分享:
分享到微信朋友圈
X
综述
基于磁共振成像的影像组学在肺癌中的研究进展
江叶海 蒲豆豆 于楠

Cite this article as: JIANG Y H, PU D D, YU Nan. Research progress of MRI based radiomics in lung cancer[J]. Chin J Magn Reson Imaging, 2023, 14(7): 166-170.本文引用格式:江叶海, 蒲豆豆, 于楠. 基于磁共振成像的影像组学在肺癌中的研究进展[J]. 磁共振成像, 2023, 14(7): 166-170. DOI:10.12015/issn.1674-8034.2023.07.030.


[摘要] 计算机断层扫描(computed tomography, CT)、正电子发射断层扫描和磁共振成像(magnetic resonance imaging, MRI)等技术在肺癌诊断、分期、治疗、术后监测和反应评估等方面具有重要意义,提供了肺癌表型的解剖和功能信息,但仍有大量的遗传和预后信息未被揭示。影像组学可深度挖掘高维数据,反映病变的分子表达和基因表达等深层生物学信息,有助于肺癌预后评估和疗效评估等精准预测。过去,肺癌影像组学常基于CT图像展开研究。随着肺部MRI技术的不断进步,其软组织分辨率得到显著提高,因此MRI也开始被广泛应用于肺癌影像组学研究。本文将从MRI肺癌影像组学的模型构建以及影像组学在肺癌鉴别、分型、病理分级、基因表达等方面进行介绍,并阐述当前肺部MRI影像组学的局限性与展望,以期为肺癌临床精准诊疗提供新的方法,促进影像组学研究的临床应用。
[Abstract] Technologies such as computed tomography (CT), positron emission tomography, and magnetic resonance imaging (MRI) play an important role in the diagnosis, staging, treatment, postoperative monitoring, and response evaluation of lung cancer, providing anatomical and functional information about the phenotype of lung cancer. However, a large amount of genetic and prognostic information remains undiscovered. Radiomics can deeply mine high-dimensional data, reflecting deep biological information such as molecular and gene expression of lesions, which can help in the accurate prediction of lung cancer prognosis and treatment efficacy. In the past, lung cancer radiomics studies were mainly based on CT images. With the continuous improvement of lung MRI technology and its significant increase in soft tissue resolution, magnetic resonance imaging has also been widely used in lung cancer radiomics research. This article will introduce the model construction of MRI lung cancer radiomics and the application of radiomics in lung cancer differentiation, classification, pathological grading, gene expression, etc., and discuss the current limitations and prospects of lung MRI radiomics, in order to provide new methods for the precise diagnosis and treatment of lung cancer and promote the clinical application of radiomics research.
[关键词] 磁共振成像;影像组学;肺癌;肺结节;特征提取;基因表型;病理分级
[Keywords] magnetic resonance imaging;radiomics;lung cancer;pulmonary nodules;feature extraction;gene phenotype;pathological grade

江叶海 1   蒲豆豆 1   于楠 1, 2*  

1 陕西中医药大学医学技术学院,咸阳 712046

2 陕西中医药大学附属医院医学影像科,咸阳 712000

通信作者:于楠,E-mail:yunan0512@sina.com

作者贡献声明:江叶海起草和撰写稿件,获取、分析或解释本研究的文献;蒲豆豆对稿件重要的内容进行了修改;于楠设计本综述的方案,对稿件重要的内容进行了修改;江叶海获得国家级大学生创新创业训练计划项目资助;于楠获得陕西省重点研发计划项目和陕西省自然科学基础研究计划项目资助。全体作者都同意最后的修改稿发表,都同意对本研究的所有方面负责,确保本研究的准确性和诚信。


基金项目: 陕西省重点研发计划项目 2021ZDLSF04-10 陕西省自然科学基础研究计划 2022JM-453 国家级大学生创新创业训练计划 202210716013
收稿日期:2022-11-29
接受日期:2023-06-26
中图分类号:R445.2  R734.2 
文献标识码:A
DOI: 10.12015/issn.1674-8034.2023.07.030
本文引用格式:江叶海, 蒲豆豆, 于楠. 基于磁共振成像的影像组学在肺癌中的研究进展[J]. 磁共振成像, 2023, 14(7): 166-170. DOI:10.12015/issn.1674-8034.2023.07.030.

0 前言

       肺癌是全球死亡率最高的恶性肿瘤。研究表明,早期肺癌手术治疗后的五年生存率为45%~65%,晚期肺癌非手术治疗后的五年生存率为5%~10%[1, 2]。目前,肺癌的早期诊断主要依靠胸部断层计算机扫描(computed tomography, CT)检查。然而,具有电离辐射效应的胸部CT具有致癌风险,约2%的癌症与电离辐射有关[3]。磁共振成像(magnetic resonance imaging, MRI)作为一种无辐射的扫描技术,可以同时反映形态和功能信息,在肺癌的评估、诊断、鉴别诊断、分期等方面显示出良好的应用价值[4, 5, 6, 7, 8]。CT、正电子发射断层扫描和MRI等技术在肺癌诊断、分期、治疗决策、术后监测和反应评估等方面具有重要意义,提供了肺癌表型的解剖和功能信息,但仍有大量的遗传和预后信息未被揭示。影像组学从医学图像中挖掘高维的数据,提取定量特征,反映了病变细胞形态、分子表达和基因表达等生物学信息,有助于疾病诊断、预后和疗效评估等[9]。许多研究已经尝试使用定量影像组学特征进行诊断或预后评估,如肺、脑、前列腺和乳腺[10, 11, 12]

       目前影像组学分析在肺癌诊断、分型、疗效评估和预后预测中发挥着重要作用,但主要是基于CT图像[13, 14]。然而,近年来随着MRI技术和影像组学的不断发展,基于MRI的影像组学分析在肺部的研究逐渐增加。笔者将对近年来影像组学在肺癌中的模型构建以及影像组学在肺癌鉴别、分型、病理分级、基因表达等方面的应用进行总结,以期为肺癌精准诊断、疗效评估和预后评估提供新的方法,为临床诊疗提供更多的信息,促进影像组学的临床应用。

1 肺癌MRI影像组学的模型选择

       影像组学将医学图像转化为可深度挖掘的高通量特征数据,并分析图像特征帮助临床决策[15]。其流程为医学图像的获取及重建、图像分割、特征提取和模型构建[16]。图像分割的准确性是决定模型性能的重要因素。图像分割包括手动分割、半自动化分割及自动分割。手动分割是黄金标准,但是存在效率低、重复性和一致性差等问题。自动分割具有一致性好、重复性高、效率高的特点,但是其分割准确度较低,因此目前多采用半自动图像分割方法。既往研究多是基于整个病变进行病灶分割,没有考虑病变内的异质性[17, 18]。WANG等[19]将异质性分析融入影像组学模型,建立了基于病变异质性的病变分割模型,并与传统的基于整个病变的模型进行了比较,发现病变异质性模型能够提高结节或肿块良恶性鉴别能力。

       除图像分割外,影像组学模型的选择也至关重要。不同的机器学习方法在应用于不同的器官时可能会表现出不同的性能[20, 21, 22]。YIN等[23]报道最小绝对收缩和选择算法(least absolute shrinkage and selection operator, LASSO)和广义线性模型在区分骶骨脊索瘤和骶骨巨细胞瘤表现最好,而随机森林和极端梯度提升分类器在脑膜瘤的结肠微阵列基因表达和分级方面表现最好[20,22]。WANG等[17]对MRI影像组学模型的最佳机器学习方法进行了研究,发现基于多参数MRI的T1WI、T2WI和表观弥散系数(apparent diffusion coefficient, ADC)的影像组学分析方法在区分肺癌和良性病变方面表现出良好的性能,其中支持向量机(support vector machine, SVM)和特征递归消除(recursive feature elimination, RFE)算法在区分肺癌和良性病变方面具有最好的性能,其工作特征曲线的曲线下面积(area under the curve, AUC)为0.88。FENG等[24]的研究也验证了SVM算法在肺结节分割具有最佳性能,同时还优化SVM算法,缩短分割时间,提高图像分割的准确度[24]。此外,在胰腺和胶质瘤的研究中也发现SVM算法联合RFE算法能够获得最佳的图像分割效果[21,25]。虽然SVM分类器存在一些缺点,如对大型数据库复杂度明显增加,耗时较长,但对于小样本,SVM通常可以利用训练集中有限的数据集获得较好的结果。

       目前,肺癌MRI影像组学的主要难点在于图像分割。由于肺部MRI序列较多,手动和半自动分割的工作量大,效率较低,而自动分割虽然工作效率高,但准确度相对较低。深度学习分割算法通过端到端的训练,可以提高图像分割的效率和准确性,从而优化肺癌MRI预测模型的性能。将深度学习和影像组学相结合,可以为肺癌的诊疗提供更加精准的信息。此外,还可以融合基于病变异质性的分割模型,进一步提高预测模型的准确度。

2 MRI影像组学在肺癌鉴别诊断的应用

       随着人工智能软件和低剂量CT应用,肺结节的检出率明显上升,有数据表明体检肺结节阳性率可高达79%,但真正恶性的结节检出率仅0.44%[26]。目前已有许多研究证实了MRI在肺部疾病检出、诊断、疗效评估的作用[5,27, 28, 29, 30]。YANG等[31]学者对96例患者的T2WI图像进行手动分割,采用最大相关最小冗余算法和LASSO建立肺结节良恶性诊断模型,其模型在训练集和验证集中都获得了良好的鉴别诊断能力(AUC分别为0.82和0.71)。WANG等[17]也发现联合多参数MRI(T1WI、T2WI、ADC)的影像组学分析方法在区分肺癌和良性病变方面有良好的性能(AUC为0.88)。

       目前肺癌MRI影像组学主要采用T2WI图像、扩散加权成像(diffusion weighted imaging, DWI)图像和ADC图像,但是有研究指出DWI序列存在变形和局部漂移等问题,不利于影像组学特征的稳定性和可重复性[32]。纵向弛豫时间定量成像(longitudinal relaxation time mapping, T1 mapping)作为一种新的MRI定量技术,可以量化组织T1值,反映组织中水分子、蛋白多糖、等微小变化,且T1 mapping较少产生伪影、变形和位置偏移,具有良好的稳定性,有利于提取影像组学特征。VAN等[33]研究发现T1 mapping在评估结节形态方面与CT相当。既往研究也发现T1 mapping具有鉴别良恶性病变、肺癌组织学分级和病理分型的作用[34, 35, 36]。YAN等[37]基于T1 mapping图像采用SVM和逻辑回归的分类器模型对肺结节或肿块进行良恶性鉴别,发现其模型诊断效能良好(AUC均为0.82,准确率为80%),与DWI具有相似的诊断能力(AUC为0.88)。虽然T1 mapping序列的影像组学特征具有良好的稳定性和诊断效能,但是T1-mapping无法识别肿块和继发性阻塞性肺炎,而ADC序列可以完成肿块与阻塞性肺炎的鉴别,两者可相互补充。目前T1 mapping在肺部的应用还较少,其在肺癌诊断中的应用的可行性、重复性、准确度还需进一步研究,未来如果T1 mapping能够克服上述困难,则有望成为新的辅助工具。

       目前MRI影像组学的结节良恶性鉴别效能约为0.71~0.88,略低于CT影像组学效能,且MRI影像组学还存在肺部生理结构的影响,对于结节的分割存在一定的困难,但是MRI可作为诊断肺部肿瘤的辅助成像技术,尤其适用于CT无法诊断的肺实性病变患者、拒绝活检或者放疗后疗效评估患者。

3 MRI影像组学在肺癌分型和病理分级的应用

       由于腺癌和鳞癌组织特征、解剖部位以及葡萄糖代谢不同,因此,在进行治疗之前,确定非小细胞肺癌的组织亚型对于改善临床结果非常关键[38]。既往MRI图像中肺癌和鳞癌的鉴别主要依靠放射医生对形态学征象进行主观判断,观察者的内部与外部异质性较差[39, 40]。而影像组学可深入提取MRI数据下的定量特征[41, 42],以客观准确地区分腺癌和鳞癌。TANG等[43]对MRI影像组学在腺癌和鳞癌之间组织分布的差异进行研究,通过五种特征类别分别对T2WI、DWI、ADC图像进行特征提取,发现ADC图提取的特征绝对系数之和最高,且训练集和验证集均具有良好的识别性能,AUC分别为0.819和0.824。TANG等[43]还将吸烟史、大小、位置、癌胚抗原等临床特征与影像组学模型结合,进一步提高腺癌和鳞癌诊断性能[43]

       组织病理学分级在肺癌的生物学行为和预后疗效中也起着至关重要的作用。与高分化、低级别肺癌相比,低分化、高级别肺癌预后更差,淋巴结转移、局部复发和死亡的风险更高[44]。在预测肺癌风险方面,低剂量CT图像深度学习的研究取得了94.4%的准确率,但是它受到CT电离辐射问题的限制[45]。因此,学者们开始探索无辐射的MRI在肺癌组织分级的应用。TANG等[18]从ADC、DWI和T2WI图像中选取5个最优特征组成影像组学模型对非小细胞肺癌(non-small cell lung carcinoma, NSCLC)进行组织学分级,获得了良好的诊断性能(训练集和试验集的AUC分别为0.761、0.753),这与CT影像组学研究结果类似[46]。综上所述,MRI影像组学可用于肺癌的分型和病理分级,且其预测效能略低于CT,未来可以在无辐射的情况下利用MRI影像组学预测肺癌病理分级和亚型预测,指导肺癌患者后续治疗方案。

4 MRI影像组学在肺癌基因学中的应用

       NSCLC的发生、发展、侵袭和转移涉及多种基因,目前最常研究的NSCLC驱动基因为表皮生长因子受体(epidermal growth factor receptor, EGFR),其在亚洲人群中突变率约为50%[47],同时EGFR也是NSCLC治疗中最常使用的靶向基因。YUAN等[48]学者使用体素内非相干运动(intravoxel incoherent motion, IVIM)和扩散峰度成像(diffusion kurtosis imaging, DKI)结合直方图预测肺腺癌患者EGFR突变率,发现IVIM和DKI参数有助于区分ⅢA-Ⅳ期肺腺癌的EGFR突变状态,验证了肺部MRI在预测EGFR突变的可行性,但是直方图分析属于半定量分析,依赖于放射科医生的诊断水平,具有一定的主观判断。WANG等[49]采用LASSO和logistic回归建立了EGFR预测模型,研究发现ADC模型的EGFR预测性能最好(AUC为0.805),同时联合T2WI、DWI、ADC三种图像可进一步提高肺腺癌患者EGFR突变的预测能力(AUC测试为0.838),与基于CT图像的EGFR预测效能(AUC为0.72~0.851)相似。综上所述,后续可以联合多个MRI序列展开肺癌基因表型的研究,增强模型的泛化性能,提高肺癌影像组学的应用范围。

5 不足与展望

       基于CT的肺癌影像组学仍是热点,其模型诊断效能、临床可实施性和可操作性具有一定的优势临床可实施性。MRI具有软组织分辨率高、多序列成像和功能成像的优势,可在肺癌的生存复发预测和疗效评估预测方面为临床诊断和治疗提供更多的功能和代谢信息,弥补CT影像组学的不足,二者联合使用可达到更好的诊断效能。

       肺癌MRI影像组学在疾病分型、病理学分级和基因表型中取得了较好的表现,具有良好的应用前景。然而,目前多数肺癌MRI影像组学研究的样本量不大,影像组学分析受操作者主观影响较大,其自定义特征参数的选择、感兴趣区勾画及分析方法等需要进一步规范及标准化。其次,图像分割仍是研究重点,深度学习可在一定程度上克服影像组学与临床实施间的困难,未来可联合影像组学和深度学习构建预测模型,进一步提高模型的诊断效能。最后,肺癌MRI影像组学研究主要以肺分割和病灶分割为主,在肺癌的定性诊断和定量分析方面较少,未来可联合Ki-67、ALK融合基因和血清学指标等临床指标对肺癌进行基因表型预测、预后评估和疗效评估。相信未来影像组学和人工智能将成为肺癌精准医疗和个性化治疗策略的有力支持。

[1]
MEIER-SCHROERS M, HOMSI R, GIESEKE J, et al. Lung cancer screening with MRI: evaluation of MRI for lung cancer screening by comparison of LDCT- and MRI-derived Lung-RADS categories in the first two screening rounds[J]. Eur Radiol, 2019, 29(2): 898-905. DOI: 10.1007/s00330-018-5607-8.
[2]
MEIER-SCHROERS M, HOMSI R, SCHILD H H, et al. Lung cancer screening with MRI: characterization of nodules with different non-enhanced MRI sequences[J]. Acta Radiol, 2019, 60(2): 168-176. DOI: 10.1177/0284185118778870.
[3]
KOO C W, LU A M, TAKAHASHI E A, et al. Can MRI contribute to pulmonary nodule analysis?[J/OL]. J Magn Reson Imaging, 2019, 49(7): e256-e264 [2022-11-28]. https://onlinelibrary.wiley.com/doi/10.1002/jmri.26587. DOI: 10.1002/jmri.26587.
[4]
MEI C L, ZHANG L, ZHANG Z Y. Vomiting management and effect prediction after early chemotherapy of lung cancer with diffusion-weighted imaging under artificial intelligence algorithm and comfort care intervention[J/OL]. Comput Math Methods Med, 2022, 2022: 1-11 [2022-11-28]. https://www.hindawi.com/journals/cmmm/2022/1056910/. DOI: 10.1155/2022/1056910.
[5]
OHNO Y, TAKENAKA D, YOSHIKAWA T, et al. Efficacy of ultrashort echo time pulmonary MRI for lung nodule detection and lung-RADS classification[J]. Radiology, 2022, 302(3): 697-706. DOI: 10.1148/radiol.211254.
[6]
RENZ D M, HERRMANN K H, KRAEMER M, et al. Ultrashort echo time MRI of the lung in children and adolescents: comparison with non-enhanced computed tomography and standard post-contrast T1w MRI sequences[J]. Eur Radiol, 2022, 32(3): 1833-1842. DOI: 10.1007/s00330-021-08236-7.
[7]
USUDA K, IWAI S, YAMAGATA A, et al. Novel insights of T2-weighted imaging: significance for discriminating lung cancer from benign pulmonary nodules and masses[J/OL]. Cancers (Basel), 2021, 13(15): 3713 [2022-11-28]. https://pubmed.ncbi.nlm.nih.gov/34359616/. DOI: 10.3390/cancers13153713.
[8]
ZHENG Y, LI J, CHEN K, et al. Comparison of conventional DWI, intravoxel incoherent motion imaging, and diffusion kurtosis imaging in differentiating lung lesions[J/OL]. Front Oncol, 2021, 11: 815967 [2022-11-28]. https://pubmed.ncbi.nlm.nih.gov/35127530/. DOI: 10.3389/fonc.2021.815967.
[9]
LAMBIN P, LEIJENAAR R T H, DEIST T M, et al. Radiomics: the bridge between medical imaging and personalized medicine[J]. Nat Rev Clin Oncol, 2017, 14(12): 749-762. DOI: 10.1038/nrclinonc.2017.141.
[10]
BONEKAMP D, KOHL S, WIESENFARTH M, et al. Radiomic machine learning for characterization of prostate lesions with MRI: comparison to ADC values[J]. Radiology, 2018, 289(1): 128-137. DOI: 10.1148/radiol.2018173064.
[11]
FAN M, YUAN W, ZHAO W R, et al. Joint prediction of breast cancer histological grade and ki-67 expression level based on DCE-MRI and DWI radiomics[J]. IEEE J Biomed Health Inform, 2020, 24(6): 1632-1642. DOI: 10.1109/JBHI.2019.2956351.
[12]
KNIEP H C, MADESTA F, SCHNEIDER T, et al. Radiomics of brain MRI: utility in prediction of metastatic tumor type[J]. Radiology, 2019, 290(2): 479-487. DOI: 10.1148/radiol.2018180946.
[13]
LUO T, XU K, ZHANG Z, et al. Radiomic features from computed tomography to differentiate invasive pulmonary adenocarcinomas from non-invasive pulmonary adenocarcinomas appearing as part-solid ground-glass nodules[J]. Chung Kuo Yen Cheng Yen Chiu, 2019, 31(2): 329-338. DOI: 10.21147/j.issn.1000-9604.2019.02.07.
[14]
XU Y, LU L, LIN-NING L N, et al. Application of radiomics in predicting the malignancy of pulmonary nodules in different sizes[J]. AJR Am J Roentgenol, 2019, 213(6): 1213-1220. DOI: 10.2214/AJR.19.21490.
[15]
GILLIES R J, KINAHAN P E, HRICAK H. Radiomics: images are more than pictures, they are data[J]. Radiology, 2016, 278(2): 563-577. DOI: 10.1148/radiol.2015151169.
[16]
SALA E, MEMA E, HIMOTO Y, et al. Unravelling tumour heterogeneity using next-generation imaging: radiomics, radiogenomics, and habitat imaging[J]. Clin Radiol, 2017, 72(1): 3-10. DOI: 10.1016/j.crad.2016.09.013.
[17]
WANG X H, WAN Q, CHEN H J, et al. Classification of pulmonary lesion based on multiparametric MRI: utility of radiomics and comparison of machine learning methods[J]. Eur Radiol, 2020, 30(8): 4595-4605. DOI: 10.1007/s00330-020-06768-y.
[18]
TANG X, BAI G Y, WANG H, et al. Elaboration of multiparametric MRI-based radiomics signature for the preoperative quantitative identification of the histological grade in patients with non-small-cell lung cancer[J]. J Magn Reson Imaging, 2022, 56(2): 579-589. DOI: 10.1002/jmri.28051.
[19]
WANG X H, LI X C, CHEN H J, et al. Pulmonary MRI radiomics and machine learning: effect of intralesional heterogeneity on classification of lesion[J]. Acad Radiol, 2022, 29(Suppl 2): S73-S81. DOI: 10.1016/j.acra.2020.12.020.
[20]
MANIRUZZAMAN M, JAHANUR RAHMAN M, AHAMMED B, et al. Statistical characterization and classification of colon microarray gene expression data using multiple machine learning paradigms[J/OL]. Comput Methods Programs Biomed, 2019, 176: 173-193 [2022-11-28]. https://pubmed.ncbi.nlm.nih.gov/31200905/. DOI: 10.1016/j.cmpb.2019.04.008.
[21]
ZHANG X, YAN L F, HU Y C, et al. Optimizing a machine learning based glioma grading system using multi-parametric MRI histogram and texture features[J]. Oncotarget, 2017, 8(29): 47816-47830. DOI: 10.18632/oncotarget.18001.
[22]
HAMERLA G, MEYER H J, SCHOB S, et al. Comparison of machine learning classifiers for differentiation of grade 1 from higher gradings in meningioma: a multicenter radiomics study[J/OL]. Magn Reson Imaging, 2019, 63: 244-249 [2022-11-28]. https://pubmed.ncbi.nlm.nih.gov/31425811/. DOI: 10.1016/j.mri.2019.08.011.
[23]
YIN P, MAO N, ZHAO C, et al. Comparison of radiomics machine-learning classifiers and feature selection for differentiation of sacral chordoma and sacral giant cell tumour based on 3D computed tomography features[J]. Eur Radiol, 2019, 29(4): 1841-1847. DOI: 10.1007/s00330-018-5730-6.
[24]
FENG B, ZHANG M H, ZHU H L, et al. MRI image segmentation model with support vector machine algorithm in diagnosis of solitary pulmonary nodule[J/OL]. Contrast Media Mol Imaging, 2021, 2021: 9668836 [2022-11-28]. https://pubmed.ncbi.nlm.nih.gov/34377105/. DOI: 10.1155/2021/9668836.
[25]
ZHANG Y Q, CHENG C, LIU Z B, et al. Radiomics analysis for the differentiation of autoimmune pancreatitis and pancreatic ductal adenocarcinoma in 18F-FDG PET/CT[J]. Med Phys, 2019, 46(10): 4520-4530. DOI: 10.1002/mp.13733.
[26]
杨锋, 樊军, 田周俊逸, 等. 人群肺亚实性结节CT筛查及人工智能应用研究初探[J]. 中华胸心血管外科杂志, 2020, 36(3): 145-150. DOI: 10.3760/cma.j.cn112434-20191126-00420
YANG F, FAN J, TIAN Z, et al. Population-based research of pulmonary subsolid nodule CT screening and artificial intelligence application[J]. Chin J Thorac Cardiovasc Surg, 2020, 36(3): 145-150. DOI: 10.3760/cma.j.cn112434-20191126-00420
[27]
HATABU H, OHNO Y, GEFTER W B, et al. Expanding applications of pulmonary MRI in the clinical evaluation of lung disorders: fleischner society position paper[J]. Radiology, 2020, 297(2): 286-301. DOI: 10.1148/radiol.2020201138.
[28]
YU N, DUAN H F, YANG C B, et al. Free-breathing radial 3D fat-suppressed T1-weighted gradient echo (r-VIBE) sequence for assessment of pulmonary lesions: a prospective comparison of CT and MRI[J/OL]. Cancer Imaging, 2021, 21(1): 68 [2022-11-28]. https://pubmed.ncbi.nlm.nih.gov/34930463/. DOI: 10.1186/s40644-021-00441-3.
[29]
FANG T, MENG N, FENG P Y, et al. A comparative study of amide proton transfer weighted imaging and intravoxel incoherent motion MRI techniques versus (18) F-FDG PET to distinguish solitary pulmonary lesions and their subtypes[J]. J Magn Reson Imaging, 2022, 55(5): 1376-1390. DOI: 10.1002/jmri.27977.
[30]
HUANG Y S, NIISATO E, SU M M, et al. Detecting small pulmonary nodules with spiral ultrashort echo time sequences in 1.5 T MRI[J]. MAGMA, 2021, 34(3): 399-409. DOI: 10.1007/s10334-020-00885-x.
[31]
YANG S Y, WANG Y D, SHI Y X, et al. Radiomics nomogram analysis of T2-fBLADE-TSE in pulmonary nodules evaluation[J/OL]. Magn Reson Imaging, 2022, 85: 80-86 [2022-11-28]. https://pubmed.ncbi.nlm.nih.gov/34666158/. DOI: 10.1016/j.mri.2021.10.010.
[32]
JIANG J Q, YIN J B, CUI L, et al. Lung cancer: short-term reproducibility of intravoxel incoherent motion parameters and apparent diffusion coefficient at 3T[J]. J Magn Reson Imaging, 2018, 47(4): 1003-1012. DOI: 10.1002/jmri.25820.
[33]
VAN GRIETHUYSEN J J M, FEDOROV A, PARMAR C, et al. Computational radiomics system to decode the radiographic phenotype[J/OL]. Cancer Res, 2017, 77(21): e104-e107 [2022-11-20]. https://aacrjournals.org/cancerres/article-split/77/21/e104/662617. DOI: 10.1158/0008-5472.CAN-17-0339.
[34]
JIANG J Q, CUI L, XIAO Y, et al. B1-CorrectedT1 mapping in lung cancer: repeatability, reproducibility, and identification of histological types[J]. Magnetic Resonance Imaging, 2021, 54(5): 1529-1540. DOI: 10.1002/jmri.27844.
[35]
YANG S Y, SHAN F, YAN Q Q, et al. A pilot study of native T1-mapping for focal pulmonary lesions in 3.0 T magnetic resonance imaging: size estimation and differential diagnosis[J]. J Thorac Dis, 2020, 12(5): 2517-2528. DOI: 10.21037/jtd.2020.03.42.
[36]
LI G Z, HUANG R J, ZHU M, et al. Native T1-mapping and diffusion-weighted imaging (DWI) can be used to identify lung cancer pathological types and their correlation with Ki-67 expression[J]. J Thorac Dis, 2022, 14(2): 443-454. DOI: 10.21037/jtd-22-77.
[37]
YAN Q Q, YI Y Q, SHEN J, et al. Preliminary study of 3 T-MRI native T1-mapping radiomics in differential diagnosis of non-calcified solid pulmonary nodules/masses[J/OL]. Cancer Cell Int, 2021, 21(1): 539 [2022-11-20]. https://pubmed.ncbi.nlm.nih.gov/34663307/. DOI: 10.1186/s12935-021-02195-1.
[38]
ZHU X Z, DONG D, CHEN Z D, et al. Radiomic signature as a diagnostic factor for histologic subtype classification of non-small cell lung cancer[J]. Eur Radiol, 2018, 28(7): 2772-2778. DOI: 10.1007/s00330-017-5221-1.
[39]
BASHIR U, KAWA B, SIDDIQUE M, et al. Non-invasive classification of non-small cell lung cancer: a comparison between random forest models utilising radiomic and semantic features[J/OL]. Br J Radiol, 2019, 92(1099): 20190159 [2022-11-20]. https://pubmed.ncbi.nlm.nih.gov/31166787/. DOI: 10.1259/bjr.20190159.
[40]
LIU L P, ZHANG X X, CUI L B, et al. Preliminary comparison of diffusion-weighted MRI and PET/CT in predicting histological type and malignancy of lung cancer[J]. Clin Respir J, 2017, 11(2): 151-158. DOI: 10.1111/crj.12316.
[41]
XU X P, WANG H J, DU P, et al. A predictive nomogram for individualized recurrence stratification of bladder cancer using multiparametric MRI and clinical risk factors[J]. J Magn Reson Imaging, 2019, 50(6): 1893-1904. DOI: 10.1002/jmri.26749.
[42]
XU X P, ZHANG X, TIAN Q, et al. Quantitative identification of nonmuscle-invasive and muscle-invasive bladder carcinomas: a multiparametric MRI radiomics analysis[J]. J Magn Reson Imaging, 2019, 49(5): 1489-1498. DOI: 10.1002/jmri.26327.
[43]
TANG X, XU X P, HAN Z P, et al. Elaboration of a multimodal MRI-based radiomics signature for the preoperative prediction of the histological subtype in patients with non-small-cell lung cancer[J/OL]. BioMed Eng OnLine, 2020, 19(1): 5 [2022-11-20]. https://biomedical-engineering-online.biomedcentral.com/articles/10.1186/s12938-019-0744-0. DOI: 10.1186/s12938-019-0744-0.
[44]
SUN Z F, AUBRY M C, DESCHAMPS C, et al. Histologic grade is an independent prognostic factor for survival in non-small cell lung cancer: an analysis of 5018 hospital- and 712 population-based cases[J]. J Thorac Cardiovasc Surg, 2006, 131(5): 1014-1020. DOI: 10.1016/j.jtcvs.2005.12.057.
[45]
ARDILA D, KIRALY A P, BHARADWAJ S, et al. End-to-end lung cancer screening with three-dimensional deep learning on low-dose chest computed tomography[J]. Nat Med, 2019, 25(6): 954-961. DOI: 10.1038/s41591-019-0447-x.
[46]
CHEN X, FANG M J, DONG D, et al. A radiomics signature in preoperative predicting degree of tumor differentiation in patients with non-small cell lung cancer[J]. Acad Radiol, 2018, 25(12): 1548-1555. DOI: 10.1016/j.acra.2018.02.019.
[47]
ABDALLAH S M B, HIRSH V. Irreversible tyrosine kinase inhibition of epidermal growth factor receptor with afatinib in egfr activating mutation-positive advanced non-small-cell lung cancer[J]. Curr Oncol, 2018, 25(11): 9-17. DOI: 10.3747/co.25.3732.
[48]
YUAN M, PU X H, XU X Q, et al. Lung adenocarcinoma: assessment of epidermal growth factor receptor mutation status based on extended models of diffusion-weighted image[J]. J Magn Reson Imaging, 2017, 46(1): 281-289. DOI: 10.1002/jmri.25572.
[49]
WANG Y Z, WAN Q, XIA X Y, et al. Value of radiomics model based on multi-parametric magnetic resonance imaging in predicting epidermal growth factor receptor mutation status in patients with lung adenocarcinoma[J]. J Thorac Dis, 2021, 13(6): 3497-3508. DOI: 10.21037/jtd-20-3358.

上一篇 Gd-EOB-DTPA增强MRI评估肝细胞癌微血管转移模式的研究进展
下一篇 MRI影像组学在乳腺癌新辅助化疗中的应用进展
  
诚聘英才 | 广告合作 | 免责声明 | 版权声明
联系电话:010-67113815
京ICP备19028836号-2