浏览全部资源
扫码关注微信
Received：05 December 2019，
Revised：2020-1-19，
Accepted：26 January 2020，
Published：16 August 2020
移动端阅览
目的
2
肝肿瘤分类计算机辅助诊断技术在临床医学中具有重要意义，但样本缺乏、标注成本高及肝脏图像的敏感性等原因，限制了深度学习的分类潜能，使得肝肿瘤分类依然是医学图像处理领域中具有挑战性的任务。针对上述问题，本文提出了一种结合特征重用和注意力机制的肝肿瘤自动分类方法。
方法
2
利用特征重用模块对计算机断层扫描（computed tomography，CT）图像进行伪自然图像的预处理，复制经Hounsfield处理后的原通道信息，并通过数据增强扩充现有数据；引入基于注意力机制的特征提取模块，从全局和局部两个方面分别对原始数据进行加权处理，充分挖掘现有样本的高维语义特征；通过迁移学习的训练策略训练提出的网络模型，并使用Softmax分类器实现肝肿瘤的精准分类。
结果
2
在120个病人的514幅CT扫描切片上进行了综合实验。与基准方法相比，本文方法平均分类准确率为87.78%，提高了9.73%；与肝肿瘤分类算法相比，本文算法针对转移性肝腺癌、血管瘤、肝细胞癌及正常肝组织的分类召回率分别达到79.47%、79.67%、85.73%和98.31%；与主流分类模型相比，本文模型在多种评价指标中均表现优异，平均准确率、召回率、精确率、F1-score及AUC（area under ROC curve）分别为87.78%、84.43%、84.59%、84.44%和97.50%。消融实验表明了本文设计的有效性。
结论
2
本文方法能提高肝脏肿瘤的分类结果，可为临床诊断提供依据。
Objective
2
Liver
which is the largest organ in the abdomen
plays a vital role in the metabolism of the human body. Early detection
accurate diagnosis
and further treatment of liver disease are important and helpful to increase the chances for survival. Computed tomography (CT) is an effective tool to detect focal liver lesions due to its robust and accurate imaging techniques. Multiphase CT scans are generally divided into four phases
namely
noncontrast
arterial
portal
and delay. Radiological practice mainly relies on clinicians to analyze the liver. Physicians need to look back or forward in different phases. This task is time and energy consuming. Liver lesion detection also depends on experienced professional physicians. The identification and diagnosis of different liver lesions are challenging tasks for inexperienced doctors due to the similarity among CT images. Therefore
an effective computer-aided diagnosis (CAD) method for doctors should be designed and developed. Most existing research methods based on CAD are mainly deep learning. Convolutional neural network in deep learning is a data-driven approach
which means it requires much training data to make a model learn the good features for a specific classification. However
a large-scale and well-annotated dataset is extremely difficult to construct due to the lack of data and the cost of labeling data. In accordance with research and analysis
the current methods for liver lesion classification can be divided into two categories
namely
methods based on data and features. The former focuses on expanding data to increase data diversity. The latter mainly studies the way to modify a network to improve the classification ability. These methods have two major drawbacks. First
appearance invariance cannot be controlled when new samples of a specific class are generated. Second
the feature extraction of lesion region cannot be enhanced adaptively.
Method
2
To solve the above-mentioned problems and improve classification performance
this study proposes a novel method for liver tumor classification by combining feature reuse and attention mechanism. Our contributions are threefold. First
we design a feature reuse module to preprocess medical images. We limit the image intensity values of all CT scans to the range of[-100
400] Hounsfield unit to eliminate the influences of unrelated tissues or organs on the classification of liver lesions in CT images. A new spatial dimension is added to the 2D pixel matrix
and we concatenate three times for the pixel matrix along the new dimension to generate an efficient feature map with a pseudo-RGB channel. We conduct data augmentation of natural images (such as cut
flip
and fill) to expand medical images and increase their diversity. The feature reuse module not only can enhance the overall representation of original image features but also can effectively avoid the overfitting problem caused by a small sample. Second
we introduce the feature extraction module from two aspects
namely
local and global feature extraction. The local feature extraction block is a pixel-to-pixel modeling
which can enhance the extraction of lesion features by generating a weight factor for each pixel. This block mainly includes two branches
namely
trunk and weight. We feed any given feature map into two group convolution layers in the trunk branch to extract deep and high-dimensional features. It is also fed into the weight branch of encoder-decoder to generate a coefficient factor for each pixel. Lesion features are acquired adaptively by weighting the two branches. The global feature extraction block focuses on the relationship among channels. It can generate a weighting factor by pooling spatially to selectively recalibrate the importance of each feature channel. The ways of local and global feature extraction blocks are processed in parallel to fully mine semantic information with data. Third
we use the training strategy of transfer learning to train the proposed classification model. During training
we transfer the same network layer parameters of SENet(squeeze-and-excitation networks) as those of the proposed network model.
Result
2
We perform comprehensive experiments on 514 CT slices from 120 patients to evaluate the proposed method thoroughly. The average classification accuracy of the proposed method is 87.78%
which shows an improvement of 9.73% over the baseline model (SENet34). The classification recall rates of metastasis
hemangioma
hepatocellular carcinoma
and healthy liver tissues are 79.47%
79.67%
85.73%
and 98.31%
respectively
by using the algorithm in this paper. Compared with the current mainstream classification models
DensNet
SENet
SE_Resnext
CBAM
and SKNet
the proposed model is excellent in many evaluation indicators. The average accuracy
recall rate
precision
F1-score
and area under ROC curve(AUC) are 87.78%
84.43%
84.59%
84.44%
and 97.50%
respectively
by utilizing the proposed architecture. The ablation experiment proves the effectiveness of the proposed design.
Conclusion
2
The feature reuse module can preprocess medical images to alleviate the overfitting problems caused by lack of data. The feature extraction module based on attention mechanism can mine data features effectively. Our proposed method significantly improves the results of the classification of liver tumors in CT images. Thus
it provides a reliable basis for clinical diagnosis and makes computer-assisted diagnosis possible.
Ben-Cohen A, Klang E, Kerpel A, Konen E, Amitai M M and Greenspan H. 2018a. Fully convolutional network and sparsity-based dictionary learning for liver lesion detection in CT examinations. Neurocomputing, 275:1585-1594[DOI:10.1016/j.neucom.2017.10.001]
Ben-Cohen A, Mechrez R, Yedidia N and Greenspan H. 2018b. Improving CNN training using disentanglement for liver lesion classification in CT[EB/OL].[2019-11-01] . https://arxiv.org/pdf/1811.00501.pdf https://arxiv.org/pdf/1811.00501.pdf
Bray F, Ferlay J, Soerjomataram I, Siegel R L, Torre L A and Jemal A. 2018. Global cancer statistics 2018:GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. A Cancer Journal for Clinicians, 68(6):394-424[DOI:10.3322/caac.21492]
Chen Y F, Yue X D, Fujita H and Fu S Y. 2017. Three-way decision support for diagnosis on focal liver lesions. Knowledge-Based Systems, 127:85-99[DOI:10.1016/j.knosys.2017.04.008]
Christ P F, Elshaer M E A, Ettlinger F, Tatavarty S, Bickel M, Bilic P, Rempfler M, Armbruster M, Hofmann F, D'Anastasi M, Sommer W H, Ahmadi S A and Menze B H. 2016. Automatic liver and lesion segmentation in CT using cascaded fully convolutional neural networks and 3D conditional random fields//Proceedings of the 19th International Conference on Medical Image Computing and Computer-Assisted Intervention. Athens: Springer: 415-423[ DOI: 10.1007/978-3-319-46723-8_48 http://dx.doi.org/10.1007/978-3-319-46723-8_48 ]
Frid-Adar M, Diamant I, Klang E, Amitai M, Goldberger J and Greenspan H. 2018a. GAN-based synthetic medical image augmentation for increased CNN performance in liver lesion classification. Neurocomputing, 321:321-331[DOI:10.1016/j.neucom.2018.09.013]
Frid-Adar M, Klang E, Amitai M, Goldberger J and Greenspan H. 2018b. Synthetic data augmentation using GAN for improved liver lesion classification//Proceedings of the 15th IEEE International Symposium on Biomedical Imaging. Washington DC, USA: IEEE: 289-293[ DOI: 10.1109/ISBI.2018.8363576 http://dx.doi.org/10.1109/ISBI.2018.8363576 ]
Fu J, Liu J, Tian H J, Li Y, Bao Y J, Fang Z W and Lu H Q. 2019. Dual attention network for scene segmentation//Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach, CA, USA: IEEE: 3146-3149[ DOI: 10.1109/CVPR.2019.00326 http://dx.doi.org/10.1109/CVPR.2019.00326 ]
He K M, Zhang X Y, Ren S Q and Sun J. 2016. Deep residual learning for image recognition//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, NV, USA: IEEE: 770-778[ DOI: 10.1109/CVPR.2016.90 http://dx.doi.org/10.1109/CVPR.2016.90 ]
He T, Zhang Z, Zhang H, Zhang Z Y, Xie J Y and Li M. 2019. Bag of tricks for image classification with convolutional neural networks//Proceedings the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach, CA, USA: IEEE: 558-567[ DOI: 10.1109/CVPR.2019.00065 http://dx.doi.org/10.1109/CVPR.2019.00065 ]
Hu J, Shen L and Sun G. 2018. Squeeze-and-excitation networks//Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, USA: IEEE: 7132-7141[ DOI: 10.1109/CVPR.2018.00745 http://dx.doi.org/10.1109/CVPR.2018.00745 ]
Huang G, Liu Z, van der Maaten L and Weinberger K Q. 2017. Densely connected convolutional networks//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, USA: IEEE: 2261-2269[ DOI: 10.1109/CVPR.2017.243 http://dx.doi.org/10.1109/CVPR.2017.243 ]
Ji C, Huang X B, Cao W, Zhu Y C and Zhang Y. 2019. Fusion of deep learning and global-local features of the image salient region calculation. Journal of Computer-Aided Design and Computer Graphics, 31(10):1838-1846.
纪超, 黄新波, 曹雯, 朱永灿, 张烨. 2019.结合深度学习和全局-局部特征的图像显著区域计算.计算机辅助设计与图形学学报, 31(10):1838-1846[DOI:10.3724/SP.J.1089.2019.17544]
Kingma D and Ba J. 2015. Adam: a method for stochastic optimization//Proceedings of the 3rd International Conference on Learning Representations. San Diego, CA, USA: ICLR: 1-15
Krizhevsky A, Sutskever I and Hinton G E. 2017. ImageNet classification with deep convolutional neural networks. Communications of the ACM, 60(6):84-90[DOI:10.1145/3065386]
Li X, Hu X L and Yang J. 2019a. Spatial group-wise enhance: improving semantic feature learning in convolutional networks[EB/OL].[2019-05-25] . https://arxiv.org/pdf/1905.09646.pdf https://arxiv.org/pdf/1905.09646.pdf
Li X, Wang W H, Hu X L and Yan J. 2019b. Selective kernel networks//Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach, CA, USA: IEEE: 510-519[ DOI: 10.1109/CVPR.2019.00060 http://dx.doi.org/10.1109/CVPR.2019.00060 ]
Liang D, Lin L F, Hu H J, Zhang Q W, Chen Q Q, Lwamoto Y, Han X H and Chen Y W. 2018a. Residual convolutional neural networks with global and local pathways for classification of focal liver lesions//Proceedings of the 15th Pacific Rim International Conference on Artificial Intelligence. Nanjing, China: Springer: 617-628[ DOI: 10.1007/978-3-319-97304-3_47 http://dx.doi.org/10.1007/978-3-319-97304-3_47 ]
Liang D, Lin L F, Hu H J, Zhang Q W, Chen Q Q, Lwamoto Y, Han X H and Chen Y W. 2018b. Combining convolutional and recurrent neural networks for classification of focal liver lesions in multi-phase CT images//Proceedings of the 21st International Conference on Medical Image Computing and Computer Assisted Intervention. Granada, Spain: Springer: 666-675[ DOI: 10.1007/978-3-030-00934-2_74 http://dx.doi.org/10.1007/978-3-030-00934-2_74 ]
Litjens G, Kooi T, Bejnordi B E, Setio A A A, Ciompi F, Ghafoorian M, van der Laak J A W M, van Ginneken B and Sánchez C I. 2017. A survey on deep learning in medical image analysis. Medical Image Analysis, 42:60-88[DOI:10.1016/j.media.2017.07.005]
Liu Z, Zhang X L, Song Y Q, Zhu Y and Yuan D Q. 2018. Liver segmentation with improved U-Net and Morphsnakes algorithm. Journal of Image and Graphics, 23(8):1254-1262
刘哲, 张晓林, 宋余庆, 朱彦, 袁德琪. 2018.结合改进的U-Net和Morphsnakes的肝脏分割.中国图象图形学报, 23(8):1254-1262[DOI:10.11834/jig.170585]
Romero F P, Diler A, Bisson-Gregoire G, Turcotte S, Lapointe R, Vandenbroucke-Menu F, Tang A and Kadoury S. 2019. End-to-end discriminative deep network for liver lesion classification//Proceedings of the 16th IEEE International Symposium on Biomedical Imaging. Venice, Italy: IEEE: 1243-1246[ DOI: 10.1109/ISBI.2019.8759257 http://dx.doi.org/10.1109/ISBI.2019.8759257 ]
Szegedy C, Ioffe S, Vanhoucke V and Alemi A A. 2017. Inception-v4, inception-ResNet and the impact of residual connections on learning//Proceedings of the 31st AAAI Conference on Artificial Intelligence. San Francisco, CA, USA: AAAI: 4278-4284
Szegedy C, Vanhoucke V, Ioffe S, Shlens J and Wojna Z. 2016. Rethinking the inception architecture for computer vision//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, USA: IEEE: 2818-2826[ DOI: 10.1109/CVPR.2016.308 http://dx.doi.org/10.1109/CVPR.2016.308 ]
Woo S, Park J, Lee J Y and Kweon I S. 2018. CBAM: Convolutional block attention module//Proceedings of the 15th European Conference on Computer Vision. Munich, Germany: Springer: 3-19[ DOI: 10.1007/978-3-030-01234-2_1 http://dx.doi.org/10.1007/978-3-030-01234-2_1 ]
Yasaka K, Akai H, Abe O and Kiryu S. 2017. Deep learning with convolutional neural network for differentiation of liver masses at dynamic contrast-enhanced CT:a preliminary study. Radiology, 286(3):887-896[DOI:10.1148/radiol.2017170706]
相关文章
相关作者
相关机构
京公网安备11010802024621
