分享:
分享到微信朋友圈
X
综述
宫颈癌影像组学研究进展
崔雅琼 王莉莉 赵莲萍 黄刚

Cite this article as: Cui YQ, Wang LL, Zhao LP, et al. Application progress of radiomics in cervical cancer. Chin J Magn Reson Imaging, 2020, 11(6): 477-480.本文引用格式:崔雅琼,王莉莉,赵莲萍,等.宫颈癌影像组学研究进展.磁共振成像, 2020, 11(6): 477-480. DOI:10.12015/issn.1674-8034.2020.06.020.


[摘要] 宫颈癌的发病率、死亡率较高并且逐渐增长,年轻化趋势明显,早期诊断和治疗变得尤为重要。治疗方式主要依据临床分期,相同临床病理特征的患者预后差异较大。影像组学因其无创、定量、快捷、动态、可重复的特点,可以为宫颈癌的诊断、预后等提供便利,帮助临床医生做出决策。笔者将从影像组学的工作流程、在宫颈癌诊治中的应用现状和发展前景进行综述。
[Abstract] The incidence and mortality of cervical cancer are high and increasing, the age of onset was significantly younger, therefore, early diagnosis and treatment become particularly important. The treatment depends on the clinical stage, and the prognosis of patients with the same clinicopathological characteristics are quite different. Radiomics can improve the diagnosis and prognosis of cervical cancer owing to its characteristics of noninvasive, quantitative, rapid, dynamic and repeatable, and help clinicians in making decisions. This paper will review the process of radiomics, the application status and development prospect of radiomics in cervical cancer.
[关键词] 影像组学;子宫颈肿瘤;磁共振成像
[Keywords] radiomics;uterine cervical neoplasms;magnetic resonance imaging

崔雅琼 甘肃中医药大学,兰州 730000;甘肃省人民医院放射科,兰州 730000

王莉莉 甘肃省人民医院放射科,兰州 730000

赵莲萍 甘肃省人民医院放射科,兰州 730000

黄刚* 甘肃省人民医院放射科,兰州 730000

通信作者:黄刚,E-mail:keen0999@163.com

利益冲突:无。


基金项目: 甘肃省人民医院院内科研基金 编号:16GSSY1-7
收稿日期:2020-02-18
接受日期:2020-04-12
中图分类号:R445.2; R737.33 
文献标识码:A
DOI: 10.12015/issn.1674-8034.2020.06.020
本文引用格式:崔雅琼,王莉莉,赵莲萍,等.宫颈癌影像组学研究进展.磁共振成像, 2020, 11(6): 477-480. DOI:10.12015/issn.1674-8034.2020.06.020.

       宫颈癌(cervical cancer)在女性恶性肿瘤中居第4位,87%的病例发生在发展中国家[1],也是女性常见的癌症相关死亡原因[2],其发病率在我国妇科恶性肿瘤中最高(98.9‰),新发病例近10万/年,死亡病例3万余/年[3]。国际妇产科联合会(International Federation of Gynecology and Obstetrics,FIGO)建议将MRI检查作为宫颈癌治疗前分期的依据,不同分期有相应的治疗策略推荐[4],但在临床工作中,分期相同的患者用同样的治疗方式预后不同。2012年Lambin等[5]提出影像组学,即使用自动化、高通量的手段提取大量医学图像的定量成像特征,深度挖掘图像信息,有望突破传统影像学检查在肿瘤早期诊断、疗效评估和预后预测中应用价值的限度。本文就影像组学应用于宫颈癌诊疗的现状和前景进行论述,以期能为影像组学在宫颈癌研究中的应用提供参考。

1 影像组学的工作流程

       Lambin等[5]认为肿瘤的影像学特征与基因、蛋白质或者分子的改变存在密切联系,影像组学以此为基础进行假设,提出基因异质性可转化为肿瘤异质性,且基因、蛋白质模式等微观层面的改变可能体现在宏观影像特征上[5]。其工作流程包含以下部分:

1.1 图像采集

       影像组学的基础是高质量、标准化的医学图像获取,关键是对影像数据的采集、重建进行标准化操作[6]。图像来源目前以CT、MR、正电子发射计算机断层显像(positron emission tomography,PET)等为主。

1.2 图像分割

       影像组学分析结果很大程度取决于ROI内的灰度值信息,因此图像分割显得尤为关键,方式主要分为自动、半自动、手动分割。宫颈癌ROI的勾画主要依靠人工手动分割,存在个体差异且重现性较低,新的全自动定位和分割方法正在探索中[7,8]

1.3 特征提取和分析

       提取ROI高维特征数据来定量描述病变属性,获得凸显其异质性的特征是影像组学的核心。采用数量庞杂的特征进行过度拟合风险较高,须按照优先级排序后进行降维,得出真正有意义的特征。具体步骤包括:①特征抽取,主成分分析可保留富含有效信息的数据;②特征筛选,利用一些算法去除无关和冗余的特征[9]。最常用的有一阶统计特征、空间几何特征、纹理和小波特征等[10]

1.4 模型建立和验证

       根据具体研究目标选择不同模型,构建模型常用的方法中,分类器中有监督的包括贝叶斯分类器、人工神经网络、支持向量机模型(support vector machine,SVM)、随机森林等,无监督的有K-means算法、高斯混合聚类等,此外还有聚类模型、回归模型等[11]

2 影像组学在宫颈癌的应用现状

       影像组学应用于宫颈癌的研究范围较广,涉及肿瘤的定性、病理分型、分期、组织分化程度、治疗前评估、疗效评价、预后预测、判断淋巴结转移与远处转移、基因分析等。

2.1 肿瘤诊断

       以多模态MRI为代表的传统成像方法可确定原发肿瘤、基质浸润程度、阴道侵犯等,准确性取决于个人诊断水平等因素。Akita等[12]使用T1增强图像的检出率为94.7%。比较常规MRI、扩散加权成像(diffusion-weighted imaging,DWI)和动态对比增强MRI (dynamic contrast-enhanced MRI,DCE-MRI)对宫颈癌和宫颈良性病变的鉴别能力,DWI结合常规MRI准确性较高(95%)且明显优于后者,与DCE-MRI相比诊断性能无明显差异(κ=0.90、0.92)[13]。随着医学图像配准技术的发展,融合成像等手段提供了新的诊断方法,如超声- MRI融合后可检出宫旁浸润的一致性增加,省时且较单一成像准确[14]。影像组学特征也能鉴别良恶性病变。ADC的中位数诊断IB期宫颈癌的敏感性和特异性分别为0.95和0.89,其分布将早期肿瘤与正常宫颈或良性宫颈病变有效区分开来[15]。ADC全肿瘤熵相关参数也有助于区分宫颈组织良恶性[16]。Lu等[17]分析宫颈癌的DCE-MRI特征数据,通过多种示踪动力学模型得出受试者工作特征AUC最高达0.961,利用动脉输入功能采样时参数的可重复性较高(组内相关系数≥0.80)。DCE-MRI药代动力学参数Ve的诊断能力也被证实[18],精度达到94.3%[19],可解释肿瘤血管生成的生物学机制。影像数据表征了宫颈肿瘤与正常组织间的病理生理差异,尽管特征分析可能不会取代病理检查,但可协助提高早期诊断的敏感性、特异性和稳定性。早期检测宫颈癌和癌前病变,保守处理轻度不典型增生,避免活检导致的感染风险增加和患者的不适感,治疗延迟和成本增加。

2.2 病理分型、病理分级分期、组织分化程度

       不同亚型的宫颈癌患者预后存在差异,影像特征可反映组织结构差异。ADC直方图的偏度,腺癌明显低于鳞状细胞癌(squamous cell carcinoma,SCC),而SCC的峰度有升高的趋势[20];PET图像特征中灰度共生矩阵(gray level co-occurrence matrix,GLCM)衍生的相关性在SCC中更高[21],可能是由于癌细胞更高的结构完整性和更强的空间关系。灰度区域矩阵中的短期强度也有助于指示SCC非SCC[22]。ADC图的全肿瘤特征分析评估SCC的组织学分级性能良好,不同观察者间重现性高[23]。分期决定治疗方式和强度,常规MRI对>1 cm宫颈癌局部分期的精度接近90%,影像组学特征也能提取分期和分化的替代标志物。6个独立指标通过SVM分类器实现对早期(I期和Ⅱ期)和晚期(Ⅲ期和Ⅳ期)宫颈癌的鉴别,特征中运行百分比最具判别力且高度稳定(AUC=0.880)[24];一项23例患者的前瞻性研究[25]发现ADC图的3个GLCM衍生特征与肿瘤分化显著相关(ϱ=0.53、-0.49、-0.51)。Wu等[26]认为形态学参数和DCE-MRI定量参数均能区分病理类型,ADC分辨能力最佳,而Ve鉴别分级AUC值达0.850。显示多参数MRI特征评估SCC病理特征和侵袭性优于解剖图像,可对患者进行风险分层。以临床分期为参考,MRI分期的准确性和一致性较高,数据分析的诊断效能接近病理学水平,提供肿瘤解剖、血管、边缘等内部信息,说明影像组学方法具备初步反映肉眼无法理解的宫颈肿瘤固有异质性的潜力,在宫颈癌的管理中可能发挥重要作用。

2.3 基因分型

       肿瘤的生物学行为差异与潜在的基因表达模式相关,深入挖掘基因组特征和影像数据的联系,使用影像特征反映微观层面基因的活动是当前热点。Halle等[27]发现接受放化疗的宫颈癌患者的DCE-MRI药代动力学参数A Brix与缺氧基因集显著相关,免疫组化显示低A Brix与HIF1α蛋白表达的上调相关。由此构建DCE-MRI缺氧基因标记在109例患者中显示了对其无进展生存期(progression free survival,PFS)和局部控制(locoregional control,LRC)的预测价值。后续研究从放化疗患者基线DCE-MRI得出A Brix、Ktrans等和不良预后有关[28]。Li等[29]发现SCC患者PET图像的直方图、GLCM衍生特征与血管内皮生长因子表达水平相关,T1WI的特征与表皮生长因子受体的表达呈负相关;T2WI直方图的偏度则有助于区分患者Her2(+)和阴性(+)表达[30]。影像组学反映出的基因差异,能够为临床提供更多信息,协助确定有治疗失败风险的患者,指导制订治疗方案。检测肿瘤分子基因表型表现出巨大潜力,可能开发成基因突变的非侵入性成像生物标志物,促进传统影像诊断模式向分子影像学模式转变。整合影像学与遗传学数据解码肿瘤分子和基因水平的生物学信息并服务于精准医疗,有望突破基因诊断技术在临床应用的限制。

2.4 治疗前评估

       影像学检查能提供宫颈癌的肿瘤大小、淋巴结状态、局部或全身扩散情况等信息,辅助确定FIGO分期,进而指导临床决策[31]。淋巴结转移(lymph node metastases,LNM)是影响患者预后的高危因素且是术后放疗的适应证之一[32],对10 mm以上淋巴结的检出常规PET-CT比CT和MRI更准确,但4%~15%的病例可出现假阴性[31]。影像组学方法预测LNM有一定价值,但准确性有限,训练集(training set,TS)和验证集(validation set,VS)中AUC分别为0.803、0.757[22,29]。多模态磁共振显示出良好的预测性能,区分转移和非转移淋巴结时,在TS和VS中AUC分别达到0.864、0.870[33]。T2WI特征的灵敏度在两队列分别为94.3%和100%[34]。Wu等[26]认为ADC图判别能力最高。延迟期CT图像的AUC在TS中为0.80,VS中为0.75[35]。探索超声图像预测LNM的可行性,TS和VS中AUC分别为0.79和0.77。虽然准确性可能略低于PET与MRI影像组学,但优于常规MRI或CT单一检查结果,提供了淋巴结状态的非侵入性预测工具[36,37]。血管淋巴管间隙浸润(lymphovascular space invasion,LVSI)对宫颈癌分期无明显影响,但会影响治疗方案,T1增强图像特征结合红细胞计数的列线图在TS中特异性和敏感性分别为0.756和0.828,在VS中为0.773和0.692[38]。T2WI区分LVSI存在与否也有统计学差异(P<0.05)[39]。MR功能图鉴别能力优于解剖图,不仅体现在肿瘤分级和预测LNM,区分LVSI时AUC范围为0.659~ 0.814,以Ve图分辨力最佳[26]。影像组学结合深度学习也是发展趋势,组合模型判断LVSI表现良好[40]。影像组学标签弥补了治疗前无创评价LNM和LVSI方法的空缺,提高了预测的准确性,指导手术计划,降低淋巴结误切除率,为早期宫颈癌患者的诊疗引入新思路。

2.5 疗效评估和预后预测

       通过测量病灶大小、监测其变化来评价治疗反应和预测预后有一定局限性,影像组学定量描述众多宫颈癌预后相关生物学标志物,突破一维方向肿瘤信息的限制,更高维度、细致化地表征肿瘤血供、增强、代谢等,协助临床医生更准确识别高危患者,提供决策支持,实时监测疗效,量化并追踪可变的肿瘤异质性,结合预后信息及时优化治疗方案并制定随访策略。PET以代谢显像和定量分析的特点在临床工作中有较大优势,挖掘图像信息预测宫颈癌的生存期[41]和评估疗效等[42,43,44]。在1台扫描仪中使用纹理特征训练用于预测复发和非复发患者的标签,在另一台扫描仪也得到验证(P<0.05),熵比最大标准摄取值更准确[45]。灰度游程长度矩阵的高灰度游程重点和非鳞癌是PFS和无骨盆复发生存期的预测因素[46]。由非小细胞肺癌和宫颈癌的肿瘤边界周围外部体素建立壳特征来预测癌细胞从原发肿瘤扩散到远处器官过程中是否发生局部区域衰竭,AUC为0.83[47]。一项多中心研究中,多参数MRI预测患者对新辅助化疗的反应,AUC值在TS和VS中分别为0.998和0.999[43]。此外,PET和MRI图像的组合模型[48]也显示出巨大优势,在多中心研究中预测模型的准确性较低,而使用ComBat法协调不同采集和成像协议后外部验证,法国和加拿大人群中PFS预测模型的准确率均为90%,远高于常用临床参数(56%~60%)。LRC模型在两个中心预测的准确度各为98%、96%,另一研究中达100%[49]。影像组学以定量方式辅助临床医师发现肉眼无法识别的宫颈癌早期改变,在治疗前评估患者能受益于哪种治疗方式,评估复发风险,区分潜在的不良预后群体,监测治疗过程中的表型变化,调整相适应的治疗计划,改善生存预测指标,将越来越广泛地应用于患者的个体化治疗。

3 影像组学在宫颈癌应用的发展前景

       如何从海量数据中准确识别真正有意义、信息量大、辨识度高、相关性和独立性强且可重复的影像标志物是一项挑战,影像组学工作流程中很多因素都会影响特征的提取和量化,降低结果的准确性。全肿瘤体积或二维肿瘤中心切片特征[23,50]、肿瘤分割方法、灰度离散化、重建算法[51]、以及体素大小、高斯滤波[52]都会导致宫颈癌患者图像特征的明显差异。特征的稳定性也存在争议,研究发现熵代表的一阶特征的可重复性总体比形状和纹理特征好[53];Fiset等[54]则认为形状特征重复性和再现性最高。特征的稳定影响模型构建和数据库的建立,对深入研究和临床转化有重要意义,需要大量数据来克服临床影像中的异质性问题。合理的数据解释同样重要,在对85例FIGO IIb期患者探索球形度、熵等指标预测盆腔LNM时得出阴性结论[55],表明18F-脱氧葡萄糖摄取异质性并不代表患者预后不同,表观异质性的差异可能是某些图像指标对其他因素(如肿瘤体积)的依赖性所致,或是所比较患者群体的潜在异质性产生的假象。因此,特征数据的解读需要仔细分析图像,解释结果才可以得出结论。

       总之,影像组学是正在开发的新技术,存在许多关键问题亟待解决,但因其客观、快捷、无创且可重复等优点,可为优化医疗决策、推动精准医学的发展尤其是肿瘤的个体化医疗提供新途径。目前,影像组学对宫颈癌的研究在诊断、治疗和预后等方面已经取得了较为可靠的结果,未来将趋向于多中心大样本研究,挖掘更多有价值的生物学信息,从循证医学的角度应用于精准医学。

[1]
Small WJ, Bacon MA, Bajaj A, et al. Cervical cancer: A global health crisis. Cancer, 2017, 123(13): 2404-2412.
[2]
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. CA: A Cancer J Clin, 2018, 68(6): 394-424.
[3]
Chen W, Zheng R, Baade PD, et al. Cancer statistics in China, 2015. CA: A Cancer J Clin, 2016, 66(2): 115-132.
[4]
Koh WJ, Abu-Rustum NR, Bean S, et al. Uterine neoplasms, version 1.2018, nccn clinical practice guidelines in oncology. J National Comprehensive Cancer Network Jnccn, 2018, 16(2): 170-199.
[5]
Lambin P, Rios-Velazquez E, Leijenaar R, et al. Radiomics: Extracting more information from medical images using advanced feature analysis. Eur J Cancer, 2012, 48(4): 441-446.
[6]
Mackin D, Fave X, Zhang L, et al. Measuring computed tomography scanner variability of radiomics features. Invest Radiol, 2015, 50(11): 757.
[7]
Lin YC, Lin CH, Lu HY, et al. Deep learning for fully automated tumor segmentation and extraction of magnetic resonance radiomics features in cervical cancer. Eur Radiol, 2020, 30(3): 1297-1305.
[8]
Mu W, Chen Z, Shen W, et al. A segmentation algorithm for quantitative analysis of heterogeneous tumors of the cervix with (1)(8)f-fdg pet/ct. IEEE Trans Biomed Eng, 2015, 62(10): 2465-2479.
[9]
Li SS, Hou Z, Liu J, et al. Review of radiomic analysis and modeling tools. Chin J Med Physics, 2018, 35(9): 1043-1049.
李双双,侯震,刘娟,等.影像组学分析与建模工具综述.中国医学物理学杂志, 2018, 35(9): 1043-1049.
[10]
Rahmim A, Schmidtlein CR, Jackson A, et al. A novel metric for quantification of homogeneous and heterogeneous tumors in pet for enhanced clinical outcome prediction. Physics in Medicine & Biology, 2016, 61(1): 227-242.
[11]
Wu YP, Lin YS, Gu JQ, et al. Research progress and challenges of radiomics. Chin J Radiol, 2017, 51(12): 983-985.
吴亚平,林予松,顾建钦,等.影像组学的研究进展与挑战.中华放射学杂志, 2017, 51(12): 983-985.
[12]
Akita A, Shinmoto H, Hayashi S, et al. Comparison of T2-weighted and contrast-enhanced T1-weighted MR imaging at 1.5 T for assessing the local extent of cervical carcinoma. Eur Radiol, 2011, 21(9): 1850.
[13]
Kuang F, Yan Z, Li H, et al. Diagnostic accuracy of diffusion-weighted mri for differentiation of cervical cancer and benign cervical lesions at 3.0 T: Comparison with routine MRI and dynamic contrast-enhanced MRI. J Magne Reson Imaging, 2015, 42(4): 1094-1099.
[14]
Moro F, Gui B, Arciuolo D, et al. Fusion imaging of ultrasound and mri in the assessment of locally advanced cervical cancer: A prospective study. Int J Gynecol Cancer, 2020, 30(4): 456-465.
[15]
Lin Y, Li H, Chen Z, et al. Correlation of histogram analysis of apparent diffusion coefficient with uterine cervical pathologic finding. Am J Roentgenol, 2015, 204(5): 1125-1131.
[16]
Guan Y, Li W, Jiang Z, et al. Whole-lesion apparent diffusion coefficient-based entropy-related parameters for characterizing cervical cancers. Acad Radiol, 2016, 23(12): 1559-1567.
[17]
Lu Y, Peng W, Song J, et al. On the potential use of dynamic contrast-enhanced (dce) MRI parameters as radiomic features of cervical cancer. Med Phys, 2019, 46(11): 5098-5109.
[18]
Wang X, Lin W, Mao Y, et al. A comparative study of two-compartment exchange models for dynamic contrast-enhanced MRI in characterizing uterine cervical carcinoma. Contrast Media Molecular Imaging, 2019, 2019: 3168416.
[19]
Shao J, Zhang Z, Liu H, et al. Dce-mri pharmacokinetic parameter maps for cervical carcinoma prediction. Comput Biol Med, 2020, 118: 103634.
[20]
Downey K, Riches SF, Morgan VA, et al. Relationship between imaging biomarkers of stage i cervical cancer and poor-prognosis histologic features: Quantitative histogram analysis of diffusion-weighted mr images. AJR Am J Roentgenol, 2013, 200(2): 314-320.
[21]
Tsujikawa T, Rahman T, Yamamoto M, et al. (18)f-fdg pet radiomics approaches: Comparing and clustering features in cervical cancer. Ann Nucl Med, 2017, 31(9): 678-685.
[22]
Shen WC, Chen SW, Liang JA, et al. [18]Fluorodeoxyglucose positron emission tomography for the textural features of cervical cancer associated with lymph node metastasis and histological type. Eur J Nucl Med Mol Imaging, 2017, 44(10): 1721-1731.
[23]
Liu Y, Zhang Y, Cheng R, et al. Radiomics analysis of apparent diffusion coefficient in cervical cancer: A preliminary study on histological grade evaluation. J Magne Reson Imaging, 2019, 49(1): 280-290.
[24]
Mu W, Chen Z, Liang Y, et al. Staging of cervical cancer based on tumor heterogeneity characterized by texture features on 18f-fdg pet images. Physics in Med Biology, 2015, 60(13): 5123.
[25]
Becker AS, Ghafoor S, Marcon M, et al. Mri texture features may predict differentiation and nodal stage of cervical cancer: A pilot study. Acta Radiol Open, 2017, 6(10): 2058.
[26]
Wu Q, Shi D, Dou S, et al. Radiomics analysis of multiparametric mri evaluates the pathological features of cervical squamous cell carcinoma. J Magn Reson Imaging, 2019, 49(4): 1141-1148.
[27]
Halle C, Andersen E, Lando M, et al. Hypoxia-induced gene expression in chemoradioresistant cervical cancer revealed by dynamic contrast-enhanced mri. Cancer Res, 2012, 72(20): 5285-5295.
[28]
Andersen EK, Hole KH, Lund KV, et al. Pharmacokinetic parameters derived from dynamic contrast enhanced mri of cervical cancers predict chemoradiotherapy outcome. Radiother Oncol, 2013, 107(1): 117-122.
[29]
Li K, Sun H, Lu Z, et al. Value of [18f] fdg pet radiomic features and vegf expression in predicting pelvic lymphatic metastasis and their potential relationship in early-stage cervical squamous cell carcinoma. Eur J Radiol, 2018, 106: 160-166.
[30]
Meyer HJ, Hamerla G, Höhn AK, et al. Whole lesion histogram analysis derived from morphological mri sequences might be able to predict egfr-and her2-expression in cervical cancer. Acad Radiol, 2019, 26(8): e208-e215.
[31]
Bhatla N, Aoki D, Sharma DN, et al. Cancer of the cervix uteri. Int J Gynecol Obstetrics, 2018, 143(S2): 22-36.
[32]
Carlson RW, Scavone JL, Koh WJ, et al. Nccn framework for resource stratification: A framework for providing and improving global quality oncology care. J National Comprehensive Cancer Network, 2016, 14(8): 961-969.
[33]
Yu YY, Zhang R, Dong RT, et al. Feasibility of an adc-based radiomics model for predicting pelvic lymph node metastases in patients with stage ib-iia cervical squamous cell carcinoma. Br J Radiol, 2019, 92(1097): 20180986.
[34]
Wu Q, Wang S, Chen X, et al. Radiomics analysis of magnetic resonance imaging improves diagnostic performance of lymph node metastasis in patients with cervical cancer. Radiother Oncol, 2019, 138: 141-148.
[35]
Chen J, He B, Dong D, et al. Noninvasive ct radiomic model for preoperative prediction of lymph node metastasis in early cervical carcinoma. British J Radiol, 2020, 93(1108): 20190558.
[36]
Jin X, Ai Y, Zhang J, et al. Noninvasive prediction of lymph node status for patients with early-stage cervical cancer based on radiomics features from ultrasound images. Eur Radiol, 2020, 1-8. DOI: org/10.1007/s00330-020-06692-1.
[37]
Luo L, Luo Q, Tang L. Diagnostic value and clinical significance of mri and ct in detecting lymph node metastasis of early cervical cancer. Oncology Letters, 2020, 19(1): 700-706.
[38]
Li Z, Li H, Wang S, et al. Mr-based radiomics nomogram of cervical cancer in prediction of the lymph-vascular space invasion preoperatively. J Magn Reson Imaging, 2019, 49(5): 1420-1426.
[39]
Wang S, Chen X, Liu Z, et al. Radiomics analysis on T2-mr image to predict lymphovascular space invasion in cervical cancer. Medical Imaging 2019: Computer-Aided Diagnosis, International Society for Optics and Photonics, 2019, 10950: 1095040. DOI: org/10.1117/12.2513129.
[40]
Hua W, Xiao T, Jiang X, et al. Lymph-vascular space invasion prediction in cervical cancer: Exploring radiomics and deep learning multilevel features of tumor and peritumor tissue on multiparametric MRI. Biomedical Signal Processing and Control, 2020, 58: 101869.
[41]
Altazi B, Fernandez D, Zhang G, et al. Suej-258: Prediction of cervical cancer treatment response using radiomics features based on f18-fdg uptake in pet images. Med Phys, 2015, 42(6Part11): 3326-3326.
[42]
Altazi BA, Fernandez DC, Zhang GG, et al. Investigating multi-radiomic models for enhancing prediction power of cervical cancer treatment outcomes. Phys Med, 2018, 46: 180-188.
[43]
Sun C, Tian X, Liu Z, et al. Radiomic analysis for pretreatment prediction of response to neoadjuvant chemotherapy in locally advanced cervical cancer: A multicentre study. EBio Med, 2019, 46: 160-169.
[44]
Tian X, Sun C, Liu Z, et al. Prediction of response to preoperative neoadjuvant chemotherapy in locally advanced cervical cancer using multicenter ct-based radiomic analysis. Front in Oncol, 2020, 10: 77.
[45]
Reuze S, Orlhac F, Nioche C, et al. Prediction of cervical cancer recurrence using textural features calculated from 18f-fdg pet images. J Nuclear Med, 2016, 57(Suppl 2): 422-423.
[46]
Chen SW, Shen WC, Hsieh TC, et al. Textural features of cervical cancers on fdg-pet/ct associate with survival and local relapse in patients treated with definitive chemoradiotherapy. Sci Rep, 2018, 8(1): 11859.
[47]
Hao H, Zhou Z, Li S, et al. Shell feature: A new radiomics descriptor for predicting distant failure after radiotherapy in non-small cell lung cancer and cervix cancer. Phys Med Biol, 2018, 63(9): 95007.
[48]
Lucia F, Visvikis D, Vallieres M, et al. External validation of a combined pet and mri radiomics model for prediction of recurrence in cervical cancer patients treated with chemoradiotherapy. Eur J Nucl Med Mol Imaging, 2019, 46(4): 864-877.
[49]
Lucia F, Visvikis D, Desseroit MC, et al. Prediction of outcome using pretreatment 18 f-fdg pet/ct and mri radiomics in locally advanced cervical cancer treated with chemoradiotherapy. Eur J Nuclear Med Mol Imaging, 2018, 45(5): 768-786.
[50]
Kan Y, Dong D, Zhang Y, et al. Radiomic signature as a predictive factor for lymph node metastasis in early-stage cervical cancer. J Magne Reson Imaging, 2019, 49(1): 304-310.
[51]
Altazi BA, Zhang GG, Fernandez DC, et al. Reproducibility of f18-fdg pet radiomic features for different cervical tumor segmentation methods, gray-level discretization, and reconstruction algorithms. J Appl Clin Med Phys, 2017, 18(6): 32-48.
[52]
Reuzé S, Orlhac F, Chargari C, et al. Prediction of cervical cancer recurrence using textural features extracted from 18f-fdg pet images acquired with different scanners. Oncotarget, 2017, 8(26): 43169.
[53]
Traverso A, Wee L, Dekker A, et al. Repeatability and reproducibility of radiomic features: A systematic review. Int J Radiat Oncol Biol Phys, 2018, 102(4): 1143-1158.
[54]
Fiset S, Welch ML, Weiss J, et al. Repeatability and reproducibility of mri-based radiomic features in cervical cancer. Radiother Oncol, 2019, 135: 107-114.
[55]
Brooks FJ, Grigsby PW. Fdg uptake heterogeneity in figo iib cervical carcinoma does not predict pelvic lymph node involvement. Radiation Oncology, 2013, 8(1): 294.

上一篇 载化疗药磁性氧化铁纳米颗粒诊疗肿瘤的研究进展
下一篇 基于多序列MRI影像组学模型预测宫颈鳞癌病理组织分型
  
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