To address the problem of inadequate feature extraction and high feature dimension when CT modal medical images are trained with convolutional neural networks, this paper proposes a method for lung tumor identification using Multi-scale DenseNet-NSCR based on non-negative sparse collaborative representation classification by fusing multi-scale images. First, the parameters of the pre-trained dense neural network model are initialized using migration learning; the lung images are then pre-processed to extract multi-scale lesion ROI. Subsequently, the DenseNet is trained using a multi-scale CT dataset to extract feature vectors at the full connection layer. To address the problem of the high dimensionality of the fused features, a non-negative, sparse, and collaborative representation (NSCR) classifier is used to represent the feature vector and solve the coefficient matrix; the residual similarity is then used for classification. Finally, a comparison test is conducted with the AlexNet, DenseNetNetNet-201 model, and a combination model of three classification algorithms (SVM, SRC, NSCR). The experimental results show that Multiscale-DenseNet-NSCR classification is better than other models; all evaluation indexes such as specificity and sensitivity are higher, and the method has better robustness and generalization ability.
关键词
密集神经网络多尺度医学图像迁移学习NSCR算法
Keywords
DenseNetmulti-scale medical imagetransfer learningnon-negative, sparse, collaborative representation classifier
YANG J, ZHOU T, GUO L F, et al. Lung tumor image recognition algorithm based on cuckoo search and deep belief network[J]. Journal of Computer Applications, 2018, 38(11): 3225-3230.(in Chinese)
SIEGEL R L, MILLER K D, JEMAL A. Cancer statistics, 2019[J]. CA: A Cancer Journal for Clinicians, 2019, 69(1): 7-34.
WU L, LYU G Q, ZHAO CH, et al. CT image super-resolution reconstruction based on multi-scale residual network[J]. Chinese Journal of Liquid Crystals and Displays, 2019, 34(10): 1006-1012.(in Chinese)
FAN L L, ZHAO H W, ZHAO H Y, et al. Survey of target detection based on deep convolutional neural networks[J]. Opt. Precision Eng., 2020, 28(5): 1152-1164.(in Chinese)
TIAN J X, LIU G C, GU SH SH, et al. Deep learning in medical image analysis and its challenges[J]. Acta Automatica Sinica, 2018, 44(3): 401-424.(in Chinese)
HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition[C]. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2730,2016, Las Vegas, NV, USA. IEEE, 2016: 770-778.
HUANG G, LIU Z, MAATEN LVAN DER, et al. Densely connected convolutional networks[C]. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2126,2017, Honolulu, HI, USA. IEEE, 2017: 2261-2269.
LUO G T, LIU Z Q, WANG Q F, et al. Fully convolutional multi-scale ScSE-DenseNet for automatic pneumothorax segmentation in chest radiographs[C]. 2019 IEEE International Conference on Bioinformatics and Biomedicine (BIBM). 1821,2019, San Diego, CA, USA. IEEE, 2019: 1551-1555.
ZHANG Z, WU C, COLEMAN S, et al. DENSE-INception U-net for medical image segmentation[J]. Computer Methods and Programs in Biomedicine, 2020, 192: 105395.
LIU Y J, ZHANG X B, ZHANG J W, et al. DenseNet-centercrop: a novel convolutional network for lung nodule classification[J]. Journal of Zhejiang University (Science Edition), 2020, 47(1): 20-26.(in Chinese)
MA X, ZHANG F D, FENG J F. Sparse representation via deep learning features based face recognition method[J]. CAAI Transactions on Intelligent Systems, 2016, 11(3): 279-286.(in Chinese)
XU J, AN W P, ZHANG L, et al. Sparse, collaborative, or nonnegative representation: Which helps pattern classification? [J]. Pattern Recognition, 2019, 88: 679-688.
ZHAO C, ZHANG B M, YU D H, et al. Airborne LiDAR point cloud classification using transfer learning [J]. Opt. Precision Eng., 2019, 27(7): 1601-1612.(in Chinese)
JUN X,ZHOU X,WANG P.et al.Jointly non-negative,sparse and collaborative representation for image recognition [J]. Pattern Recognition.Preprint .2019
BOYD, PARIKHN., CHUE.,et al. Distributed optimization and statistical learning via the alternating direction method of multipliers[J].Found. Trends Mach. Learn., 2011,3:1-122
LIANG M M, ZHOU T, XIA Y, et al. Multimodal lung tumor image recognition based on randomized fusion and CNN[J]. Journal of Nanjing University (Natural Science), 2018, 54(4): 775-785.(in Chinese)