浏览全部资源
扫码关注微信
1.西北大学 信息科学与技术学院,陕西 西安 710127
2.西北大学 文化遗产数字化国家地方联合工程研究中心,陕西 西安 710127
Received:25 January 2022,
Revised:17 February 2022,
Published:10 May 2022
移动端阅览
杨嘉楠,王忠昊,王昊霖等.改进BYOL的非小细胞肺癌表皮生长因子受体基因突变预测[J].光学精密工程,2022,30(09):1080-1090.
YANG Jianan,WANG Zhonghao,WANG Haolin,et al.Improved BYOL method for predicting epidermal growth factor receptor gene mutations in non-small cell lung cancer[J].Optics and Precision Engineering,2022,30(09):1080-1090.
杨嘉楠,王忠昊,王昊霖等.改进BYOL的非小细胞肺癌表皮生长因子受体基因突变预测[J].光学精密工程,2022,30(09):1080-1090. DOI: 10.37188/OPE.20223009.1080.
YANG Jianan,WANG Zhonghao,WANG Haolin,et al.Improved BYOL method for predicting epidermal growth factor receptor gene mutations in non-small cell lung cancer[J].Optics and Precision Engineering,2022,30(09):1080-1090. DOI: 10.37188/OPE.20223009.1080.
通过表皮生长因子受体(Epidermal Growth Factor Receptor,EGFR)突变情况可以对患者是否患有非小细胞肺癌(Non-small Cell Lung Cancer, NSCLC)进行检测。提出了一种基于对比学习的自监督EGFR基因突变预测方法,在不需要大量专家手工标注患者数据集的情况下,对输入网络的患者病灶区图像进行阴性、阳性预测。对自监督BYOL网络进行修改,增加了网络投影层非线性多层感知器(Multilayer Perceptron,MLP)的层数,并将患者CT和PET两个模态的图像数据融合作为网络的输入,在不需要大量标注患者数据集的情况下,对阴性、阳性病例进行预测。在非小细胞肺癌EGFR基因突变数据集上,与传统的影像组学、有监督VGG-16网络、有监督ResNet-50、有监督Inception v3和无监督迁移学习CAE进行对比。实验结果表明,使用对比学习从患者的CT和PET图像学习到的患者病灶区图像的实例特征可以对阴性、阳性病例进行区分,并取得了77%的曲线下面积(Area Under the Curve,AUC);相对于传统的影像组学方法分类结果AUC提高了7%,相对于有监督VGG-16网络的分类结果AUC提高了5%;在不需要大量专家手工标注数据集及大量患者临床数据的情况下仅比有监督ResNet-50 AUC低9%。改进BYOL网络仅需要少量标注的患者数据集便可得到比部分传统有监督方法更准确的检测结果,展示了其辅助临床决策的潜力。
The epidermal growth factor receptor (EGFR) mutation status can predict whether a patient has non-small cell lung cancer (NSCLC). A self-supervised EGFR gene mutation prediction method based on contrastive learning is proposed, which can distinguish between negative and positive images of the patient’s lesion area input to the network, without requiring a large number of expert hand-labeled patient datasets. The self-supervised BYOL network was modified to increase the number of layers of the non-linear multilayer perceptron (MLP) of the network projection layer, and image data of the patient's CT and PET modalities were merged as the input of the network. Negative and positive medical records can be predicted without the need to annotate a large number of patient datasets. Using the non-small cell lung cancer EGFR gene mutation datasets, it is compared with traditional radiomics, supervised VGG-16 network, supervised ResNet-50 network, supervised Inception v3 network, and unsupervised transfer learning CAE. The experimental results show that the instance features of patient lesion area images learned from CT and PET images of patients using contrastive learning can be used to distinguish negative and positive cases, with an area under the curve (AUC) of 77%. The classification results improved by AUC of 7% compared to the traditional radiomics method, and by AUC of 5% compared to the classification results of the supervised VGG-16 network. The AUC is only 9% lower than that of supervised ResNet-50, without requiring a large number of expert hand-annotated datasets and large patient clinical datasets. The improved BYOL network proposed in this paper requires only a small number of labeled patient datasets to obtain more accurate prediction results than some traditional supervised methods, demonstrating its potential to help clinical decision-making.
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 . doi: 10.3322/caac.21492 http://dx.doi.org/10.3322/caac.21492
CHEN W Q , ZHENG R S , BAADE P D , et al . Cancer statistics in China, 2015 [J]. CA: A Cancer Journal for Clinicians , 2016 , 66 ( 2 ): 115 - 132 . doi: 10.3322/caac.21338 http://dx.doi.org/10.3322/caac.21338
郑荣寿 , 孙可欣 , 张思维 , 等 . 2015年中国恶性肿瘤流行情况分析 [J]. 中华肿瘤杂志 , 2019 , 41 ( 1 ): 19 - 28 . doi: 10.3760/cma.j.issn.0253-3766.2019.01.005 http://dx.doi.org/10.3760/cma.j.issn.0253-3766.2019.01.005
ZHENG R SH , SUN K X , ZHANG S W , et al . Report of cancer epidemiology in China, 2015 [J]. Chinese Journal of Oncology , 2019 , 41 ( 1 ): 19 - 28 . (in Chinese) . doi: 10.3760/cma.j.issn.0253-3766.2019.01.005 http://dx.doi.org/10.3760/cma.j.issn.0253-3766.2019.01.005
HANAHAN D , WEINBERG R A . Hallmarks of cancer: the next generation [J]. Cell , 2011 , 144 ( 5 ): 646 - 674 . doi: 10.1016/j.cell.2011.02.013 http://dx.doi.org/10.1016/j.cell.2011.02.013
BARR KUMARAKULASINGHE N , ZANWIJK NVAN , SOO R A . Molecular targeted therapy in the treatment of advanced stage non-small cell lung cancer (NSCLC) [J]. Respirology , 2015 , 20 ( 3 ): 370 - 378 . doi: 10.1111/resp.12490 http://dx.doi.org/10.1111/resp.12490
SHI Y K , WANG L , HAN B H , et al . First-line icotinib versus cisplatin/pemetrexed plus pemetrexed maintenance therapy for patients with advancedEGFR mutation-positive lung adenocarcinoma (CONVINCE): a phase 3, open-label, randomized study [J]. Annals of Oncology , 2017 , 28 ( 10 ): 2443 - 2450 . doi: 10.1093/annonc/mdx359 http://dx.doi.org/10.1093/annonc/mdx359
郑军 , 谢贵元 , 李姣 , 等 . 非小细胞肺癌EGFR基因突变的临床意义研究 [J]. 中国肿瘤临床 , 2014 , 41 ( 14 ): 904 - 907 . doi: 10.3969/j.issn.1000-8179.20140495 http://dx.doi.org/10.3969/j.issn.1000-8179.20140495
ZHENG J , XIE G Y , LI J , et al . Clinical significance of EGFR mutations in non-small cell lung cancer [J]. Chinese Journal of Clinical Oncology , 2014 , 41 ( 14 ): 904 - 907 . (in Chinese) . doi: 10.3969/j.issn.1000-8179.20140495 http://dx.doi.org/10.3969/j.issn.1000-8179.20140495
BOELLAARD R . Standards for PET image acquisition and quantitative data analysis [J]. Journal of Nuclear Medicine: Official Publication , Society of Nuclear Medicine, 2009 , 50 ( Suppl 1 ): 11S - 20S . doi: 10.2967/jnumed.108.057182 http://dx.doi.org/10.2967/jnumed.108.057182
KUMAR R , XIU Y , YU J Q , et al . 18F-FDG PET in evaluation of adrenal lesions in patients with lung cancer [J]. Journal of Nuclear Medicine: Official Publication , Society of Nuclear Medicine, 2004 , 45 ( 12 ): 2058 - 2062 .
KONINGS R , GOOL M HVAN , BARD M P L , et al . Prognostic value of pre-operative glucose-corrected maximum standardized uptake value in patients with non-small cell lung cancer after complete surgical resection and 5-year follow-up [J]. Annals of Nuclear Medicine , 2016 , 30 ( 5 ): 362 - 368 . doi: 10.1007/s12149-016-1070-2 http://dx.doi.org/10.1007/s12149-016-1070-2
SHI X R , MENG X , SUN X D , et al . PET/CT imaging-guided dose painting in radiation therapy [J]. Cancer Letters , 2014 , 355 ( 2 ): 169 - 175 . doi: 10.1016/j.canlet.2014.07.042 http://dx.doi.org/10.1016/j.canlet.2014.07.042
李嘉威 , 李夏东 , 陈雪琴 , 等 . CT影像组学在肺癌诊治中应用的研究进展和问题探索 [J]. 中国肺癌杂志 , 2020 , 23 ( 10 ): 904 - 908 . doi: 10.3779/j.issn.1009-3419.2020.101.36 http://dx.doi.org/10.3779/j.issn.1009-3419.2020.101.36
LI J W , LI X D , CHEN X Q , et al . Research advances and obstacles of CT-based radiomics in diagnosis and treatment of lung cancer [J]. Chinese Journal of Lung Cancer , 2020 , 23 ( 10 ): 904 - 908 . (in Chinese) . doi: 10.3779/j.issn.1009-3419.2020.101.36 http://dx.doi.org/10.3779/j.issn.1009-3419.2020.101.36
ZHANG L W , CHEN B J , LIU X , et al . Quantitative biomarkers for prediction of epidermal growth factor receptor mutation in non-small cell lung cancer [J]. Translational Oncology , 2018 , 11 ( 1 ): 94 - 101 . doi: 10.1016/j.tranon.2017.10.012 http://dx.doi.org/10.1016/j.tranon.2017.10.012
HU N , WANG G , WU Y H , et al . LDA-SVM-based EGFR mutation model for NSCLC brain metastases [J]. Medicine , 2015 , 94 ( 5 ): e375 . doi: 10.1097/md.0000000000000375 http://dx.doi.org/10.1097/md.0000000000000375
胡丽霞 , 江长思 , 罗燕 , 等 . 基于机器学习的放射组学预测非小细胞肺癌EGFR基因突变 [J]. 医学影像学杂志 , 2019 , 29 ( 7 ): 1128 - 1131 .
HU L X , JIANG CH S , LUO Y , et al . Machine learning-based radiomics predicts EGFR Gene Mutation in non-small cell lung cancer [J]. Journal of Medical Imaging , 2019 , 29 ( 7 ): 1128 - 1131 . (in Chinese)
SHIRI I , MALEKI H , HAJIANFAR G , et al . PET/CT radiomic sequencer for prediction of EGFR and KRAS mutation status in NSCLC patients [C]. 2018 IEEE Nuclear Science Symposium and Medical Imaging Conference Proceedings . 1017,2018 , Sydney, NSW, Australia . IEEE , 2018 : 1 - 4 . doi: 10.1109/nssmic.2018.8824469 http://dx.doi.org/10.1109/nssmic.2018.8824469
肖术明 , 王绍举 , 常琳 , 等 . 面向手写数字图像的压缩感知快速分类 [J]. 光学 精密工程 , 2021 , 29 ( 7 ): 1709 - 1719 . doi: 10.37188/OPE.20212907.1709 http://dx.doi.org/10.37188/OPE.20212907.1709
XIAO SH M , WANG SH J , CHANG L , et al . Compressive sensing fast classification for handwritten digital images [J]. Opt. Precision Eng. , 2021 , 29 ( 7 ): 1709 - 1719 . (in Chinese) . doi: 10.37188/OPE.20212907.1709 http://dx.doi.org/10.37188/OPE.20212907.1709
吕晓琪 , 吴凉 , 谷宇 , 等 . 基于三维卷积神经网络的低剂量CT肺结节检测 [J]. 光学 精密工程 , 2018 , 26 ( 5 ): 1211 - 1218 . doi: 10.3788/OPE.20182605.1211 http://dx.doi.org/10.3788/OPE.20182605.1211
LÜ X Q , WU L , GU Y , et al . Detection of low dose CT pulmonary nodules based on 3D convolution neural network [J]. Opt. Precision Eng. , 2018 , 26 ( 5 ): 1211 - 1218 . (in Chinese) . doi: 10.3788/OPE.20182605.1211 http://dx.doi.org/10.3788/OPE.20182605.1211
WANG Y J , HUA X Y , WANG Y , et al . Mut-Detecter: an EGFR activating mutation type classification method with a deep convolutional neural network [C]. 2020 IEEE International Conference on Bioinformatics and Biomedicine . 1619,2020 , Seoul , Korea (South) . IEEE , 2020 : 2386 - 2389 . doi: 10.1109/bibm49941.2020.9313577 http://dx.doi.org/10.1109/bibm49941.2020.9313577
SILVA F , PEREIRA T , MORGADO J , et al . EGFR assessment in lung cancer CT images: analysis of local and holistic regions of interest using deep unsupervised transfer learning [J]. IEEE Access , 2021 , 9 : 58667 - 58676 . doi: 10.1109/access.2021.3070701 http://dx.doi.org/10.1109/access.2021.3070701
MISRA I , MAATEN LVAN DER . Self-supervised learning of pretext-invariant representations [C]. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 1319,2020 , Seattle, WA, USA. IEEE , 2020 : 6706 - 6716 . doi: 10.1109/cvpr42600.2020.00674 http://dx.doi.org/10.1109/cvpr42600.2020.00674
OORD A V D , LI Y Z , VINYALS O . Representation learning with contrastive predictive coding [EB/OL]. 2018: arXiv : 1807 .03748[cs.LG]. https://arxiv.org/abs/1807.03748 https://arxiv.org/abs/1807.03748
CHEN T , KORNBLITH S , NOROUZI M , et al . A simple framework for contrastive learning of visual representations [EB/OL]. 2020: arXiv : 2002 .05709[cs.LG]. https://arxiv.org/abs/2002.05709 https://arxiv.org/abs/2002.05709
HE K M , FAN H Q , WU Y X , et al . Momentum contrast for unsupervised visual representation learning [C]. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 1319,2020 , Seattle, WA, USA. IEEE , 2020 : 9726 - 9735 . doi: 10.1109/cvpr42600.2020.00975 http://dx.doi.org/10.1109/cvpr42600.2020.00975
CARON M , MISRA I , MAIRAL J , et al . Unsupervised learning of visual features by contrasting cluster assignments [EB/OL]. 2020: arXiv : 2006 .09882[cs.CV]. https://arxiv.org/abs/2006.09882 https://arxiv.org/abs/2006.09882
CHEN X L , HE K M . Exploring simple Siamese representation learning [C]. 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2025,2021 , Nashville, TN, USA. IEEE , 2021 : 15745 - 15753 . doi: 10.1109/cvpr46437.2021.01549 http://dx.doi.org/10.1109/cvpr46437.2021.01549
GRILL J B , STRUB F , ALTCHÉ F , et al . Bootstrap your own latent: a new approach to self-supervised learning [EB/OL]. 2020: arXiv : 2006 .07733[cs.LG]. https://arxiv.org/abs/2006.07733 https://arxiv.org/abs/2006.07733
慕晓冬 , 白坤 , 尤轩昂 , 等 . 基于对比学习方法的遥感影像特征提取与分类 [J]. 光学 精密工程 , 2021 , 29 ( 9 ): 2222 - 2234 . doi: 10.37188/OPE.20212909.2222 http://dx.doi.org/10.37188/OPE.20212909.2222
MU X D , BAI K , YOU X A , et al . Remote sensing image feature extraction and classification based on contrastive learning method [J]. Opt. Precision Eng. , 2021 , 29 ( 9 ): 2222 - 2234 . (in Chinese) . doi: 10.37188/OPE.20212909.2222 http://dx.doi.org/10.37188/OPE.20212909.2222
SHIN H B , SHEEN H , LEE H Y , et al . Digital Imaging and Communications in Medicine (DICOM) information conversion procedure for SUV calculation of PET scanners with different DICOM header information [J]. Physica Medica , 2017 , 44 : 243 - 248 . doi: 10.1016/j.ejmp.2017.05.063 http://dx.doi.org/10.1016/j.ejmp.2017.05.063
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 . 2730,2016 , Las Vegas, NV, USA . IEEE , 2016 : 770 - 778 . doi: 10.1109/cvpr.2016.90 http://dx.doi.org/10.1109/cvpr.2016.90
刘佳珺 , 李彪 . PET-CT在非小细胞肺癌EGFR分子靶向治疗疗效预测的应用价值 [J]. 中国实用内科杂志 , 2019 , 39 ( 2 ): 189 - 192 . doi: 10.19538/j.nk2019020501 http://dx.doi.org/10.19538/j.nk2019020501
LIU J J , LI B . Value of PET-CT in EGFR molecular targeting treatment in non-small cell lung cancer [J]. Chinese Journal of Practical Internal Medicine , 2019 , 39 ( 2 ): 189 - 192 . (in Chinese) . doi: 10.19538/j.nk2019020501 http://dx.doi.org/10.19538/j.nk2019020501
刘寒冰 , 赵杰 , 胡春峰 , 等 . PET/CT纹理分析在预测非小细胞肺癌EGFR基因突变中的应用 [J]. 临床放射学杂志 , 2020 , 39 ( 9 ): 1759 - 1763 .
LIU H B , ZHAO J , HU CH F , et al . The application of PET/CT combined texture analysis in predicting EGFR gene mutation in non-small cell lung cancer [J]. Journal of Clinical Radiology , 2020 , 39 ( 9 ): 1759 - 1763 . (in Chinese)
曾樊顺 , 于丽娟 , 马敬全 , 等 . 18 F-FDG PET/CT在预测非小细胞肺癌EGFR突变中的价值 [J]. 现代肿瘤医学 , 2019 , 27 ( 5 ): 787 - 790 . doi: 10.3969/j.issn.1672-4992.2019.05.018 http://dx.doi.org/10.3969/j.issn.1672-4992.2019.05.018
ZENG F SH , YU L J , MA J Q , et al . Value of 18 F-FDG PET/CT in predicting EGFR mutations in non-small cell lung cancer [J]. Journal of Modern Oncology , 2019 , 27 ( 5 ): 787 - 790 . (in Chinese) . doi: 10.3969/j.issn.1672-4992.2019.05.018 http://dx.doi.org/10.3969/j.issn.1672-4992.2019.05.018
王云华 , 姜阳 . 18 F-FDG PET/CT显像评估非小细胞肺癌EGFR基因突变的研究现状 [J]. 医学临床研究 , 2020 , 37 ( 7 ): 961 - 964 .
WANG Y H , JIANG Y . Assessment of EGFR gene mutations in non-small cell lung cancer by 18 F-FDG PET/CT imaging [J]. Journal of Clinical Research , 2020 ( 7 ): 961 - 964 . (in Chinese)
尹国涛 , 徐文贵 , 李小凤 . 18 F-FDG PET/CT在非小细胞肺癌EGFR突变状态预测中的应用价值 [J]. 中华核医学与分子影像杂志 , 2019 , 39 ( 10 ): 623 - 626 .
YIN G T , XU W G , LI X F . Application value of 18 F-FDG PET/CT in predicting EGFR mutation status in non-small cell lung cancer [J]. Chinese Journal of Nuclear Medicine and Molecular Imaging , 2019 , 39 ( 10 ): 623 - 626 . (in Chinese)
PINSKY P . Re: Is the area under an ROC curve a valid measure of the performance of a screening or diagnostic test? [J]. Journal of Medical Screening , 2014 , 21 ( 4 ): 219 . doi: 10.1177/0969141314548907 http://dx.doi.org/10.1177/0969141314548907
WALD N J , BESTWICK J P . Is the area under an ROC curve a valid measure of the performance of a screening or diagnostic test? [J]. Journal of Medical Screening , 2014 , 21 ( 1 ): 51 - 56 . doi: 10.1177/0969141313517497 http://dx.doi.org/10.1177/0969141313517497
0
Views
743
下载量
0
CSCD
Publicity Resources
Related Articles
Related Author
Related Institution