浏览全部资源
扫码关注微信
Received：16 May 2018，
Revised：2018-7-24，
Published：16 January 2019
移动端阅览
目的
2
基于球谐函数与容斥映射算法向量化球面表面纹理与结节形状用以进行胸部CT图像肺结节良恶性判定。区别于基于深度学习解决肺结节良恶性筛查的方法，目前方法多集中于框架改进而忽略了数据预处理，文中所提方法旨在对球面纹理与结节形状进行向量表达，使其可以输入深度森林进行特征分类训练。
方法
2
首先采用辽宁中医药大学附属医院数据，通过3维重构获得3维肺结节图像。其次使用球谐函数与容斥映射算法在保留空间信息的同时将纹理以网格方式映射到标准球面上。再次使用网格-LBP与映射形变能量分别完成对球面纹理与结节形状信息的构建。最后提出一种基于网格的多粒度扫描方法对深度森林训练框架进行改进，并将向量化后的纹理和形状特征加入到改进的深度森林训练框架中进行实验验证。
结果
2
通过大量的实验结果验证，在准确率（ACC）、特异度（SPE）、敏感度（SEN）和受试者工作特征曲线下的面积（AUC）4个衡量指标下，本文方法具有优于现存先进方法的表现，其中ACC、SPE、SEN和AUC分别达到76.06%、69.46%、88.46%和0.84。
结论
2
基于球谐函数与容斥映射算法可成功地对肺结节表面和形状两个特征进行向量化并训练，不仅考虑了数据预处理，而且通过两个特征对肺结节良恶性检测的准确率要高于传统1个特征检测的结果，同时也为3维模型中特征的提取及向量化提供了一个有效的方法。
Objective
2
In this paper
the spherical surface texture and nodule shape are vectorized through spherical harmonics and repulsive mapping algorithm for the benign and malignant determination of pulmonary nodule in chest CT (computed tomography) images. The current methods of deep learning during benign and malignant screening of pulmonary nodules neglect data-preprocessing while focusing more on framework improvement. So far
the depth-learning method is mainly oriented to feature information
which can be vectored. In image-processing
two kinds of targets are mainly included in two-and three-dimensional processing. In two-dimensional processing
the existence of input data must be an equal-length problem. Considering that the obtained size of the pulmonary nodules is different
we must compress large-scale images in the input process and stretch the small-scale images
which will undoubtedly affect the quality of feature extraction and the final classification results. In the classification of CT nodules for the three-dimensional treatment of pulmonary nodules
the CT image angle is more stringent due to the different sizes of pulmonary nodules and the uncertainty of growth position
and the angle factors are uncontrollable during actual CT shooting. Hence
if we insist on the characteristics of the convolution channel
it is necessary to give priority to the solution. So we have to standardize different pulmonary nodules. Different from traditional pulmonary nodule classification method
the proposed method aims on how to vectorize the spherical texture and nodule shape to allow input of data to the depth forest for feature classification training.
Method
2
First
the three-dimensional pulmonary nodule images are produced by three-dimensional reconstruction of the data from the Affiliated Hospital of Liaoning University of Traditional Chinese Medicine. The data is divided into training and test set at 8:2 ratio. Second
the spherical harmonic function and the repulsive mapping algorithm are used to map the texture to the standard sphere in a mesh manner while preserving the spatial information. Third
the texture features of the pulmonary nodules are calculated by the method of mesh-LBP (local binary pattern) and vectorized by the construction ring. Then
the shape energy loss is constructed by the distance difference between the center of gravity and the central point of the pulmonary nodule during reconstruction of the three-dimensional pulmonary nodules
and the shape energy loss of the lung nodules is extracted and vectorized during rebuilding. Finally
a mesh-based multi-grain scanning method is proposed to improve the deep forest training framework by constructing multi-scale concentric ordered rings instead of traditional multi-grain scanning methods. The vectorized texture and shape features are added to the improved deep forest training framework for experimental verification.
Result
2
The pulmonary nodule data of this trial was mainly provided by the IRB (institutional review committee) of the Affiliated Hospital of Liaoning University of Traditional Chinese Medicine. The approval notice number is 2017111CS(KT)-040-01. According to the growth of pulmonary nodules
the dataset was divided into four types:independent standing lung nodules
and ground glass-shaped
vascular adhesion
and thoracic adhesion type pulmonary nodules. The benign and malignant lung nodules divided into five levels:1-benign
2-suspected benign
3-unknown
4-suspected malignant
and 5-malignant. A total of 7 326 three-dimensional lung nodules were extracted as the data set for this experiment. According to several experimental results
this algorithm have a better performance than the existing advanced methods (Variational Auto-Encoder
Faster Region Convolutional neural network
GcForest deep forest
Deep Convolutional Generative Adversarial Networks
and Extreme learning machine) under the following indices:accuracy (ACC)
specificity (SPE)
sensitivity (SEN)
and AUC (area under the receiver operating characteristic ROC curve) values. In the experiments
ACC
SPE
SEN
and AUC reached 76.06%
69.46%
88.46%
and 0.84
respectively. Accuracy indicates the proportion of the classifier's correct classification of positive and negative examples
which can measure the judgment of the classifier on the sample. Specificity refers to the true negative rate
which indicates the proportion of the classifier to the correct classification of the counterexample and can measure the ability of the classifier to identify the counterexample. Sensitivity refers to the true positive rate
which indicates the proportion of correct classification of positive examples and can measure the ability of the classifier to identify positive examples. It also indicates the area under the ROC curve. The ROC curve can dynamically display the classification result. The true positive rate (sensitivity) is the ordinate
whereas the false positive rate (1-specificity) is the abscissa. A value closer to the upper left corner indicates a stronger classification ability of the method. To accurately measure the ROC curve
it can be represented by the AUC value
which is generally between 0.5 and 1. A larger value indicates a stronger classification ability. Comparatively
the method used in this paper is sub optimal for the SEN value but the method used in this article maximizes SPE and ACC values.The AUC value is also sub optimal.
Conclusion
2
Lung cancer have one of the fastest growing morbidity and mortality rates worldwide and is a serious threat to people's health and life. The incidence of malignant pulmonary nodules is concealed. Many patients are often in the local late stage or even distant metastasis at the time of diagnosis
thus losing the chance for cure. Therefore
the early detection of malignant pulmonary nodules is crucial for the chance of successful cure. Based on the spherical harmonic function and the tolerance rejection mapping algorithm
the two surface and shape of pulmonary nodules can be successfully vectored and trained. Aside from considering data pretreatment
the accuracy of benign and malignant detection of pulmonary nodules is improved by these two features. Our proposed method can solve the problem of angle normalization by using a spherical space mesh to obtain the nodular information through a spherical space mesh. In addition
this method can also obtain different texture features and shape edge feature vectors as classification features by using the loop method. It is also an effective method for feature extraction and is vectorized in three-dimensional models.
Li M Y, Zhang N, Pan B, et al. Hyperspectral image classification based on deep forest and spectral-spatial cooperative feature[M]//Zhao Y, Kong X W, Taubman D. Image and Graphics. Cham: Springer, 2017: 325-336.[ DOI: 10.1007/978-3-319-71598-8_29 http://dx.doi.org/10.1007/978-3-319-71598-8_29 ]
Goodfellow I J, Pouget-Abadie J, Mirza M, et al. Generative adversarial nets[C]//Proceedings of the 27th International Conference on Neural Information Processing Systems. Montreal, Canada: MIT Press, 2014: 2672-2680. http://dl.acm.org/citation.cfm?id=2969125 .
Lenc K, Vedaldi A. R-CNN minusR[J]. eprint arXiv: 1506.06981, 2015. http://www.mendeley.com/catalog/rcnn-minus-r/ .
Ren S Q, He K M, Girshick R, et al. Faster R-CNN:towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 39(6):1137-1149.[DOI:10.1109/TPAMI.2016.2577031]
Courtney K K. Yolo:the year of the learning organization[J]. AALL Spectrum, 2012, 16(3):20-24.
Goodfellow, I J, Pouget-Abadie J, Mirza M, et al. Generativeadversarialnets[C]//Proceedings of International Conference on Neural Information Processing Systems. MIT Press, 2014: 2672-2680[ DOI: 10.1016/j.neucom.2014.01.064 http://dx.doi.org/10.1016/j.neucom.2014.01.064 ]
Liang Y, Li J P, Guo K, et al. A VEA encryption algorithm design based on two-dimensional logistic chaos mapping[J]. Computer Applications and Software, 2011, 28(10):111-113.
梁元, 李建平, 郭科, 等.一种基于二维Logistic混沌映射的VEA加密算法设计[J].计算机应用与软件, 2011, 28(10):111-113.
Chang J, Scherer S. Learning representations of emotional speech with deep convolutional generative adversarial networks[J]. arXiv preprint arXiv: 1705.02394, 2017.
Lin T Y, Dollár P, Girshick R, et al. Feature pyramid networks for object detection[C]//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, HI, USA: IEEE, 2017: 936-944.[ DOI: 10.1109/CVPR.2017.106 http://dx.doi.org/10.1109/CVPR.2017.106 ]
Ji S W, Xu W, Yang M, et al. 3D convolutional neural networks for human action recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(1):221-231.[DOI:10.1109/TPAMI.2012.59]
Wu M D. Research on 3D face reconization based on deep learning[D]. Harbin: Harbin Institute of Technology, 2016. http://www.cqvip.com/QK/88711X/201703/674297851.html .
吴梦蝶.基于深度学习的三维人脸识别方法研究[D].哈尔滨: 哈尔滨工业大学, 2016.
Kass M, Witkin A, Terzopoulos D. Snakes: active models[J]. Int. J. of Comp, 1987 Vision, vol. 1, pp. 321-331.
Fang Q Q, Boas D A. Tetrahedral mesh generation from volumetric binary and grayscale images[C]//2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro. Boston, MA, USA: IEEE, 2009: 1142-1145.[ DOI: 10.1109/ISBI.2009.5193259 http://dx.doi.org/10.1109/ISBI.2009.5193259 ]
Werghi N, Berretti S, del Bimbo A. The mesh-LBP:a framework for extracting local binary patterns from discrete manifolds[J]. IEEE Transactions on Image Processing, 2015, 24(1):220-235.[DOI:10.1109/TIP.2014.2370253]
Wang X Y, Han T X, Yan S C. An HOG-LBP human detector with partial occlusion handling[C]//Proceedings of 2009 IEEE 12th International Conference on Computer Vision. Kyoto, Japan: IEEE, 2009: 32-39.[ DOI: 10.1109/ICCV.2009.5459207 http://dx.doi.org/10.1109/ICCV.2009.5459207 ]
OjalaT, Pietikäinen M, Harwood I. A comparative study of texture measures with classification based on featured distributions[J]. Pattern Recognition, 1996, 29(1):51-59.[DOI:10.1016/0031-3203(95)00067-4]
Valery A, Rauch E F, Pofelski A, et al. Dealing with multiple grains in tem lamellae thickness for microstructure analysis using scanning precession electron diffraction[J]. Microscopy and Microanalysis, 2015, 21(S3):1243-1244.
Zhou Z H, Feng J. Deep Forest: towards an alternative to deep neural networks[C]//Proceedings of the 26th International Joint Conference on Artificial Intelligence, Nanjing, China, IJCAI, 2017: 3553-3559.[ DOI: 10.24963/ijcai.2017/497 http://dx.doi.org/10.24963/ijcai.2017/497 ]
相关文章
相关作者
相关机构
京公网安备11010802024621
