阳性预测率系数评估模型的分割性能。实验结果表明,该模型操作简单,鲁棒性较好,3个评估指标值分别能够达到0. 94、0. 92和0. 97。
Multimodal Magnetic Resonance Imaging( MRI) brain tumors image has many defects,such as uneven gray level,diverse tissue types,which lead to the difficulty and low accuracy of brain tumors segmentation,and most of the existing brain tumors segmentation algorithms are semi-automatic segmentation algorithms. To solve this problem,an end-toend automatic brain tumors segmentation model is established. A large number of two-dimensional slice images are obtained by slicing the three-dimensional images of brain tumors. The slice images of the training set are normalized and then directly input into the segmentation model. The brain glioma region is correctly segmented by the trained model. The segmentation of the model is evaluated by Dice coefficient,sensitivity coefficient and Positive Predictive Value( PPV) coefficient.Experimental results show that the proposed model is easy to operate and has good robustness,the three evaluation indexes can reach 0. 94,0. 92 and 0. 97 respectively.
Multimodal Magnetic Resonance Imaging( MRI) brain tumors image has many defects,such as uneven gray level,diverse tissue types,which lead to the difficulty and low accuracy of brain tumors segmentation,and most of the existing brain tumors segmentation algorithms are semi-automatic segmentation algorithms. To solve this problem,an end-toend automatic brain tumors segmentation model is established. A large number of two-dimensional slice images are obtained by slicing the three-dimensional images of brain tumors. The slice images of the training set are normalized and then directly input into the segmentation model. The brain glioma region is correctly segmented by the trained model. The segmentation of the model is evaluated by Dice coefficient,sensitivity coefficient and Positive Predictive Value( PPV) coefficient.Experimental results show that the proposed model is easy to operate and has good robustness,the three evaluation indexes can reach 0. 94,0. 92 and 0. 97 respectively.
引文
[1]SCHWARTZBAUM J A,FISHER J L,ALDAPE K D,et al.Epidemiology and molecular pathology of glioma[J].Nat Clin Pract Neurol,2006,2(9):494-503.
[2]YAMAHARA T,NUMA Y,OISHI T,et al.Morphological and flow cytometric analysis of cell infiltration in glioblastoma:a comparison of autopsy brain and neuro-imaging[J].Brain Tumor Pathology,2010,27(2):81-87.
[3]JONES T L,BYRNES T J,YANG G,et al.Brain tumor classification using the diffusion tensor image segmentation(D-SEG)technique[J].Neuro Oncology,2015,17(3):466-476.
[4]李传朋,秦品乐,张晋京.基于深度卷积神经网络的图像去噪研究[J].计算机工程,2017,43(3):253-260.
[5]王盛玉,曾碧卿,胡翩翩.基于卷积神经网络参数优化的中文情感分析[J].计算机工程,2017,43(8):200-207.
[6]易生,梁华刚,茹锋.基于多列深度3D卷积神经网络的手势识别[J].计算机工程,2017,43(8):243-248.
[7]HAVAEI M,DAVY A,WARDE-FARLEY D,et al.Brain tumor segmentation with deep neural networks[J].Medical Image Analysis,2017,35:18-31.
[8]PEREIRA S,PINTO A,ALVES V,et al.Braintumor segmentation using convolutional neural networks in MRIimages[J].IEEE Transactions on Medical Imaging,2016,35(5):1240-1251.
[9]李健,罗蔓,罗晓,等.基于多尺度卷积神经网络的磁共振成像脑肿瘤分割研究[J].中国医学装备,2016(2):25-28.
[10]师冬丽,李锵,关欣.结合卷积神经网络和模糊系统的脑肿瘤分割[J].计算机科学与探索,2018,12(4):608-617.
[11]LONG J,SHELHAMER E,DARRELL T.Fully convolutional networks for semantic segmentation[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEEComputer Society,2015:3431-3440.
[12]ZHAO H,SHI J,QI X,et al.Pyramid scene parsing network[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEEComputer Society,2017:6230-6239.
[13]HE K,ZHANG X,REN S,et al.Deep residual learning for image recognition[C]//Proceedings of 2016 IEEEConference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Computer Society,2016:770-778.
[14]ZAGORUYKO S,KOMODAKIS N.Wide residual networks[EB/OL].[2018-01-01].http://www.deeplearningitalia.com/wp-content/uploads/2017/12/Dropbo x_Wide-Residual-Nets.pdf.
[15]CHANG P.Fully convolutional neural networks with hyperlocal features for brain tumor segmentation[EB/OL].[2017-12-20].https://www.cbica.upenn.edu/sbia/Spyridon.Bakas/MICCAI_Bra TS/MICCAI_Bra TS_2016_proce edings.pdf.
[16]LYKSBORG M,PUONTI O,AGN M,et al.An ensemble of 2D convolutional neural networks for tumor segmentation[M]//RICHARDS J A.Remote sensing digital image analysis.Berlin,Germany:Springer,2006.
[17]KISTLER M,BONARETTI S,PFAHRER M,et al.The virtual skeleton database:an open access repository for biomedical research and collaboration[J].Journal of Medical Internet Research,2013,15(11):e245.
[2]YAMAHARA T,NUMA Y,OISHI T,et al.Morphological and flow cytometric analysis of cell infiltration in glioblastoma:a comparison of autopsy brain and neuro-imaging[J].Brain Tumor Pathology,2010,27(2):81-87.
[3]JONES T L,BYRNES T J,YANG G,et al.Brain tumor classification using the diffusion tensor image segmentation(D-SEG)technique[J].Neuro Oncology,2015,17(3):466-476.
[4]李传朋,秦品乐,张晋京.基于深度卷积神经网络的图像去噪研究[J].计算机工程,2017,43(3):253-260.
[5]王盛玉,曾碧卿,胡翩翩.基于卷积神经网络参数优化的中文情感分析[J].计算机工程,2017,43(8):200-207.
[6]易生,梁华刚,茹锋.基于多列深度3D卷积神经网络的手势识别[J].计算机工程,2017,43(8):243-248.
[7]HAVAEI M,DAVY A,WARDE-FARLEY D,et al.Brain tumor segmentation with deep neural networks[J].Medical Image Analysis,2017,35:18-31.
[8]PEREIRA S,PINTO A,ALVES V,et al.Braintumor segmentation using convolutional neural networks in MRIimages[J].IEEE Transactions on Medical Imaging,2016,35(5):1240-1251.
[9]李健,罗蔓,罗晓,等.基于多尺度卷积神经网络的磁共振成像脑肿瘤分割研究[J].中国医学装备,2016(2):25-28.
[10]师冬丽,李锵,关欣.结合卷积神经网络和模糊系统的脑肿瘤分割[J].计算机科学与探索,2018,12(4):608-617.
[11]LONG J,SHELHAMER E,DARRELL T.Fully convolutional networks for semantic segmentation[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEEComputer Society,2015:3431-3440.
[12]ZHAO H,SHI J,QI X,et al.Pyramid scene parsing network[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEEComputer Society,2017:6230-6239.
[13]HE K,ZHANG X,REN S,et al.Deep residual learning for image recognition[C]//Proceedings of 2016 IEEEConference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Computer Society,2016:770-778.
[14]ZAGORUYKO S,KOMODAKIS N.Wide residual networks[EB/OL].[2018-01-01].http://www.deeplearningitalia.com/wp-content/uploads/2017/12/Dropbo x_Wide-Residual-Nets.pdf.
[15]CHANG P.Fully convolutional neural networks with hyperlocal features for brain tumor segmentation[EB/OL].[2017-12-20].https://www.cbica.upenn.edu/sbia/Spyridon.Bakas/MICCAI_Bra TS/MICCAI_Bra TS_2016_proce edings.pdf.
[16]LYKSBORG M,PUONTI O,AGN M,et al.An ensemble of 2D convolutional neural networks for tumor segmentation[M]//RICHARDS J A.Remote sensing digital image analysis.Berlin,Germany:Springer,2006.
[17]KISTLER M,BONARETTI S,PFAHRER M,et al.The virtual skeleton database:an open access repository for biomedical research and collaboration[J].Journal of Medical Internet Research,2013,15(11):e245.