-
摘要: 肺癌的早期发现、精确诊断对于患者的预后至关重要。影像学能够无创、全面地反映肿瘤的异质性,在肺癌诊断中发挥重要作用。海量影像数据的深入挖掘是影像医师面临的巨大挑战。人工智能(artificial intelligence,AI)擅长处理大批量、高维度的信息,用算法解析数据,既可以自动提取定量特征,也可以自动学习现有数据,从而对新数据进行预测。AI在影像处理领域得到快速发展,在肺结节检出、肺癌诊断等方面显示出较大的优势和应用前景。将AI与临床工作相结合有助于精准医疗的实施。本文对近年来AI在肺部肿瘤影像诊断领域的研究现状和进展予以概述。Abstract: Early detection and accurate diagnosis are critical for the prognosis of lung cancer. Radiological imaging could reflect tumor heterogeneity in a non-invasive and comprehensive manner. Deep mining of high throughput imaging data is a big challenge for radiologists. Artificial intelligence (AI) methods excel at processing large quantities of high-dimensional information and analyzing data using algorithm. It can automatically recognize complex patterns in imaging data, provide quantitative assessments of radiographic characteristics, and is promising in tumor detection and diagnosis. Precision medicine could be made when AI was integrated into the clinical workflow as a tool to assist radiologists. Here we review the current progress and discuss the challenges and future directions of AI applications in lung tumor imaging diagnosis.
-
Key words:
- artificial intelligence (AI) /
- radiomics /
- deep learning /
- lung tumor /
- diagnosis
-
[1] Gillies RJ, Anderson AR, Gatenby RA, et al. The biology underlying molecular imaging in oncology:from genome to anatome and back again[J]. Clin Radiol, 2010, 65(7):517-521. http://cn.bing.com/academic/profile?id=72931bd2b8428989a4a2a158802d8d94&encoded=0&v=paper_preview&mkt=zh-cn [2] Zwanenburg A, Vallieres M, Abdalah MA, et al. The image biomarker standardization initiative:standardized quantitative radiomics for high-throughput image-based phenotyping[J]. Radiology, 2020, 22(1):191145. http://cn.bing.com/academic/profile?id=577ae04422cb835f7ea5249563a66da3&encoded=0&v=paper_preview&mkt=zh-cn [3] Visvikis D, Rest CCL, Jaouen V, et al. Artificial intelligence, machine (deep) learning and radio(geno)mics:definitions and nuclear medicine imaging applications[J]. Eur J Nucl Med Mol Imaging, 2019, 46(13):2630-2637. http://cn.bing.com/academic/profile?id=5dc1cadd784a8725ba2889b03dc305b0&encoded=0&v=paper_preview&mkt=zh-cn [4] Scholten ET, Horeweg N, De Koning HJ, et al. Computed tomographic characteristics of interval and post screen carcinomas in lung cancer screening[J]. Eur Radiol, 2015, 25(1):81-88. http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=c36dc487bff691e8e2038a90360a04cb [5] Zhang GB, Jiang S, Yang ZY, et al. Automatic nodule detection for lung cancer in CT images:A review[J]. Comput Biol Med, 2018, (103):287-300. http://cn.bing.com/academic/profile?id=a404a61da0efe1e1051b5cc2f83da321&encoded=0&v=paper_preview&mkt=zh-cn [6] Saien S, Hamid Pilevar A, Abrishami Moghaddam H. Refinement of lung nodule candidates based on local geometric shape analysis and Laplacian of Gaussian kernels[J]. Comput Biol Med, 2014, (54):188-198. http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=67fffe65d82be62c80c3caac9eb343ca [7] Wang Q, Shen FY, Shen LY, et al. Lung nodule detection in CT images using a raw patch-based convolutional neural network[J]. J Digit Imaging, 2019, 32(6):971-979. http://cn.bing.com/academic/profile?id=29dc0aebfec8dae75396bf556a99168d&encoded=0&v=paper_preview&mkt=zh-cn [8] Setio AAA, Ciompi F, Litjens G, et al. Pulmonary nodule detection in CT images:false positive reduction using multi-view convolutional networks[J]. IEEE Trans Med Imaging, 2016, 35(5):1160-1169. http://cn.bing.com/academic/profile?id=9878ee7cf824ebd680bb3eb3f1e05088&encoded=0&v=paper_preview&mkt=zh-cn [9] Dou Q, Chen H, Yu LQ, et al. Multi-level contextual 3D CNNs for false positive reduction in pulmonary nodule detection[J]. IEEE Trans BioNed Eng, 2017, 64(7):1558-1567. https://acadpubl.eu/hub/2018-119-18/2/108.pdf [10] Zheng SY, Guo JP, Cui XN, et al. Automatic pulmonary nodule detection in CT scans using convolutional neural networks based on maximum intensity projection[J]. IEEE Trans Med Imag, 2020, 39(3):797-805. http://cn.bing.com/academic/profile?id=0c427b17f86781bd914176119fe6101d&encoded=0&v=paper_preview&mkt=zh-cn [11] Wang H, Guo XH, Jia ZW, et al. Multilevel binomial logistic prediction model for malignant pulmonary nodules based on texture features of CT image[J]. Eur J Radiol, 2010, 74(1):124-129. http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=a671008d7461c3ea5c062e8426b0773a [12] Gao N, Tian SJ, Li X, et al. Three-dimensional texture feature analysis of pulmonary nodules in CT images:lung cancer predictive models based on support vector machine classifier[J]. J Digit Imaging, 2019, (16):863-871. http://cn.bing.com/academic/profile?id=1e91fe79d4b455cb1b1b54cb1c353217&encoded=0&v=paper_preview&mkt=zh-cn [13] Sun WQ, Zheng B, Qian W. Automatic feature learning using multichannel ROI based on deep structured algorithms for computerized lung cancer diagnosis[J]. Comput Biol Med, 2017, (89):530-539. http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=0750e1bc9ea022b70b47cae71bce4ebc [14] Zhang GB, Yang ZY, Gong L, et al. Classification of lung nodules based on CT images using squeeze-and-excitation network and aggregated residual transformations[J]. Radiol Med, 2020.[Epub ahead of print] http://cn.bing.com/academic/profile?id=475ea10e05987b600d88635c5dc4fa46&encoded=0&v=paper_preview&mkt=zh-cn [15] Kirienko M, Cozzi L, Rossi A, et al. Ability of FDG PET and CT radiomics features to differentiate between primary and metastatic lung lesions[J]. Eur J Nucl Med Mol Imaging, 2018, 45(10):1649-1660. http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=6a9f2bded5dd2fbb860a16fbb6613a65 [16] Ferreira-Junior JR, Koenigkam-Santos M, Magalhaes Tenorio AP, et al. CT-based radiomics for prediction of histologic subtype and metastatic disease in primary malignant lung neoplasms[J]. Int J Comput Assist Radiol Surg, 2020, 15(1):163-172. http://cn.bing.com/academic/profile?id=0add345c8b80b6535ae5f332dbd602cb&encoded=0&v=paper_preview&mkt=zh-cn [17] Digumarthy SR, Padole AM, Gullo RL, et al. Can CT radiomic analysis in NSCLC predict histology and EGFR mutation status[J]? Med(Baltimore), 2019, 98(1):e13963. http://cn.bing.com/academic/profile?id=1a94f58e3f582cb1f2854a3033eed447&encoded=0&v=paper_preview&mkt=zh-cn [18] Hyun SH, Ahn MS, Koh YW, et al. A machine-learning approach using PET-based radiomics to predict the histological subtypes of lung cancer[J]. Clin Nucl Med, 2019, 44(12):956-960. http://cn.bing.com/academic/profile?id=450d351dd02e2dba9fd49ec03e9edd32&encoded=0&v=paper_preview&mkt=zh-cn [19] Koyasu S, Nishio M, Isoda H, et al. Usefulness of gradient tree boosting for predicting histological subtype and EGFR mutation status of nonsmall cell lung cancer on (18)F FDG-PET/CT[J]. Ann Nucl Med, 2020, 34(1):49-57. [20] Linning E, Lin Lu, Li Li, et al. Radiomics for classifying histological subtypes of lung cancer based on multiphasic contrast-enhanced computed tomography[J]. J Comput Assist Tomogr, 2019, 43(2):300-306. http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=10.1097/RCT.0000000000000836 [21] Weng Q, Zhou L, Wang H, et al. A radiomics model for determining the invasiveness of solitary pulmonary nodules that manifest as part-solid nodules[J]. Clin Radiol, 2019, 74(12):933-943. http://cn.bing.com/academic/profile?id=9f7f5b66761defbc77e089f67a9b7b30&encoded=0&v=paper_preview&mkt=zh-cn [22] ChoHH, Lee G, Lee HY, et al. Marginal radiomics features as imaging biomarkers for pathological invasion in lung adenocarcinoma[J]. Eur Radiol, 2020.[Epub ahead of print] http://cn.bing.com/academic/profile?id=4fe09ea857658d0dc60675cf7fd9c901&encoded=0&v=paper_preview&mkt=zh-cn [23] Jun Wang, Xiaorong Chen, Hongbing Lu, et al. Feature-shared adaptiveboost deep learning for invasiveness classification of pulmonary subsolid nodules in CT images[J]. Med Phys, 2020.[Epub ahead of print] [24] Zhao W, Yang JC, Sun YL, et al. 3D deep learning from CT scans predicts tumor invasiveness of subcentimeter pulmonary adenocarcinomas[J]. Cancer Res, 2018, 78(24):6881-6889. http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=684271ea2608ee1a911dd04512f759ab [25] Yanagawa M, Niioka H, Hata A, et al. Application of deep learning (3-dimensional convolutional neural network) for the prediction of pathological invasiveness in lung adenocarcinoma:A preliminary study[J]. Medicine (Baltimore), 2019, 98(25):e16119. http://cn.bing.com/academic/profile?id=eb02e61bcad7a4575b29543bf43b6f6d&encoded=0&v=paper_preview&mkt=zh-cn [26] CorollerTP, Grossmann P, Hou Y, et al. CT-based radiomic signature predicts distant metastasis in lung adenocarcinoma[J]. Radiother Oncol, 2015, 114(3):345-350. http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=ba678a93c7ad64544f3731f8e27969f1 [27] Xinyan Xu, Lyu Huang, Jiayan Chen, et al. Application of radiomics signature captured from pretreatment thoracic CT to predict brain metastases in stage Ⅲ/Ⅳ ALK-positive non-small cell lung cancer patients[J]. J Thorac Dis, 2019, 11(11):4516-4528. [28] Cong MD, Feng H, Ren JL, et al. Development of a predictive radiomics model for lymph node metastases in pre-surgical CT-based stageⅠA non-small cell lung cancer[J]. Lung Cancer, 2020, (139):73-79. https://www.ncbi.nlm.nih.gov/pubmed/31743889 [29] Yang XG, Pan XH, Liu H, et al. A new approach to predict lymph node metastasis in solid lung adenocarcinoma:a radiomics nomogram[J]. J Thorac Dis, 2018, 10(Suppl 7):S807-s819. http://cn.bing.com/academic/profile?id=5d63176e48c2427a919241154a960f9d&encoded=0&v=paper_preview&mkt=zh-cn [30] Wang X, Zhao XY, Li Q, et al. Can peritumoral radiomics increase the efficiency of the prediction for lymph node metastasis in clinical stage T1 lung adenocarcinoma on CT[J]? Eur Radiol, 2019, 29(11):6049-6058. http://cn.bing.com/academic/profile?id=01e2e4b9c9d19d2cd4797d89fdb4fc58&encoded=0&v=paper_preview&mkt=zh-cn [31] Bayanati H, Thornhill RE, Souza CA, et al. Quantitative CT texture and shape analysis:can it differentiate benign and malignant mediastinal lymph nodes in patients with primary lung cancer[J]? Eur Radiol, 2015, 25(2):480-487. http://cn.bing.com/academic/profile?id=0265da3458bb2bc20aa2d6e7caedcd73&encoded=0&v=paper_preview&mkt=zh-cn [32] Moitra D, Mandal R Kr. Automated AJCC (7th edition) staging of nonsmall cell lung cancer (NSCLC) using deep convolutional neural network (CNN) and recurrent neural network (RNN)[J]. Health Inf Sci Syst, 2019, 7(1):14. [33] Wang HK, Zhou ZW, Li YC, et al. Comparison of machine learning methods for classifying mediastinal lymph node metastasis of nonsmall cell lung cancer from (18)F-FDG PET/CT images[J]. EJNMMI Res, 2017, 7(1):11. doi: 10.1186/s13550-017-0260-9 [34] Zhao W, Zhang W, Sun YL, et al. Convolution kernel and iterative reconstruction affect the diagnostic performance of radiomics and deep learning in lung adenocarcinoma pathological subtypes[J]. Thorac Cancer, 2019, 10(10):1893-1903. http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=10.1111/1759-7714.13161 [35] Velazquez ER, Parmar C, Liu Y, et al. Somatic mutations drive distinct imaging phenotypes in lung cancer[J]. Cancer Res, 2017, 77(14):3922-3930. http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=781c569a8784785dcf9115bdf0979cd2 [36] Yoon HJ, Sohn I, Cho JH, et al. Decoding tumor phenotypes for ALK, ROS1, and RET fusions in lung adenocarcinoma using a radiomics approach[J]. Medicine (Baltimore), 2015, 94(41):e1753. http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=5df4d861704b48084bac970554c3c269 [37] Hong D, Xu K, Zhang L, et al. Radiomics signature as a predictive factor for EGFR mutations in advanced lung adenocarcinoma[J]. Front Oncol, 2020, (10):28. http://cn.bing.com/academic/profile?id=13c80b356c362271dac5b52caf9691e0&encoded=0&v=paper_preview&mkt=zh-cn [38] Nair JKR, Saeed UA, McDougall CC, et al. Radiogenomic models using machine learning techniques to predict EGFR mutations in non-small cell lung cancer[J]. Can Assoc Radiol J, 2020.[Epub ahead of print] http://cn.bing.com/academic/profile?id=6271445b855b374453f54257affaeb79&encoded=0&v=paper_preview&mkt=zh-cn [39] Wang S, Shi JY, Ye ZX, et al. Predicting EGFR mutation status in lung adenocarcinoma on computed tomography image using deep learning[J]. Eur Respir J, 2019, 53(3). Doi: 10.1183/13993003.00986-2018 [40] Li XY, Xiong JF, Jia TY, et al. Detection of epithelial growth factor receptor (EGFR) mutations on CT images of patients with lung adenocarcinoma using radiomics and/or multi-level residual convolutionary neural networks[J]. J Thorac Dis, 2018, 10(12):6624-6635. http://cn.bing.com/academic/profile?id=0844a5a63af648c6a5e2bf824fed25a7&encoded=0&v=paper_preview&mkt=zh-cn [41] Mei DD, Luo Y, Wang Y, et al. CT texture analysis of lung adenocarcinoma:can Radiomic features be surrogate biomarkers for EGFR mutation statuses[J]. Cancer Imaging, 2018, 18(1):52. http://cn.bing.com/academic/profile?id=7f75297cda6d85d5ca78773a1452c2d7&encoded=0&v=paper_preview&mkt=zh-cn [42] Zhao W, Wu YZ, Xu YN, et al. The potential of radiomics nomogram in non-invasively prediction of epidermal growth factor receptor mutation status and subtypes in lung adenocarcinoma[J]. Front Oncol, 2020.[Epub ahead of print] http://cn.bing.com/academic/profile?id=fe26b198eaa0f3fd9ed8eddd74f163ab&encoded=0&v=paper_preview&mkt=zh-cn
点击查看大图
计量
- 文章访问数: 216
- HTML全文浏览量: 17
- PDF下载量: 36
- 被引次数: 0