{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T02:43:41Z","timestamp":1760150621284,"version":"build-2065373602"},"reference-count":70,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2023,12,12]],"date-time":"2023-12-12T00:00:00Z","timestamp":1702339200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["4202025","VTJ-OT20230209-2","Qiankehe foundation zk[2022] general 012"],"award-info":[{"award-number":["4202025","VTJ-OT20230209-2","Qiankehe foundation zk[2022] general 012"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Tianjin Anjian IoT Technology Enterprise Key Laboratory Research Project","award":["4202025","VTJ-OT20230209-2","Qiankehe foundation zk[2022] general 012"],"award-info":[{"award-number":["4202025","VTJ-OT20230209-2","Qiankehe foundation zk[2022] general 012"]}]},{"name":"Guizhou Provincial Sci-Tech project","award":["4202025","VTJ-OT20230209-2","Qiankehe foundation zk[2022] general 012"],"award-info":[{"award-number":["4202025","VTJ-OT20230209-2","Qiankehe foundation zk[2022] general 012"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Symmetry"],"abstract":"<jats:p>Ground-glass nodules (GGN) are the main manifestation of early lung cancer, and accurate and efficient identification of ground-glass pulmonary nodules is of great significance for the treatment of lung diseases. In response to the problem of traditional machine learning requiring manual feature extraction, and most deep learning models applied to 2D image classification, this paper proposes a Transformer-based recognition model for ground-glass nodules from the view of global 3D asymmetry feature representation. Firstly, a 3D convolutional neural network is used as the backbone to extract the features of the three-dimensional CT-image block of pulmonary nodules automatically; secondly, positional encoding information is added to the extracted feature map and input into the Transformer encoder layer for further extraction of global 3D asymmetry features, which can preserve more spatial information and obtain higher-order asymmetry feature representation; finally, the extracted asymmetry features are entered into a support vector machine or ELM-KNN model to further improve the recognition ability of the model. The experimental results show that the recognition accuracy of the proposed method reaches 95.89%, which is 4.79, 2.05, 4.11, and 2.74 percentage points higher than the common deep learning models of AlexNet, DenseNet121, GoogLeNet, and VGG19, respectively; compared with the latest models proposed in the field of pulmonary nodule classification, the accuracy has been improved by 2.05, 2.05, and 0.68 percentage points, respectively, which can effectively improve the recognition accuracy of ground-glass nodules.<\/jats:p>","DOI":"10.3390\/sym15122192","type":"journal-article","created":{"date-parts":[[2023,12,12]],"date-time":"2023-12-12T09:15:33Z","timestamp":1702372533000},"page":"2192","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Transformer-Based Recognition Model for Ground-Glass Nodules from the View of Global 3D Asymmetry Feature Representation"],"prefix":"10.3390","volume":"15","author":[{"given":"Jun","family":"Miao","sequence":"first","affiliation":[{"name":"School of Computer Science, Beijing Information Science and Technology University, Beijing 100101, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Maoxuan","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Beijing Information Science and Technology University, Beijing 100101, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yiru","family":"Chang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Beijing Information Science and Technology University, Beijing 100101, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuanhua","family":"Qiao","sequence":"additional","affiliation":[{"name":"College of Applied Sciences, Beijing University of Technology, Beijing 100124, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2023,12,12]]},"reference":[{"key":"ref_1","first-page":"1477","article-title":"The effect of astaxanthin on human lung cancer A549 in nude mice","volume":"28","author":"Qiu","year":"2019","journal-title":"Chin. J. New Drugs"},{"key":"ref_2","first-page":"1123","article-title":"Diagnostic value of different reconstruction methods of MSCT for pulmonary ground glass nodules within 3 cm","volume":"29","author":"Chen","year":"2019","journal-title":"J. Med. Imaging"},{"key":"ref_3","first-page":"1458","article-title":"CT signs and clinical diagnostic value of benign and malignant solitary focal ground glass density pulmonary nodules","volume":"37","author":"Zhang","year":"2016","journal-title":"J. Hebei Med. Univ."},{"key":"ref_4","first-page":"90","article-title":"Application of computer-aided CT image features in the diagnosis of early lung cancer with ground glass nodules","volume":"4","author":"Feng","year":"2020","journal-title":"J. Imaging Res. Med. Appl."},{"key":"ref_5","first-page":"164","article-title":"Application of deep learning AI technology in Medical imaging aided analysis","volume":"36","author":"Jiang","year":"2021","journal-title":"China Med. Devices"},{"key":"ref_6","first-page":"185","article-title":"The Application of Computer Aided Diagnosis System in Teaching Pulmonary Nodules","volume":"19","author":"Xu","year":"2021","journal-title":"Chin. Foreign Med. Res."},{"key":"ref_7","first-page":"111","article-title":"Breast mass detection based on multi spectral channel attention and two-way feature fusion","volume":"42","author":"Chen","year":"2023","journal-title":"J. South-Cent. Univ. Natl. (Nat. Sci. Ed.)"},{"key":"ref_8","first-page":"1","article-title":"Real time lung nodule detection algorithm combining attention and multipath fusion","volume":"43","author":"Zhao","year":"2023","journal-title":"J. Comput. Appl."},{"key":"ref_9","first-page":"661","article-title":"Classification of brain network features in schizophrenia based on resting statefunctional magnetic resonance imaging","volume":"37","author":"Yu","year":"2020","journal-title":"J. Biomed. Eng."},{"key":"ref_10","first-page":"30","article-title":"Malaria recognition algorithm based on unsupervised sample relationship embedding model","volume":"42","author":"Hu","year":"2022","journal-title":"J. Baoji Univ. Arts Sci. (Nat. Sci. Ed.)"},{"key":"ref_11","unstructured":"Gao, Y. (2020). Segmentation and Classification of Benign and Malignant Pulmonary Nodules Based on Deep Learning, Hebei Normal University. (In Chinese)."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"541","DOI":"10.1162\/neco.1989.1.4.541","article-title":"Backpropagation applied to handwritten zip code recognition","volume":"1","author":"LeCun","year":"1989","journal-title":"Neural Comput."},{"key":"ref_13","first-page":"54","article-title":"A deep learning classification method for pulmonary nodules based on fused prior knowledge","volume":"36","author":"Gao","year":"2021","journal-title":"China Med. Devices"},{"key":"ref_14","first-page":"20","article-title":"DenseNet centrop: A Convolutional Network for Classification of Pulmonary Nodules","volume":"47","author":"Liu","year":"2020","journal-title":"J. Zhe Jiang Univ. (Sci. Ed.)"},{"key":"ref_15","first-page":"135","article-title":"Multi branch convolutional neural network classification method for pulmonary nodules and its interpretability","volume":"47","author":"Zhang","year":"2020","journal-title":"Comput. Sci."},{"key":"ref_16","first-page":"1249","article-title":"3D pulmonary nodule recognition based on K-L transform and support vector machine","volume":"30","author":"Liu","year":"2009","journal-title":"J. Northeast. Univ. (Nat. Sci.)"},{"key":"ref_17","first-page":"87","article-title":"Classification of pulmonary nodules based on three-dimensional convolutional neural networks","volume":"26","author":"Wang","year":"2021","journal-title":"J. Harbin Univ. Sci. Technol."},{"key":"ref_18","unstructured":"Simonyan, K., and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv."},{"key":"ref_19","unstructured":"Raunak, D., Lu, Z., and Hong, Y. (2018, January 4\u20137). Diagnostic classification of lung nodules using 3D neural networks. Proceedings of the 2018 IEEE 15th International Symposium on Biomedical Imaging, Washington, DC, USA."},{"key":"ref_20","first-page":"1590","article-title":"Classification of pulmonary nodules based on CNN multi-level second-order feature fusion","volume":"14","author":"Wei","year":"2020","journal-title":"J. Front. Comput. Sci. Technol."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Halder, A., Chatterjee, S., and Dey, D. (2022). Adaptive morphology aided 2-pathway convolutional neural network for lung nodule classification. Biomed. Signal Process. Control., 72.","DOI":"10.1016\/j.bspc.2021.103347"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"1163","DOI":"10.1007\/s11045-020-00703-6","article-title":"Novel convolutional neural network architecture for improved pulmonary nodule classification on computed tomography","volume":"31","author":"Wang","year":"2020","journal-title":"Multidimens. Syst. Signal Process."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"3606","DOI":"10.1109\/TIP.2023.3287738","article-title":"Hyperspectral Image Classification with Multi-attention Transformer and Adaptive Superpixel Segmentation-based Active Learning","volume":"32","author":"Zhao","year":"2023","journal-title":"IEEE Trans. Image Process."},{"key":"ref_24","unstructured":"Vaswani, A., and Shazeer, N. (2017). Attention Is All You Need. arXiv."},{"key":"ref_25","unstructured":"Dosovitskiy, A., and Beyer, L. (2020). An Image is Worth 16 \u00d7 16 Words: Transformers for Image Recognition at Scale. arXiv."},{"key":"ref_26","first-page":"547","article-title":"YOLOX traffic sign detection based on Swin Transformer","volume":"49","author":"Ji","year":"2023","journal-title":"Radio Commun. Technol."},{"key":"ref_27","first-page":"85","article-title":"Research on lung cancer detection methods based on deep learning","volume":"38","author":"Wang","year":"2020","journal-title":"Digit. Technol. Appl."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"He, K., and Zhang, X. (2016, January 27\u201330). Deep Residual Learning for Image Recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1109\/5254.708428","article-title":"Support vector machines","volume":"13","author":"Hearst","year":"1998","journal-title":"IEEE Intell. Syst. Their Appl."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Setio, A., and Traverso, A. (2017). Validation, Comparison, and Combination of Algorithms for Automatic Detection of Pulmonary Nodules in Computed Tomography Images: The LUNA16 Challenge, Elsevier.","DOI":"10.1016\/j.media.2017.06.015"},{"key":"ref_31","first-page":"189","article-title":"Research Progress and Development Trend of Modern Medical imaging","volume":"14","author":"Qiao","year":"2017","journal-title":"China Health Ind."},{"key":"ref_32","first-page":"949","article-title":"The value of CT histogram analysis in distinguishing benign and malignant pure ground glass nodules of the lung","volume":"35","author":"Cai","year":"2020","journal-title":"Radiol. Pract."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Hu, X., Gong, J., Zhou, W., Li, H., Wang, S., Wei, M., Peng, W., and Gu, Y. (2021). Computer-aided diagnosis of ground glass pulmonary nodule by fusing deep learning and radiomics features. Phys. Med. Biol., 66.","DOI":"10.1088\/1361-6560\/abe735"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"6215085","DOI":"10.1155\/2016\/6215085","article-title":"Pulmonary nodule classification with deep convolutional neural networks on computed tomography images","volume":"2016","author":"Li","year":"2016","journal-title":"Comput. Math. Methods Med."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"1144","DOI":"10.1007\/s10278-020-00355-9","article-title":"The invasiveness classification of ground-glass nodules using 3D attention network and HRCT","volume":"33","author":"Ni","year":"2020","journal-title":"J. Digit. Imaging"},{"key":"ref_36","first-page":"1097","article-title":"ImageNet Classification with Deep Convolutional Neural Networks","volume":"25","author":"Krizhevsky","year":"2012","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Szegedy, C., and Liu, W. (2015, January 7\u201312). Going deeper with convolutions. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA.","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref_38","first-page":"135","article-title":"Research on abnormal disturbance of power quality based on improved Convolutional neural network","volume":"39","author":"Zhang","year":"2023","journal-title":"Microcomput. Appl."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"016025","DOI":"10.1088\/1741-2552\/ab405f","article-title":"HS-CNN: A CNN with hybrid convolution scale for EEG motor imagery classification","volume":"17","author":"Dai","year":"2020","journal-title":"J. Neural Eng."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"124087","DOI":"10.1109\/ACCESS.2019.2927169","article-title":"A dilated CNN model for image classification","volume":"7","author":"Lei","year":"2019","journal-title":"IEEE Access"},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Sharma, H., Jain, J.S., Bansal, P., and Gupta, S. (2020, January 29\u201331). Feature Extraction and Classification of Chest X-Ray Images Using CNN to Detect Pneumonia. Proceedings of the 2020 10th International Conference on Cloud Computing, Data Science & Engineering (Confluence), Noida, India.","DOI":"10.1109\/Confluence47617.2020.9057809"},{"key":"ref_42","unstructured":"Wang, J. (2022). Research on V2X Early Warning Information Display Algorithm and System Implementation Based on Augmented Reality, Jilin University. (In Chinese)."},{"key":"ref_43","first-page":"1382","article-title":"Segmentation method of Hippocampus combin-ng sequence learning and U-shaped network","volume":"31","author":"Cao","year":"2019","journal-title":"J. Comput.-Aided Des. Comput. Graph."},{"key":"ref_44","first-page":"171","article-title":"Classification of pulmonary nodules based on multi-dimensional Convolutional neural network","volume":"55","author":"Wu","year":"2019","journal-title":"Comput. Eng. Appl."},{"key":"ref_45","unstructured":"Shen, W., and Zhou, M. (July, January 28). Multi-scale convolutional neural networks for lung nodule classification. Proceedings of the International Conference on Information Processing in Medical Imaging, Isle of Skye, UK."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"012155","DOI":"10.1088\/1742-6596\/1827\/1\/012155","article-title":"Lung Nodule Classification in CT Images Using 3D DenseNet","volume":"1827","author":"Zhang","year":"2021","journal-title":"J. Phys. Conf. Ser."},{"key":"ref_47","first-page":"1471","article-title":"Survey on Medical Image Computer Aided Detection and Diagnosis Systems","volume":"29","author":"Yuan","year":"2018","journal-title":"J. Softw."},{"key":"ref_48","first-page":"77","article-title":"Research on Coronary Artery Segmentation Method Based on Semi supervised Collaborative Training","volume":"28","author":"Li","year":"2023","journal-title":"Chin. J. Stereol. Image Anal."},{"key":"ref_49","doi-asserted-by":"crossref","unstructured":"Chenyu, Y., Zhao, R., Liu, F., Chinchali, S., Topcu, U., Staib, L., and Duncan, J.S. (2022). Class-Aware Generative Adversarial Transformers for Medical Image Segmentation. arXiv.","DOI":"10.1145\/3561613.3561614"},{"key":"ref_50","unstructured":"Cao, H., Wang, Y., Chen, J., Jiang, D., Zhang, X., Tian, Q., and Wang, M. (2021). Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation. arXiv."},{"key":"ref_51","doi-asserted-by":"crossref","unstructured":"Chen, J., Frey, E.C., He, Y., Segars, W.P., Li, Y., and Du, Y. (2021). TransMorph: Transformer for unsupervised medical image registration. arXiv.","DOI":"10.1016\/j.media.2022.102615"},{"key":"ref_52","doi-asserted-by":"crossref","unstructured":"Valanarasu, J.M.J., Oza, P., Hacihaliloglu, I., and Patel, V. (October, January 27). Medical transformer: Gated axial-attention for medical image segmentation. Proceedings of the Medical Image Computing and Computer Assisted Intervention\u2013MICCAI 2021: 24th International Conference, Strasbourg, France. Part I 24.","DOI":"10.1007\/978-3-030-87193-2_4"},{"key":"ref_53","unstructured":"Veli\u010dkovi\u0107, P., Cucurull, G., Casanova, A., Romero, A., Lio, P., and Bengio, Y. (2017). Graph attention networks. arXiv."},{"key":"ref_54","unstructured":"Ba, J.L., Kiros, J.R., and Hinton, G.E. (2016). Layer normalization. arXiv."},{"key":"ref_55","unstructured":"Powell, M.J.D. (, January July). Radial basis function for multivariable approximations: A review. Proceedings of the IMA Conference on Algorithms for the Approximation of Functions and Data, Shrivenham, UK."},{"key":"ref_56","unstructured":"Dallimore, P.J. (1970). HAUSER-A Computer Code for the Calculation of Compound Nucleus Cross Sections Using the Hauser-Feshbach Theory, Australian National University."},{"key":"ref_57","doi-asserted-by":"crossref","first-page":"108904","DOI":"10.1016\/j.buildenv.2022.108904","article-title":"Diagnosis for multiple faults of chiller using ELM-KNN model enhanced by multi-label learning and specific feature combinations","volume":"214","author":"Li","year":"2022","journal-title":"Build. Environ."},{"key":"ref_58","doi-asserted-by":"crossref","first-page":"513","DOI":"10.1109\/TSMCB.2011.2168604","article-title":"Extreme learning machine for regression and multiclass classification","volume":"42","author":"Huang","year":"2011","journal-title":"IEEE Trans. Syst. Man Cybern. Part B (Cybern.)"},{"key":"ref_59","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1109\/TIT.1967.1053964","article-title":"Nearest neighbor pattern classification","volume":"13","author":"Cover","year":"1967","journal-title":"IEEE Trans. Inf. Theor."},{"key":"ref_60","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1016\/S0020-7373(87)80053-6","article-title":"Simplifying decision trees","volume":"27","author":"Quinlan","year":"1987","journal-title":"Int. J. Man-Mach. Stud."},{"key":"ref_61","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach. Learn."},{"key":"ref_62","first-page":"564","article-title":"Regularizing adaboost","volume":"11","author":"Onoda","year":"1998","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_63","doi-asserted-by":"crossref","unstructured":"Gao, H., Zhuang, L., van der Maaten, L., and Weinberger, K.Q. (2017, January 21\u201326). Densely Connected Convolutional Networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref_64","first-page":"163","article-title":"Classification of pulmonary nodules based on attention mechanism","volume":"39","author":"Kuang","year":"2022","journal-title":"Comput. Appl. Softw."},{"key":"ref_65","first-page":"389","article-title":"Classification of benign and malignant pulmonary nodules based on multi model fusion method","volume":"32","author":"Guo","year":"2021","journal-title":"J. Optoelectron. Laser"},{"key":"ref_66","doi-asserted-by":"crossref","unstructured":"Zhu, Q., Wang, Y., Chu, X., Yang, X., and Zhong, W. (2022, January 4\u20138). Multi-View Coupled Self-Attention Network for Pulmonary Nodules Classification. Proceedings of the Asian Conference on Computer Vision, Macau SAR, China.","DOI":"10.1007\/978-3-031-26351-4_3"},{"key":"ref_67","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1016\/j.media.2015.02.002","article-title":"Segmentation of pulmonary nodules in computed tomography using a regression neural network approach and its application to the Lung Image Database Consortium and Image Database Resource Initiative dataset","volume":"22","author":"Messay","year":"2015","journal-title":"Med. Image Anal."},{"key":"ref_68","unstructured":"Li, C. (2020). Classification Model of Lung Nodules Combining DPN Network and Capsule Network, Jilin University. (In Chinese)."},{"key":"ref_69","first-page":"165","article-title":"Comparative study on classification of pulmonary nodules based on multi-scale multi-mode images","volume":"56","author":"Tang","year":"2020","journal-title":"Comput. Eng. Appl."},{"key":"ref_70","doi-asserted-by":"crossref","unstructured":"Han, Y., Qi, H., Wang, L., Chen, C., Miao, J., Xu, H., Wang, Z., Guo, Z., Xu, Q., and Lin, Q. (2022). Pulmonary nodules detection assistant platform: An effective computer aided system for early pulmonary nodules detection in physical examination. Comput. Methods Programs Biomed., 217.","DOI":"10.1016\/j.cmpb.2022.106680"}],"container-title":["Symmetry"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-8994\/15\/12\/2192\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T21:37:28Z","timestamp":1760132248000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-8994\/15\/12\/2192"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,12]]},"references-count":70,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2023,12]]}},"alternative-id":["sym15122192"],"URL":"https:\/\/doi.org\/10.3390\/sym15122192","relation":{},"ISSN":["2073-8994"],"issn-type":[{"type":"electronic","value":"2073-8994"}],"subject":[],"published":{"date-parts":[[2023,12,12]]}}}