基于深度迁移学习的大鼠肝纤维化诊断
|
摘要
针对肝纤维化临床诊断方法具有有创性和传统机器学习方法特征提取的不完全性的缺陷,本文采用深度迁移学习方法利用预训练的ResNet-18和VGGNet-11模型用于肝纤维化分期诊断.使用南方医科大学提供的大鼠肝纤维化核磁共振影像数据集进行不同程度的迁移训练.将两种模型在通过4种不同参数采集的核磁共振影像数据集上,分别使用6种网络迁移配置训练.实验结果表明,使用T1RHO-FA参数采集的核磁共振影像和采用VGGNet-11模型更能提高肝纤维化分期诊断的准确率.同时相对于ResNet-18模型,深度模型迁移学习方法能稳定提升VGGNet-11模型进行肝纤维化分期诊断的准确率和训练速度.
In view of the incompleteness of the clinical diagnosis method of liver fibrosis and the incompleteness of the feature extraction of traditional machine learning methods, by the deep transfer learning method, this study uses the pretrained ResNet-18 and VGGNet-11 models for the diagnosis of liver fibrosis. Different degrees of transfer training were performed using the rat liver fibrosis nuclear magnetic resonance image dataset provided by Southern Medical University.The two models were trained using six network migration configurations on the MRI image datasets collected by four different parameters. The experimental results show that the use of T1 RHO-FA parameters to acquire nuclear magnetic resonance images and the use of VGGNet-11 model can improve the accuracy of liver fibrosis staging diagnosis. At the same time, compared with the ResNet-18 model, the deep model migration learning method can stably improve the accuracy and training speed of the VGGNet-11 model for liver fibrosis staging diagnosis.
In view of the incompleteness of the clinical diagnosis method of liver fibrosis and the incompleteness of the feature extraction of traditional machine learning methods, by the deep transfer learning method, this study uses the pretrained ResNet-18 and VGGNet-11 models for the diagnosis of liver fibrosis. Different degrees of transfer training were performed using the rat liver fibrosis nuclear magnetic resonance image dataset provided by Southern Medical University.The two models were trained using six network migration configurations on the MRI image datasets collected by four different parameters. The experimental results show that the use of T1 RHO-FA parameters to acquire nuclear magnetic resonance images and the use of VGGNet-11 model can improve the accuracy of liver fibrosis staging diagnosis. At the same time, compared with the ResNet-18 model, the deep model migration learning method can stably improve the accuracy and training speed of the VGGNet-11 model for liver fibrosis staging diagnosis.
引文
1陆伦根,曾民德.肝纤维化的诊断和评估.中华肝脏病杂志,2005,13(8):603-604.[doi:10.3760/j.issn:1007-3418.2005.08.013]
2Brenner DA.Reversibility of Liver Fibrosis.Gastroenterology&Hepatology,2013,9(11):737-739.
3Lee YA,Wallace MC,Friedman SL.Pathobiology of liver fibrosis:A translational success story.Gut,2015,64(5):830-841.[doi:10.1136/gutjnl-2014-306842]
4夏璐,杨长青.肝纤维化治疗的研究进展.中华肝脏病杂志,2017,25(8):566-570.[doi:10.3760/cma.j.issn.1007-3418.2017.08.003]
5Sattar A,Khan AM,Anjum S,et al.Role of ultrasound guided fine needle aspiration cytology in diagnosis of space occupying lesions of liver.Journal of Ayub Medical College,Abbottabad:JAMC,2014,26(3):334-336.
6曾民德,王泰龄,王宝恩.肝纤维化诊断及疗效评估共识.肝脏,2002,7(2):147-148.[doi:10.3760/j.issn:1007-3418.2002.02.032]
7刘平,高云华,谭开彬,等.声学造影对早期肝纤维化诊断的实验研究.中国超声医学杂志,2002,18(12):897-899.[doi:10.3969/j.issn.1002-0101.2002.12.005]
8葛永祥,王丽辉.肝纤维化诊断新进展.医学综述,2011,17(19):2952-2955.[doi:10.3969/j.issn.1006-2084.2011.19.025]
9张弘,陶森,郝彧,等.国外肝纤维化诊断的研究热点分析.首都医科大学学报,2016,37(1):83-88.[doi:10.3969/j.issn.1006-7795.2016.01.016]
10Sarraf S,Tofighi G.Classification of alzheimer’s disease using fMRI data and deep learning convolutional neural networks.arXiv preprint arXiv:1603.08631,2016.
11Anthimopoulos M,Christodoulidis S,Ebner L,et al.Lung pattern classification for interstitial lung diseases using a deep convolutional neural network.IEEE Transactions on Medical Imaging,2016,35(5):1207-1216.[doi:10.1109/TMI.2016.2535865]
12孟丹.基于深度学习的图像分类方法研究[博士学位论文].上海:华东师范大学,2017.
13Wang K,Lu X,Zhou H,et al.Deep learning Radiomics of shear wave elastography significantly improved diagnostic performance for assessing liver fibrosis in chronic hepatitis B:A prospective multicentre study.Gut,2018:gutjnl-2018-316204.[doi:10.1136/gutjnl-2018-316204]
14Hinton GE,Osindero S,Teh Y.A fast learning algorithm for deep belief nets.Neural Computation,2006,18(7):1527-1554.[doi:10.1162/neco.2006.18.7.1527]
15Hubel DH,Wiesel TN.Receptive fields,binocular interaction and functional architecture in the cat’s visual cortex.The Journal of Physiology,1962,160(1):106-154.[doi:10.1113/jphysiol.1962.sp006837]
16Sermanet P,Eigen D,Zhang X,et al.OverFeat:Integrated recognition,localization and detection using convolutional networks.arXiv preprint arXiv:1312.6229,2013.
17Ioffe S,Szegedy C.Batch normalization:Accelerating deep network training by reducing internal covariate shift. Proceedings of the 32nd International Conference on Machine Learning.Lille,France.2015.448-456.
18Srivastava N,Hinton G,Krizhevsky A,et al.Dropout:A simple way to prevent neural networks from overfitting.The Journal of Machine Learning Research,2014,15(1):1929-1958.
19Pan SJ,Yang Q.A survey on transfer learning.IEEE Transactions on Knowledge and Data Engineering,2010,22(10):1345-1359.[doi:10.1109/TKDE.2009.191]
20He KM,Zhang XY,Ren SQ,et al.Deep residual learning for image recognition.Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition.Las Vegas,NV,USA.2016.770-778.
21Simonyan K,Zisserman A.Very deep convolutional networks for large-scale image recognition.arXiv preprint arXiv:1409.1556,2014.
2Brenner DA.Reversibility of Liver Fibrosis.Gastroenterology&Hepatology,2013,9(11):737-739.
3Lee YA,Wallace MC,Friedman SL.Pathobiology of liver fibrosis:A translational success story.Gut,2015,64(5):830-841.[doi:10.1136/gutjnl-2014-306842]
4夏璐,杨长青.肝纤维化治疗的研究进展.中华肝脏病杂志,2017,25(8):566-570.[doi:10.3760/cma.j.issn.1007-3418.2017.08.003]
5Sattar A,Khan AM,Anjum S,et al.Role of ultrasound guided fine needle aspiration cytology in diagnosis of space occupying lesions of liver.Journal of Ayub Medical College,Abbottabad:JAMC,2014,26(3):334-336.
6曾民德,王泰龄,王宝恩.肝纤维化诊断及疗效评估共识.肝脏,2002,7(2):147-148.[doi:10.3760/j.issn:1007-3418.2002.02.032]
7刘平,高云华,谭开彬,等.声学造影对早期肝纤维化诊断的实验研究.中国超声医学杂志,2002,18(12):897-899.[doi:10.3969/j.issn.1002-0101.2002.12.005]
8葛永祥,王丽辉.肝纤维化诊断新进展.医学综述,2011,17(19):2952-2955.[doi:10.3969/j.issn.1006-2084.2011.19.025]
9张弘,陶森,郝彧,等.国外肝纤维化诊断的研究热点分析.首都医科大学学报,2016,37(1):83-88.[doi:10.3969/j.issn.1006-7795.2016.01.016]
10Sarraf S,Tofighi G.Classification of alzheimer’s disease using fMRI data and deep learning convolutional neural networks.arXiv preprint arXiv:1603.08631,2016.
11Anthimopoulos M,Christodoulidis S,Ebner L,et al.Lung pattern classification for interstitial lung diseases using a deep convolutional neural network.IEEE Transactions on Medical Imaging,2016,35(5):1207-1216.[doi:10.1109/TMI.2016.2535865]
12孟丹.基于深度学习的图像分类方法研究[博士学位论文].上海:华东师范大学,2017.
13Wang K,Lu X,Zhou H,et al.Deep learning Radiomics of shear wave elastography significantly improved diagnostic performance for assessing liver fibrosis in chronic hepatitis B:A prospective multicentre study.Gut,2018:gutjnl-2018-316204.[doi:10.1136/gutjnl-2018-316204]
14Hinton GE,Osindero S,Teh Y.A fast learning algorithm for deep belief nets.Neural Computation,2006,18(7):1527-1554.[doi:10.1162/neco.2006.18.7.1527]
15Hubel DH,Wiesel TN.Receptive fields,binocular interaction and functional architecture in the cat’s visual cortex.The Journal of Physiology,1962,160(1):106-154.[doi:10.1113/jphysiol.1962.sp006837]
16Sermanet P,Eigen D,Zhang X,et al.OverFeat:Integrated recognition,localization and detection using convolutional networks.arXiv preprint arXiv:1312.6229,2013.
17Ioffe S,Szegedy C.Batch normalization:Accelerating deep network training by reducing internal covariate shift. Proceedings of the 32nd International Conference on Machine Learning.Lille,France.2015.448-456.
18Srivastava N,Hinton G,Krizhevsky A,et al.Dropout:A simple way to prevent neural networks from overfitting.The Journal of Machine Learning Research,2014,15(1):1929-1958.
19Pan SJ,Yang Q.A survey on transfer learning.IEEE Transactions on Knowledge and Data Engineering,2010,22(10):1345-1359.[doi:10.1109/TKDE.2009.191]
20He KM,Zhang XY,Ren SQ,et al.Deep residual learning for image recognition.Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition.Las Vegas,NV,USA.2016.770-778.
21Simonyan K,Zisserman A.Very deep convolutional networks for large-scale image recognition.arXiv preprint arXiv:1409.1556,2014.