Journal of Computer Applications ›› 2022, Vol. 42 ›› Issue (5): 1424-1430.DOI: 10.11772/j.issn.1001-9081.2021050813
Special Issue: 人工智能
• Artificial intelligence • Previous Articles Next Articles
Xinlin XIE1,2, Yi XIAO3, Xinying XU3()
Received:
2021-05-17
Revised:
2021-09-26
Accepted:
2021-11-26
Online:
2022-03-08
Published:
2022-05-10
Contact:
Xinying XU
About author:
XIE Xinlin, born in 1990,Ph. D.,lecturer. His research interests include medical image processing,rough set.Supported by:
通讯作者:
续欣莹
作者简介:
谢新林(1990—),男,山西运城人,讲师,博士,CCF会员,主要研究方向:医学图像处理、粗糙集基金资助:
CLC Number:
Xinlin XIE, Yi XIAO, Xinying XU. Lung nodule classification algorithm based on neural network architecture search[J]. Journal of Computer Applications, 2022, 42(5): 1424-1430.
谢新林, 肖毅, 续欣莹. 基于神经网络架构搜索的肺结节分类算法[J]. 《计算机应用》唯一官方网站, 2022, 42(5): 1424-1430.
Add to citation manager EndNote|Ris|BibTeX
URL: https://www.joca.cn/EN/10.11772/j.issn.1001-9081.2021050813
算法 | Acc. | Sens. | Spec. | Pre. | AUC | F1 |
---|---|---|---|---|---|---|
NAS | 87.57 | 86.30 | 94.64 | 87.31 | 92.03 | 87.10 |
NAS+MS-SCAM | 88.04 | 85.08 | 95.73 | 88.24 | 92.59 | 88.51 |
NAS+integrated | 89.20 | 88.18 | 94.36 | 89.19 | 92.82 | 89.11 |
NAS+MS-SCAM+integrated | 90.86 | 87.78 | 95.37 | 88.74 | 93.42 | 89.19 |
Tab. 1 Ablation experimental results under different strategies
算法 | Acc. | Sens. | Spec. | Pre. | AUC | F1 |
---|---|---|---|---|---|---|
NAS | 87.57 | 86.30 | 94.64 | 87.31 | 92.03 | 87.10 |
NAS+MS-SCAM | 88.04 | 85.08 | 95.73 | 88.24 | 92.59 | 88.51 |
NAS+integrated | 89.20 | 88.18 | 94.36 | 89.19 | 92.82 | 89.11 |
NAS+MS-SCAM+integrated | 90.86 | 87.78 | 95.37 | 88.74 | 93.42 | 89.19 |
算法 | Acc. | Sens. | Spec. | Pre. | AUC | F1 |
---|---|---|---|---|---|---|
删除MS-SCAM模块 | 87.57 | 86.30 | 94.64 | 87.31 | 92.03 | 87.10 |
阶段3 | 87.78 | 86.43 | 94.98 | 87.60 | 92.26 | 87.51 |
阶段3+阶段4 | 87.89 | 85.51 | 95.42 | 87.97 | 92.46 | 87.98 |
阶段3+阶段4+阶段5 | 88.04 | 85.08 | 95.73 | 88.24 | 92.59 | 88.51 |
Tab. 2 Influence of number of MS-SCAM modules on classification performance
算法 | Acc. | Sens. | Spec. | Pre. | AUC | F1 |
---|---|---|---|---|---|---|
删除MS-SCAM模块 | 87.57 | 86.30 | 94.64 | 87.31 | 92.03 | 87.10 |
阶段3 | 87.78 | 86.43 | 94.98 | 87.60 | 92.26 | 87.51 |
阶段3+阶段4 | 87.89 | 85.51 | 95.42 | 87.97 | 92.46 | 87.98 |
阶段3+阶段4+阶段5 | 88.04 | 85.08 | 95.73 | 88.24 | 92.59 | 88.51 |
算法 | Acc. | Sens. | Spec. | Pre. | AUC | F1 |
---|---|---|---|---|---|---|
通道注意力+ 空间注意力 | 88.04 | 85.08 | 95.73 | 88.24 | 92.59 | 88.51 |
空间注意力+ 通道注意力 | 87.65 | 82.86 | 96.43 | 87.11 | 89.74 | 86.37 |
Tab. 3 Influence of order of channel attention and spatial attention on classification performance
算法 | Acc. | Sens. | Spec. | Pre. | AUC | F1 |
---|---|---|---|---|---|---|
通道注意力+ 空间注意力 | 88.04 | 85.08 | 95.73 | 88.24 | 92.59 | 88.51 |
空间注意力+ 通道注意力 | 87.65 | 82.86 | 96.43 | 87.11 | 89.74 | 86.37 |
算法 | Acc. | Sens. | Spec. | Pre. | AUC | F1 |
---|---|---|---|---|---|---|
NASpure | 87.04 | 83.48 | 90.63 | 85.44 | 89.01 | 84.59 |
NASpure+ 残差卷积cell | 87.55 | 84.47 | 92.13 | 86.25 | 90.77 | 86.56 |
NASpure+POP | 87.28 | 84.03 | 91.50 | 85.79 | 89.41 | 85.74 |
NASpure+残差 卷积cell+POP | 87.57 | 86.30 | 94.64 | 87.31 | 92.03 | 87.10 |
Tab. 4 Influence of neural network architecture search setting on classification performance
算法 | Acc. | Sens. | Spec. | Pre. | AUC | F1 |
---|---|---|---|---|---|---|
NASpure | 87.04 | 83.48 | 90.63 | 85.44 | 89.01 | 84.59 |
NASpure+ 残差卷积cell | 87.55 | 84.47 | 92.13 | 86.25 | 90.77 | 86.56 |
NASpure+POP | 87.28 | 84.03 | 91.50 | 85.79 | 89.41 | 85.74 |
NASpure+残差 卷积cell+POP | 87.57 | 86.30 | 94.64 | 87.31 | 92.03 | 87.10 |
多模型融合策略 | Acc./% | Sens./% | Spec./% | Pre./% | AUC/% | F1/% | 参数量/106 |
---|---|---|---|---|---|---|---|
加权投票 | 88.32 | 88.02 | 94.73 | 88.59 | 92.65 | 87.76 | 25.72 |
堆叠法 | 89.20 | 88.18 | 94.36 | 89.19 | 92.82 | 89.11 | 36.53 |
Tab. 5 Influence of multi-model fusion strategy on classification performance
多模型融合策略 | Acc./% | Sens./% | Spec./% | Pre./% | AUC/% | F1/% | 参数量/106 |
---|---|---|---|---|---|---|---|
加权投票 | 88.32 | 88.02 | 94.73 | 88.59 | 92.65 | 87.76 | 25.72 |
堆叠法 | 89.20 | 88.18 | 94.36 | 89.19 | 92.82 | 89.11 | 36.53 |
算法 | Acc./% | Sens./% | Spec./% | Pre./% | AUC/% | F1/% | 参数量/106 |
---|---|---|---|---|---|---|---|
Autoencoder | 80.29 | 73.00 | 85.00 | — | 86.00 | — | — |
MC-CNN | 87.14 | 77.00 | 93.00 | — | 93.00 | — | — |
Local-Global | 88.46 | 88.66 | — | — | 95.62 | — | — |
DeepLung | 90.44 | 81.42 | — | — | — | — | 141.57 |
NAS-lung | 90.77 | 85.37 | 95.04 | — | — | 89.29 | 16.84 |
MV-KBC | 91.60 | 86.52 | 94.00 | 87.75 | 95.70 | 87.13 | — |
本文算法 | 90.86 | 87.78 | 95.37 | 93.42 | 88.74 | 89.19 | 30.64 |
Tab. 6 Performance comparison of different classification algorithms on LIDC-IDRI dataset
算法 | Acc./% | Sens./% | Spec./% | Pre./% | AUC/% | F1/% | 参数量/106 |
---|---|---|---|---|---|---|---|
Autoencoder | 80.29 | 73.00 | 85.00 | — | 86.00 | — | — |
MC-CNN | 87.14 | 77.00 | 93.00 | — | 93.00 | — | — |
Local-Global | 88.46 | 88.66 | — | — | 95.62 | — | — |
DeepLung | 90.44 | 81.42 | — | — | — | — | 141.57 |
NAS-lung | 90.77 | 85.37 | 95.04 | — | — | 89.29 | 16.84 |
MV-KBC | 91.60 | 86.52 | 94.00 | 87.75 | 95.70 | 87.13 | — |
本文算法 | 90.86 | 87.78 | 95.37 | 93.42 | 88.74 | 89.19 | 30.64 |
1 | BRAY F, FERLAY J, SOERJOMATARAM I, et al. Global cancer statistics 2018: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries [J]. CA: A Cancer Journal for Clinicians, 2018, 68(6): 394-424. 10.3322/caac.21492 |
2 | 中华医学会呼吸病学分会肺癌学组,中国肺癌防治联盟专家组.肺结节诊治中国专家共识(2018年版)[J].中华结核和呼吸杂志,2018,41(10):763-771. 10.3760/cma.j.issn.1001-0939.2018.10.004 |
Lung Cancer Group of Chinese Thoracic Society of Chinese Medical Association, Expert Group of China Lung Cancer Prevention and Treatment Alliance. Interpretation of Chinese expert consensus on the diagnosis and treatment of pulmonary nodules (2018 version) [J]. Chinese Journal of Tuberculosis and Respiratory Diseases, 2018, 41(10): 763-771. 10.3760/cma.j.issn.1001-0939.2018.10.004 | |
3 | 李祥霞,李彬,田联房,等.基于放射影像组学和随机森林算法的肺结节良恶性分类[J].华南理工大学学报(自然科学版),2018,46(8):72-80. 10.3969/j.issn.1000-565X.2018.08.011 |
LI X X, LI B, TIAN L F, et al. Classification of benign and malignant pulmonary nodules based on radiomics and random forests algorithm [J]. Journal of South China University of Technology (Natural Science Edition), 2018, 46(8): 72-80. 10.3969/j.issn.1000-565X.2018.08.011 | |
4 | 强彦,裴博,赵涓涓,等.模糊支持向量机在肺结节良恶性分类中的应用[J].清华大学学报(自然科学版),2014,54(3):354-359. |
QIANG Y, PEI B, ZHAO J J, et al. Classification on pulmonary nodules based on a fuzzy support vector machine [J]. Journal of Tsinghua University (Science and Technology), 2014, 54(3): 354-359. | |
5 | 高峰,代美玲,祁瑾.基于Bootstrap-异质SVM集成学习的肺结节分类方法[J].天津大学学报(自然科学与工程技术版),2017,50(3):321-327. 10.11784/tdxbz201603019 |
GAO F, DAI M L, QI J. Classification of lung nodules by ensemble learning based on Bootstrap-heterogeneous SVM [J]. Journal of Tianjin University (Science and Technology), 2017, 50(3): 321-327. 10.11784/tdxbz201603019 | |
6 | 张婧,李彬,田联房,等.结合规则和SVM方法的肺结节识别[J].华南理工大学学报(自然科学版),2011,39(2):125-129,147. 10.3969/j.issn.1000-565X.2011.02.021 |
ZHANG J, LI B, TIAN L F, et al. Lung nodule recognition combining rule-based method and SVM [J]. Journal of South China University of Technology (Natural Science Edition), 2011, 39(2): 125-129, 147. 10.3969/j.issn.1000-565X.2011.02.021 | |
7 | SHEN W, ZHOU M, YANG F, et al. Multi-crop convolutional neural networks for lung nodule malignancy suspiciousness classification [J]. Pattern Recognition, 2017, 61: 663-673. 10.1016/j.patcog.2016.05.029 |
8 | XIE Y T, ZHANG J P, XIA Y, et al. Fusing texture, shape and deep model-learned information at decision level for automated classification of lung nodules on chest CT [J]. Information Fusion, 2018, 42: 102-110. 10.1016/j.inffus.2017.10.005 |
9 | XIE Y T, XIA Y, ZHANG J P, et al. Knowledge-based collaborative deep learning for benign-malignant lung nodule classification on chest CT [J]. IEEE Transactions on Medical Imaging, 2019, 38(4): 991-1004. 10.1109/tmi.2018.2876510 |
10 | ELSKEN T, METZEN J H, HUTTER F. Neural architecture search: a survey [J]. Journal of Machine Learning Research, 2019, 20: 1-21. 10.1007/978-3-030-05318-5_3 |
11 | LI X, ZHOU Y M, PAN Z, et al. Partial order pruning: for best speed/accuracy trade-off in neural architecture search [C]// Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2019: 9137-9145. 10.1109/cvpr.2019.00936 |
12 | 慧影医疗科技(北京)有限公司.一种基于多模型融合的肺结节检测方法及系统:中国,201910399988.6[P].2019-08-30. 10.1055/s-009-42979 |
Huiying Medical Technology (Beijing) Company Limited. A multi-model fusion-based method and system for detecting lung nodules: China, 201910399988.6 [P]. 2019-08-30. 10.1055/s-009-42979 | |
13 | LI F, CHENG D N, LIU M H. Alzheimer’s disease classification based on combination of multi-model convolutional networks [C]// Proceedings of the 2017 IEEE International Conference on Imaging Systems and Techniques. Piscataway: IEEE, 2017: 1-5. 10.1109/ist.2017.8261566 |
14 | JIANG H L, SHEN F H, GAO F, et al. Learning efficient, explainable and discriminative representations for pulmonary nodules classification [J]. Pattern Recognition, 2021, 113: Article No.107825. 10.1016/j.patcog.2021.107825 |
15 | KUMAR D, WONG A, CLAUSI D A. Lung nodule classification using deep features in CT images [C]// Proceedings of the 2015 12th Conference on Computer and Robot Vision. Piscataway: IEEE, 2015: 133-138. 10.1109/crv.2015.25 |
16 | AL-SHABI M, LAN B L, CHAN W Y, et al. Lung nodule classification using deep local-global networks [J]. International Journal of Computer Assisted Radiology and Surgery, 2019, 14(10): 1815-1819. 10.1007/s11548-019-01981-7 |
17 | ZHU W T, LIU C C, FAN W, et al. DeepLung: deep 3D dual path nets for automated pulmonary nodule detection and classification [C]// Proceedings of the 2018 IEEE Winter Conference on Applications of Computer Vision. Piscataway: IEEE, 2018: 673-681. 10.1109/wacv.2018.00079 |
[1] | Yexin PAN, Zhe YANG. Optimization model for small object detection based on multi-level feature bidirectional fusion [J]. Journal of Computer Applications, 2024, 44(9): 2871-2877. |
[2] | Yunchuan HUANG, Yongquan JIANG, Juntao HUANG, Yan YANG. Molecular toxicity prediction based on meta graph isomorphism network [J]. Journal of Computer Applications, 2024, 44(9): 2964-2969. |
[3] | Jing QIN, Zhiguang QIN, Fali LI, Yueheng PENG. Diagnosis of major depressive disorder based on probabilistic sparse self-attention neural network [J]. Journal of Computer Applications, 2024, 44(9): 2970-2974. |
[4] | Xiyuan WANG, Zhancheng ZHANG, Shaokang XU, Baocheng ZHANG, Xiaoqing LUO, Fuyuan HU. Unsupervised cross-domain transfer network for 3D/2D registration in surgical navigation [J]. Journal of Computer Applications, 2024, 44(9): 2911-2918. |
[5] | Shunyong LI, Shiyi LI, Rui XU, Xingwang ZHAO. Incomplete multi-view clustering algorithm based on self-attention fusion [J]. Journal of Computer Applications, 2024, 44(9): 2696-2703. |
[6] | Yeheng LI, Guangsheng LUO, Qianmin SU. Logo detection algorithm based on improved YOLOv5 [J]. Journal of Computer Applications, 2024, 44(8): 2580-2587. |
[7] | Yuhan LIU, Genlin JI, Hongping ZHANG. Video pedestrian anomaly detection method based on skeleton graph and mixed attention [J]. Journal of Computer Applications, 2024, 44(8): 2551-2557. |
[8] | Yanjie GU, Yingjun ZHANG, Xiaoqian LIU, Wei ZHOU, Wei SUN. Traffic flow forecasting via spatial-temporal multi-graph fusion [J]. Journal of Computer Applications, 2024, 44(8): 2618-2625. |
[9] | Qianhong SHI, Yan YANG, Yongquan JIANG, Xiaocao OUYANG, Wubo FAN, Qiang CHEN, Tao JIANG, Yuan LI. Multi-granularity abrupt change fitting network for air quality prediction [J]. Journal of Computer Applications, 2024, 44(8): 2643-2650. |
[10] | Yiqun ZHAO, Zhiyu ZHANG, Xue DONG. Anisotropic travel time computation method based on dense residual connection physical information neural networks [J]. Journal of Computer Applications, 2024, 44(7): 2310-2318. |
[11] | Song XU, Wenbo ZHANG, Yifan WANG. Lightweight video salient object detection network based on spatiotemporal information [J]. Journal of Computer Applications, 2024, 44(7): 2192-2199. |
[12] | Xun SUN, Ruifeng FENG, Yanru CHEN. Monocular 3D object detection method integrating depth and instance segmentation [J]. Journal of Computer Applications, 2024, 44(7): 2208-2215. |
[13] | Zhe KONG, Han LI, Shaowei GAN, Mingru KONG, Bingtao HE, Ziyu GUO, Ducheng JIN, Zhaowen QIU. Structure segmentation model for 3D kidney images based on asymmetric multi-decoder and attention module [J]. Journal of Computer Applications, 2024, 44(7): 2216-2224. |
[14] | Zheng WU, Zhiyou CHENG, Zhentian WANG, Chuanjian WANG, Sheng WANG, Hui XU. Deep learning-based classification of head movement amplitude during patient anaesthesia resuscitation [J]. Journal of Computer Applications, 2024, 44(7): 2258-2263. |
[15] | Huanhuan LI, Tianqiang HUANG, Xuemei DING, Haifeng LUO, Liqing HUANG. Public traffic demand prediction based on multi-scale spatial-temporal graph convolutional network [J]. Journal of Computer Applications, 2024, 44(7): 2065-2072. |
Viewed | ||||||
Full text |
|
|||||
Abstract |
|
|||||