分享:
分享到微信朋友圈
X
综述
较低级别脑胶质瘤预后预测的影像组学研究进展
李阳阳 谭艳

Cite this article as: Li YY, Tan Y. Research progress in radiomics on prognosis prediction of lower-grade gliomas[J]. Chin J Magn Reson Imaging, 2022, 13(11): 129-132, 148.本文引用格式:李阳阳, 谭艳. 较低级别脑胶质瘤预后预测的影像组学研究进展[J]. 磁共振成像, 2022, 13(11): 129-132, 148. DOI:10.12015/issn.1674-8034.2022.11.025.


[摘要] 较低级别脑胶质瘤(lower-grade gliomas, LGGs)是指世界卫生组织(World Health Organization, WHO)2级和3级脑胶质瘤,与胶质母细胞瘤相比,LGGs患者的病理级别低,预后较好。但是,由于其侵袭性生长方式,部分患者治疗后仍然会出现复发或恶性转变,因此,早期进行预后预测有望对LGGs患者提供个体化精准治疗,提高生活质量。影像组学可以从图像中提取高通量成像特征,将图像信息转换为直观的数据来反映肿瘤内部异质性信息,这有助于临床医生为患者选择合适的治疗方案。基于MRI的影像组学可以直接预测LGGs患者的预后,也可以将影像组学特征与基因表型或免疫特征结合共同预测预后,但多项研究仍存在局限性,开展基于功能MRI的影像组学,并将影像组学与新发现的预后相关基因或免疫学特征结合用于预后预测是未来研究的方向。本文综述了影响LGGs的预后因素及影像组学在LGGs预后预测中的作用,以拓展基于影像组学预测LGGs患者预后的方法,为临床精准诊治提供新思路。
[Abstract] Lower-grade gliomas (LGGs) are World Health Organization (WHO) grade 2 and 3 gliomas. Compared with glioblastoma, LGGs have lower pathological grade and better prognosis. However, due to its aggressive growth mode, some patients still have recurrence or malignant transformation after treatment. Therefore, early prognosis prediction is expected to provide individualized and accurate treatment for LGGs patients and improve their quality of life. Radiomics, extracting and analyzing high-throughput imaging features from images, and converting the image information into intuitive data to reflect the internal heterogeneity of tumors, is helpful for clinicians to select the appropriate treatment plan for patients. The radiomics based on magnetic resonance imaging can directly predict the prognosis of LGGs, and can also combine the radiomics features with gene phenotype or immune features to predict the prognosis. However, many studies still have limitations. It is the direction of future research to develop radiomics based on MRI functional imaging and combine radiomics with newly discovered prognostic related genes or immunological features for prognosis prediction. This article reviews the prognostic factors of LGGs and the role of radiomics in predicting the prognosis of LGGs, in order to expand the method of predicting the prognosis based on radiomics and provide a new idea for accurate clinical diagnosis and treatment.
[关键词] 较低级别脑胶质瘤;胶质瘤;预后;影像组学;影像基因组学;磁共振成像
[Keywords] lower-grade gliomas;glioma;prognosis;radiomics;radiogenomics;magnetic resonance imaging

李阳阳 1   谭艳 2*  

1 山西医科大学医学影像学院,太原 030001

2 山西医科大学第一医院影像科,太原 030001

谭艳,E-mail:tanyan123456@sina.com

作者利益冲突声明:全体作者均声明无利益冲突。


基金项目: 国家自然科学基金 82071893
收稿日期:2022-07-09
接受日期:2022-11-07
中图分类号:R445.2  R730.264 
文献标识码:A
DOI: 10.12015/issn.1674-8034.2022.11.025
本文引用格式:李阳阳, 谭艳. 较低级别脑胶质瘤预后预测的影像组学研究进展[J]. 磁共振成像, 2022, 13(11): 129-132, 148. DOI:10.12015/issn.1674-8034.2022.11.025.

       较低级别脑胶质瘤(lower-grade gliomas, LGGs)是指世界卫生组织(World Health Organization, WHO)Ⅱ级和Ⅲ级脑胶质瘤,主要包括弥漫性星形细胞瘤、少突胶质细胞瘤、少突星形细胞瘤3种类型[1]。2021年第五版世界卫生组织中枢神经系统肿瘤分类(the fifth edition of the WHO Classification of Tumors of the Central Nervous System, WHO CNS 5)中[2],成人弥漫性脑胶质瘤只包括3种类型:星形细胞瘤,异柠檬酸脱氢酶(isocitrate dehydrogenase, IDH)突变型;少突胶质细胞瘤,IDH突变伴1p/19q联合缺失型;胶质母细胞瘤,IDH野生型。此外,WHO CNS 5中提出肿瘤的分级将使用阿拉伯数字而非罗马数字,因此,将LGGs定义为2级和3级脑胶质瘤。

       目前临床上对LGGs患者的治疗首选早期最大程度手术切除,术后对高危患者进行放化疗[3, 4],以减缓肿瘤的恶性进展。与胶质母细胞瘤相比,虽然LGGs级别较低,预后相对较好,但由于其侵袭性生长方式,完全切除不太可能,残余肿瘤存在引起的复发率与恶变率仍然很高[4, 5],并且,部分LGGs患者对放化疗的敏感性较差,接受放化疗时引起的不良反应严重降低了患者的生存质量[6],因此早期对LGGs患者进行预后预测有利于及时制订个性化治疗方案,提高患者生存率。

       当前,临床医生主要依据预后风险因素、肿瘤基因表型及病理分级等对LGGs患者进行预后预测,但各项研究中影响患者预后的风险因素尚未统一,且肿瘤基因表型和病理分级主要依赖有创性病理学检查。而影像组学[7]从医学图像中提取并分析高通量图像特征,将图像信息转换为反映肿瘤内部异质性的信息后,进行深层次预测来辅助临床医师做出更为准确的判断。它作为一种新的研究方法,具有安全性、无创性、全面性等优点,在LGGs鉴别诊断、肿瘤分级、基因表达预测、疗效评估及预后预测等方面有深入的研究。本文对影响LGGs预后的因素及影像组学在LGGs预后预测中的作用予以综述,以拓展基于影像组学预测LGGs患者预后的方法。

1 影响LGGs预后的因素

       既往研究表明,LGGs患者的预后及疗效与患者年龄、肿瘤大小、部位、术前卡氏活动状态(Karnofsky Performance Status, KPS)评分、手术切除程度、术后放化疗和肿瘤基因表型等因素相关。

       Li等[8]研究表明60岁以下患者的中位生存期显著高于60岁及以上患者,而Zhao等[9]认为年龄>40岁是不良预后因素,两项研究中年龄不同可能与研究对象有关,患者的预后与年龄相关可能是由于脑胶质瘤在老年患者中更具有侵袭力,也可能与老年患者治疗方案的选择及就诊时功能状态较差有关。Yahanda等[10]的研究阐述了肿瘤位于额叶和枕/顶叶与较短的无进展生存期(progression-free-survival, PFS)相关。Zhao等[9]的研究也表明了肿瘤所在部位与预后相关,并且肿瘤位于多个部位时预后最差。Liu等[11]的研究证明最大肿瘤直径是总体生存期(overall survival, OS)的预后因素,同时肿瘤直径≥7 cm是无事件生存期的独立危险因素。术前KPS评分在一定程度上反映了患者的功能状态,评分越高表明患者的身体状况越好,越能耐受手术和放化疗引起的副作用。Li等[8]的研究发现,术前KPS评分≥70分的患者预后明显优于KPS评分<70分的患者。多项研究[12, 13, 14]表明手术切除程度也是影响LGGs患者预后的危险因素,较高的切除率或较少的残留体积对患者生存有益。此外,高危患者接受辅助放化疗也与患者的预后及疗效相关[15, 16]

       除上述临床因素以外,很多肿瘤基因表型如IDH[17]、1p/19q[18]、TP53[19]及O6-甲基鸟嘌呤-DNA-甲基转移酶(O6-methylguanine DNA methyltransferase, MGMT)[20]均可用于LGGs的诊断、预后预测及疗效评估中。近年来,很多临床研究还发现CDKN2A/B纯合子缺失导致IDH突变型星形细胞瘤的OS缩短,并且与IDH突变型胶质母细胞瘤几乎无法区分[21, 22, 23],从而证实了CDKN2A/B纯合子缺失是LGGs患者的不良预后因素[21]。在2021年WHO CNS 5中也提到,即使不存在胶质母细胞瘤特异性组织学特征如坏死和微血管增殖,也可以将存在CDKN2A/B纯合子缺失的星形细胞瘤升级诊断为WHO 4级[2]

       LGGs患者年龄越小,术前KPS评分越高,预后越好,并且位于额叶的肿瘤预后优于额叶以外的肿瘤,肿瘤直径越小、手术切除越完全,疗效也越好。然而,目前各项研究对预后危险因素的规定尚未统一,还不能给临床较准确的数值来评估患者的危险性。另一方面,虽然肿瘤基因表型能提供强有力的预后信息,但精准检测基因表型往往需要进行病理活检,而病理活检具有创伤性,且空间和时间异质性会不可避免地降低采样的准确性,还可能引发相应的并发症[24]。多项研究表明,联合影像组学能提高临床风险因素的预测效能。

2 影像组学对LGGs预后预测的研究现状

       通过整合多种临床数据及影像图像特征构建预测模型可以提供给患者可视化的概率估计,帮助临床医生和研究人员快速预测患者的预后,从而制订最佳治疗方案。

2.1 MRI单一/多序列影像组学特征预测预后

       从MRI单一序列提取的影像组学特征联合临床病理等因素构建的模型可以用于预测患者的生存时间。Liu等[25]提取了每位患者术前T2WI中的431个影像组学特征,采用单变量Cox回归模型及最小绝对收缩和选择算法(least absolute shrinkage and selection operator, LASSO)筛选出9个特征并构建Cox回归模型来评估影像组学特征与PFS的相关性,结果显示,该模型预测患者PFS的C指数(C-index)达0.823。另一项研究[26]发现,影像组学特征与患者的OS相关,并且可以将训练组中的患者分为高、低风险两组(P=0.0369),同时,使用影像组学风险评分及临床因素构建的预测患者OS的模型显示出良好的预测准确性(C-index=0.70),为个体生存评估提供了一种有效方法。还有研究[27, 28]通过对比增强后T1加权序列(post-contrast enhanced T1-weighted, CE-T1WI)图像中提取特征构建的影像组学模型,将LGGs患者分为预后显著不同的高、低风险组(P<0.001),对LGGs患者的预后也有较好的预测能力。最近一项研究[29]使用扩散峰度成像(diffusion kurtosis imaging, DKI)直方图分析与临床因素结合构建列线图预测LGGs患者的生存率,该列线图对LGGs患者预后预测的AUC达0.95,明显优于临床因素预测效能(AUC=0.76)。

       与MRI单一序列提取的影像组学特征相比,基于多序列的影像组学特征模型可以进一步改善预后预测的准确性。Wang等[30]从149名LGGs患者的CE-T1WI和T2加权流体衰减反转恢复(T2-weighted fluid attenuation inversion recovery, T2-FLAIR)序列图像中提取影像组学特征,采用LASSO回归进行筛选后构建Cox回归模型对LGGs患者的生存进行预测,研究证明了CE-T1WI和T2-FLAIR联合序列的影像组学特征(C-index=0.798)比单独CE-T1WI序列(C-index=0.744)或T2-FLAIR序列(C-index=0.736)的特征预测性能更好。并且,临床病理风险因素结合影像组学特征(C-index=0.821)对OS的估计性能也优于单纯临床病理风险因素(C-index=0.692)的性能。此外,还有多项研究[31, 32, 33]证明多序列影像组学特征的加入进一步提高了临床特征预测预后的能力。例如,Choi等[31]基于影像组学、临床特征及患者IDH突变状态,运用随机森林算法构建模型对LGGs患者的OS进行预测,结果显示,相对于非影像组学预后参数构建的模型(AUC=0.627),增加影像组学特征后(AUC= 0.709)显著提高了预测准确性。Xu等[34]首次将影像组学和深度学习特征用于LGGs的预后预测中,研究发现深度学习影像组学特征是独立预后因素,与临床预后因素结合构建的综合列线图(C-index=0.865)在预测LGGs的OS方面表现出明显优于临床列线图(C-index=0.796)的性能。

       除上述影像组学特征直接预测患者预后情况外,一些研究还通过预测肿瘤病理分级、治疗效果或术后复发风险指导临床决策,从而预测患者的预后情况。一般来说,病理分级越高,患者的预后越差、生存率越低。LGGs患者的预后比高级别脑胶质瘤(high-grade gliomas, HGGs)更好,术前预测肿瘤病理分级可以更好地指导治疗。Ding等[35]开发了一种基于多平面重建的深度学习影像组学模型来区分HGGs和LGGs,研究采用3种机器学习方法(支持向量机、logistic回归和随机森林)分析发现,同时使用影像组学特征和深度学习特征构建的分类模型AUC值高于仅使用影像组学或深度学习特征构建的分类模型。同样,在Ning等[36]的研究中证明了整合多模态影像组学特征和深度学习特征开发的模型对脑胶质瘤分级预测的可行性。上述两项研究都展示了影像组学术前区分高低级别脑胶质瘤的价值。有学者通过影像组学区分患者对放化疗的敏感度来判断预后。如Wang等[30]的研究利用LASSO算法构建的模型将患者分为高、低影像组学特征两组,其中,化疗显著增加了高影像组学特征组患者的OS,而对低影像组学特征组没有显著影响。同样,Wei等[19]的研究也证明了影像组学特征有助于预测替莫唑胺(temozolomide, TMZ)的化疗效果。Zhang等[37]的研究中构建了4个多变量logistic回归模型来预测术后残余肿瘤对放化疗的反应,结果显示,多序列联合模型的预测性能最佳(AUC=0.852),有望准确识别对放化疗不敏感的患者,以减少脱发、呕吐等不必要的副作用发生[30]。MRI影像组学模型还可作为术前预测脑胶质瘤复发的有效工具,在临床决策中发挥提示作用。Wang等[38]采用logistic回归分析开发多参数影像组学模型来预测2级脑胶质瘤首次切除后早期复发(<1年)的情况,其敏感度、特异度、准确率分别为100%、80%、90%。Liu等[39]也发现影像组学对预测脑胶质瘤患者复发的价值,同时,影像组学特征与临床因素结合构建模型还可以提高预测复发的效能。

       总之,基于MRI影像组学特征,采用多种方法构建的预测模型在预测LGGs患者预后中具有较大价值,结合临床预后因素并运用MRI多模态、多序列、多方位成像构建的模型可以进一步提高预测效能。上述研究均展现了影像组学作为生物学替代物预测LGGs患者预后的潜力。

2.2 基因-影像组学特征预测预后

       肿瘤基因表型也是预测脑胶质瘤预后的关键因子。近年来,越来越多的研究将影像组学特征与基因组数据结合来提高脑胶质瘤精准诊断和预后预测的准确性。Ma等[40]收集了65名LGGs患者MRI多序列(T1WI、CE-T1WI、T2WI和T2-FLAIR)图像特征及基因特征,采用Cox回归模型、相关性分析及LASSO等方法识别出与患者预后相关的4个图像特征和43个基因特征,通过粒子群优化算法获得结合两者的综合模型来预测LGGs患者的生存情况,使用ROC曲线评估不同模型的预测能力,结果显示,与单纯影像组学特征或基因特征相比,综合模型(AUC=0.79)提高了预后预测能力。

       此外,有大量研究通过提取影像组学特征构建模型来预测IDH[41, 42]、1p/19q[43]、端粒酶逆转录酶(telomerase reverse tranase, TERT)[44]和MGMT[45]等基因表型从而反映患者的预后情况,沙永建等[46]构建的影像组学模型还可以预测LGGs患者IDH突变合并MGMT甲基化亚型(AUC=0.935),该亚型的准确预测为LGGs患者TMZ治疗及生存期预测提供了重要的临床价值。Ki-67、CD44、CIC等基因与LGGs患者的预后也有一定相关性,但影像组学与上述基因结合预测LGGs患者预后的研究相对较少。Ki-67是细胞增殖最可靠的标志物,其表达水平越高表明脑胶质瘤患者预后越差[47]。Li等[48]的研究中预测Ki-67表达状态的模型在训练组和验证组中分别实现了83.3%和88.6%的准确率,还证明了Ki-67低表达的患者PFS和OS明显长于高表达患者。肿瘤干细胞是指少部分具有自我更新和多分化能力的癌细胞,它能促进肿瘤的发生发展[49]。多项研究[50, 51, 52]表明CD44和CD133基因是肿瘤干细胞标志物,可以显著调节肿瘤细胞的生长、增殖和存活,与脑胶质瘤较差的OS有关。Wang等[53]的研究中Kaplan-Meier生存分析提示,与CD44和CD133的低表达水平相比,CD44和CD133高表达水平与LGGs患者的预后较差有关,并且CD44表达水平还是LGGs患者OS的独立预测因子(P<0.05),该研究中建立基于T2-FLAIR影像组学特征的logistic回归模型可以有效预测术前CD44(AUC=0.805)和CD133(AUC=0.816)的表达水平。Zhang等[54]探索CIC突变与患者生存之间的关系时发现,CIC突变型患者的OS比CIC野生型患者更长。随后,研究者从每位患者的多序列MRI图像中提取特征,通过LASSO回归进行筛选后构建两个logistic回归模型来预测脑胶质瘤和少突胶质细胞瘤患者的CIC突变状态,其准确率分别为94.2%、92.3%。以上研究结果均证实通过MRI影像组学特征预测肿瘤基因状态来反映患者预后情况的可行性。

2.3 免疫-影像组学特征预测预后

       近年来,还有学者报道了影像组学与免疫相关特征联合预测LGGs患者预后的研究。Li等[55]通过免疫表型评分选取7个与LGGs患者预后相关的特征构建免疫预后预测模型(IMriscScore),研究表明,该模型是评估LGGs患者预后的独立因素(P=0.003),可以用于预测LGGs的预后。而IMriskScore 特征可以被使用神经网络深度学习方法的影像组学模型预测,并且该模型在两验证组中AUC值分别达0.821和0.708,这表明MRI影像组学可以通过预测LGGs患者的IMriskScore特征来预测预后,研究还证明高风险患者的生存率低于低风险患者(P=0.007)。

       影像组学特征联合其他临床病理特征对LGGs患者进行预后预测已经取得一定成效,近年来,影像组学特征与免疫或基因特征联合预测LGG患者预后的研究拓宽了我们的思路,当前还有很多与LGGs预后相关性高的免疫或基因特征,其与影像组学特征结合后预测患者的预后情况可能会成为未来的发展方向。

3 局限性与前景展望

       影像组学作为一种快速发展的用于分类与预测的方法,在LGGs预后预测等方面已有深入的研究,但仍然存在以下问题:(1)大多数影像组学研究是单中心、回顾性的研究,可以得出的结论有限,因此,有必要进行更大规模的、多中心的、前瞻性的研究以提高预测性能,并在临床工作中有意义地实施;(2)当前各项研究基于不同磁共振设备和后处理软件得到的结果可能存在差异,还需要进一步规范MRI扫描序列;(3)多数研究是基于常规MRI序列的,有关扩散张量成像和灌注加权成像等功能参数图的影像组学研究相对较少,纳入新的功能MRI技术可能会优化影像组学预测能力;(4)由于个体生存时间的差异和对患者卷积神经网络训练的不足,很少有研究将该方法应用于生存分析中;(5)2021年WHO CNS 5中新增的分子标志物在LGGs患者预后预测中的作用不容忽视,目前还没有研究将其作为预测预后的指标,这为影像组学结合基因表型预测LGGs患者的预后提供了新的方向。

4 小结

       影像组学在预测LGGs患者预后中有深入的研究,该方法前景广阔,今后开展更多中心、更大样本的研究将会使影像组学在无创性获取更多肿瘤特征信息中发挥更大的作用,与免疫标志物和基因表型等微观生物学信息结合也有望协助临床更准确地预测LGGs患者的预后并选择合适的治疗方案,为LGGs个性化精准治疗提供帮助。

[1]
Brat DJ, Verhaak RG, Aldape KD, et al. Comprehensive, Integrative Genomic Analysis of Diffuse Lower-Grade Gliomas[J]. N Engl J Med, 2015, 372(26): 2481-2498. DOI: 10.1056/NEJMoa1402121.
[2]
Louis DN, Perry A, Wesseling P, et al. The 2021 WHO Classification of Tumors of the Central Nervous System: a summary[J]. Neuro Oncol, 2021, 23(8): 1231-1251. DOI: 10.1093/neuonc/noab106.
[3]
Jakola AS, Skjulsvik AJ, Myrmel KS, et al. Surgical resection versus watchful waiting in low-grade gliomas[J]. Ann Oncol, 2017, 28(8): 1942-1948. DOI: 10.1093/annonc/mdx230.
[4]
Youssef G, Miller JJ. Lower Grade Gliomas[J/OL]. Curr Neurol Neurosci Rep, 2020, 20(7): 21 [2022-07-08]. https://doi.org/10.1007/s11910-020-01040-8. DOI: 10.1007/s11910-020-01040-8.
[5]
Murphy ES, Leyrer CM, Parsons M, et al. Risk Factors for Malignant Transformation of Low-Grade Glioma[J]. Int J Radiat Oncol Biol Phys, 2018, 100(4): 965-971. DOI: 10.1016/j.ijrobp.2017.12.258.
[6]
Weller M, van den Bent M, Tonn JC, et al. European Association for Neuro-Oncology (EANO) guideline on the diagnosis and treatment of adult astrocytic and oligodendroglial gliomas[J/OL]. Lancet Oncol, 2017, 18(6): e315-e329 [2022-07-08]. https://doi.org/10.1016/s1470-2045(17)30194-8. DOI: 10.1016/s1470-2045(17)30194-8.
[7]
Lambin P, Rios-Velazquez E, Leijenaar R, et al. Radiomics: extracting more information from medical images using advanced feature analysis[J]. Eur J Cancer, 2012, 48(4): 441-446. DOI: 10.1016/j.ejca.2011.11.036.
[8]
Li F, Zhang Y, Wang N, et al. Evaluation of the Prognosis of Neuroglioma Based on Dynamic Magnetic Resonance Enhancement[J]. World Neurosurg, 2020, 138: 663-671. DOI: 10.1016/j.wneu.2020.01.087.
[9]
Zhao YY, Chen SH, Hao Z, et al. A Nomogram for Predicting Individual Prognosis of Patients with Low-Grade Glioma[J/OL]. World Neurosurg, 2019, 130: e605-e612 [2022-07-08]. https://doi.org/10.1016/j.wneu.2019.06.169. DOI: 10.1016/j.wneu.2019.06.169.
[10]
Yahanda AT, Patel B, Shah AS, et al. Impact of Intraoperative Magnetic Resonance Imaging and Other Factors on Surgical Outcomes for Newly Diagnosed Grade Ⅱ Astrocytomas and Oligodendrogliomas: A Multicenter Study[J]. Neurosurgery, 2020, 88(1): 63-73. DOI: 10.1093/neuros/nyaa320.
[11]
Liu H, Shen L, Huang X, et al. Maximal tumor diameter in the preoperative tumor magnetic resonance imaging (MRI) T2 image is associated with prognosis of Grade Ⅱ Glioma[J/OL]. Medicine (Baltimore), 2021, 100(10): e24850 [2022-07-08]. https://doi.org/10.1097/md.0000000000024850. DOI: 10.1097/md.0000000000024850.
[12]
Xia L, Fang C, Chen G, et al. Relationship between the extent of resection and the survival of patients with low-grade gliomas: a systematic review and meta-analysis[J/OL]. BMC Cancer, 2018, 18(1): 48 [2022-07-08]. https://doi.org/10.1186/s12885-017-3909-x. DOI: 10.1186/s12885-017-3909-x.
[13]
Kavouridis VK, Boaro A, Dorr J, et al. Contemporary assessment of extent of resection in molecularly defined categories of diffuse low-grade glioma: a volumetric analysis[J]. J Neurosurg, 2019, 133(5): 1291-1301. DOI: 10.3171/2019.6.Jns19972.
[14]
Wang P, Luo C, Hong PJ, et al. The Role of Surgery in IDH-Wild-Type Lower-Grade Gliomas: Threshold at a High Extent of Resection Should be Pursued[J]. Neurosurgery, 2021, 88(6): 1136-1144. DOI: 10.1093/neuros/nyab052.
[15]
Liu Y, Liu S, Li G, et al. Association of high-dose radiotherapy with improved survival in patients with newly diagnosed low-grade gliomas[J]. Cancer, 2022, 128(5): 1085-1092. DOI: 10.1002/cncr.34028.
[16]
Wei S, Li J. Efficacy and Safety of Temozolomide Combined with Radiotherapy in the Treatment of Malignant Glioma[J/OL]. J Healthc Eng, 2022, 2022: 3477918 [2022-07-08]. https://doi.org/10.1155/2022/3477918. DOI: 10.1155/2022/3477918.
[17]
Kizilbash SH, Giannini C, Voss JS, et al. The impact of concurrent temozolomide with adjuvant radiation and IDH mutation status among patients with anaplastic astrocytoma[J]. J Neurooncol, 2014, 120(1): 85-93. DOI: 10.1007/s11060-014-1520-4.
[18]
Franceschi E, Mura A, De Biase D, et al. The role of clinical and molecular factors in low-grade gliomas: what is their impact on survival?[J]. Future Oncol, 2018, 14(16): 1559-1567. DOI: 10.2217/fon-2017-0634.
[19]
Noor H, Briggs NE, McDonald KL, et al. TP53 Mutation Is a Prognostic Factor in Lower Grade Glioma and May Influence Chemotherapy Efficacy[J/OL]. Cancers (Basel), 2021, 13(21): 5362 [2022-07-08]. https://doi.org/10.3390/cancers13215362. DOI: 10.3390/cancers13215362.
[20]
Wei J, Yang G, Hao X, et al. A multi-sequence and habitat-based MRI radiomics signature for preoperative prediction of MGMT promoter methylation in astrocytomas with prognostic implication[J]. Eur Radiol, 2019, 29(2): 877-888. DOI: 10.1007/s00330-018-5575-z.
[21]
Lu VM, O'Connor KP, Shah AH, et al. The prognostic significance of CDKN2A homozygous deletion in IDH-mutant lower-grade glioma and glioblastoma: a systematic review of the contemporary literature[J]. J Neurooncol, 2020, 148(2): 221-229. DOI: 10.1007/s11060-020-03528-2.
[22]
Appay R, Dehais C, Maurage CA, et al. CDKN2A homozygous deletion is a strong adverse prognosis factor in diffuse malignant IDH-mutant gliomas[J]. Neuro Oncol, 2019, 21(12): 1519-1528. DOI: 10.1093/neuonc/noz124.
[23]
Shirahata M, Ono T, Stichel D, et al. Novel, improved grading system(s) for IDH-mutant astrocytic gliomas[J]. Acta Neuropathol, 2018, 136(1): 153-166. DOI: 10.1007/s00401-018-1849-4.
[24]
Riche M, Amelot A, Peyre M, et al. Complications after frame-based stereotactic brain biopsy: a systematic review[J]. Neurosurg Rev, 2021, 44(1): 301-307. DOI: 10.1007/s10143-019-01234-w.
[25]
Liu X, Li Y, Qian Z, et al. A radiomic signature as a non-invasive predictor of progression-free survival in patients with lower-grade gliomas[J]. Neuroimage Clin, 2018, 20: 1070-1077. DOI: 10.1016/j.nicl.2018.10.014.
[26]
Qian Z, Li Y, Sun Z, et al. Radiogenomics of lower-grade gliomas: a radiomic signature as a biological surrogate for survival prediction[J]. Aging (Albany NY), 2018, 10(10): 2884-2899. DOI: 10.18632/aging.101594.
[27]
Wu W, Wang Y, Xiang J, et al. A Novel Multi-Omics Analysis Model for Diagnosis and Survival Prediction of Lower-Grade Glioma Patients[J/OL]. Front Oncol, 2022, 12: 729002 [2022-07-08]. https://doi.org/10.3389/fonc.2022.729002. DOI: 10.3389/fonc.2022.729002.
[28]
Lu J, Li X, Li H. A radiomics feature-based nomogram to predict telomerase reverse transcriptase promoter mutation status and the prognosis of lower-grade gliomas[J/OL]. Clin Radiol, 2022, 77(8): e560-e567 [2022-07-08]. https://doi.org/10.1016/j.crad.2022.04.005. DOI: 10.1016/j.crad.2022.04.005.
[29]
施蒙, 马跃虎, 任军, 等. 基于扩散峰度成像直方图构建低级别胶质瘤预后的列线图模型[J]. 磁共振成像, 2022, 13(8): 7-12, 18. DOI: 10.12015/issn.1674-8034.2022.08.002.
Shi M, Ma YH, Ren J, et al. Construction of nomogram model for predicting prognosis of low-grade gliomas based on diffusion kurtosis imaging histogram[J]. Chin J Magn Reson Imaging, 2022, 13(8): 7-12, 18. DOI: 10.12015/issn.1674-8034.2022.08.002.
[30]
Wang J, Zheng X, Zhang J, et al. An MRI-based radiomics signature as a pretreatment noninvasive predictor of overall survival and chemotherapeutic benefits in lower-grade gliomas[J]. Eur Radiol, 2021, 31(4): 1785-1794. DOI: 10.1007/s00330-020-07581-3.
[31]
Choi YS, Ahn SS, Chang JH, et al. Machine learning and radiomic phenotyping of lower grade gliomas: improving survival prediction[J]. Eur Radiol, 2020, 30(7): 3834-3842. DOI: 10.1007/s00330-020-06737-5.
[32]
Park CJ, Han K, Kim H, et al. Radiomics risk score may be a potential imaging biomarker for predicting survival in isocitrate dehydrogenase wild-type lower-grade gliomas[J]. Eur Radiol, 2020, 30(12): 6464-6474. DOI: 10.1007/s00330-020-07089-w.
[33]
Park YW, Kim S, Park CJ, et al. Adding radiomics to the 2021 WHO updates may improve prognostic prediction for current IDH-wildtype histological lower-grade gliomas with known EGFR amplification and TERT promoter mutation status[J/OL]. Eur Radiol, 2022 [2022-07-08]. https://doi.org/10.1007/s00330-022-08941-x. DOI: 10.1007/s00330-022-08941-x.
[34]
Xu C, Peng Y, Zhu W, et al. An automated approach for predicting glioma grade and survival of LGG patients using CNN and radiomics[J/OL]. Front Oncol, 2022, 12: 969907 [2022-10-09]. https://doi.org/10.3389/fonc.2022.969907. DOI: 10.3389/fonc.2022.969907.
[35]
Ding J, Zhao R, Qiu Q, et al. Developing and validating a deep learning and radiomic model for glioma grading using multiplanar reconstructed magnetic resonance contrast-enhanced T1-weighted imaging: a robust, multi-institutional study[J]. Quant Imaging Med Surg, 2022, 12(2): 1517-1528. DOI: 10.21037/qims-21-722.
[36]
Ning Z, Luo J, Xiao Q, et al. Multi-modal magnetic resonance imaging-based grading analysis for gliomas by integrating radiomics and deep features[J/OL]. Ann Transl Med, 2021, 9(4): 298 [2022-07-08]. https://doi.org/10.21037/atm-20-4076. DOI: 10.21037/atm-20-4076.
[37]
Zhang Z, He K, Wang Z, et al. Multiparametric MRI Radiomics for the Early Prediction of Response to Chemoradiotherapy in Patients With Postoperative Residual Gliomas: An Initial Study[J/OL]. Front Oncol, 2021, 11: 779202 [2022-07-08]. https://doi.org/10.3389/fonc.2021.779202. DOI: 10.3389/fonc.2021.779202.
[38]
Wang ZH, Xiao XL, Zhang ZT, et al. A Radiomics Model for Predicting Early Recurrence in Grade Ⅱ Gliomas Based on Preoperative Multiparametric Magnetic Resonance Imaging[J/OL]. Front Oncol, 2021, 11: 684996 [2022-07-08]. https://doi.org/10.3389/fonc.2021.684996. DOI: 10.3389/fonc.2021.684996.
[39]
Liu C, Li Y, Xia X, et al. Application of radiomics feature captured from MRI for prediction of recurrence for glioma patients[J]. J Cancer, 2022, 13(3): 965-974. DOI: 10.7150/jca.65366.
[40]
Ma C, Yao Z, Zhang Q, et al. Quantitative integration of radiomic and genomic data improves survival prediction of low-grade glioma patients[J]. Math Biosci Eng, 2020, 18(1): 727-744. DOI: 10.3934/mbe.2021039.
[41]
Wu S, Zhang X, Rui W, et al. A nomogram strategy for identifying the subclassification of IDH mutation and ATRX expression loss in lower-grade gliomas[J]. Eur Radiol, 2022, 32(5): 3187-3198. DOI: 10.1007/s00330-021-08444-1.
[42]
Cao M, Suo S, Zhang X, et al. Qualitative and Quantitative MRI Analysis in IDH1 Genotype Prediction of Lower-Grade Gliomas: A Machine Learning Approach[J/OL]. Biomed Res Int, 2021, 2021: 1235314 [2022-07-08]. https://doi.org/10.1155/2021/1235314. DOI: 10.1155/2021/1235314.
[43]
Kha QH, Le VH, Hung TNK, et al. Development and Validation of an Efficient MRI Radiomics Signature for Improving the Predictive Performance of 1p/19q Co-Deletion in Lower-Grade Gliomas[J/OL]. Cancers (Basel), 2021, 13(21): 5398 [2022-07-08]. https://doi.org/10.3390/cancers13215398. DOI: 10.3390/cancers13215398.
[44]
Jiang C, Kong Z, Zhang Y, et al. Conventional magnetic resonance imaging-based radiomic signature predicts telomerase reverse transcriptase promoter mutation status in gradeⅡandⅢgliomas[J]. Neuroradiology, 2020, 62(7): 803-813. DOI: 10.1007/s00234-020-02392-1.
[45]
Yogananda CGB, Shah BR, Nalawade SS, et al. MRI-Based Deep-Learning Method for Determining Glioma MGMT Promoter Methylation Status[J]. AJNR Am J Neuroradiol, 2021, 42(5): 845-852. DOI: 10.3174/ajnr.A7029.
[46]
沙永建, 王效春, 谭艳, 等. MRI影像组学术前预测较低级别胶质瘤IDH突变合并MGMT启动子甲基化亚型的价值[J]. 磁共振成像, 2022, 13(7): 6-11. DOI: 10.12015/issn.1674-8034.2022.07.002.
Sha YJ, Wang XC, Tan Y, et al. The value of predicting the subtype of IDH mutation combining with MGMT promoter methylation in lower grade gliomas by radiomics based on preoperative MRI[J]. Chin J Magn Reson Imaging, 2022, 13(7): 6-11. DOI: 10.12015/issn.1674-8034.2022.07.002.
[47]
Takano S, Ishikawa E, Sakamoto N, et al. Immunohistochemistry on IDH 1/2, ATRX, p53 and Ki-67 substitute molecular genetic testing and predict patient prognosis in grade Ⅲ adult diffuse gliomas[J]. Brain Tumor Pathol, 2016, 33(2): 107-116. DOI: 10.1007/s10014-016-0260-x.
[48]
Li Y, Qian Z, Xu K, et al. Radiomic features predict Ki-67 expression level and survival in lower grade gliomas[J]. J Neurooncol, 2017, 135(2): 317-324. DOI: 10.1007/s11060-017-2576-8.
[49]
Yang L, Shi P, Zhao G, et al. Targeting cancer stem cell pathways for cancer therapy[J/OL]. Signal Transduct Target Ther, 2020, 5(1): 8 [2022-07-08]. https://doi.org/10.1038/s41392-020-0110-5. DOI: 10.1038/s41392-020-0110-5.
[50]
Wu G, Song X, Liu J, et al. Expression of CD44 and the survival in glioma: a meta-analysis[J/OL]. Biosci Rep, 2020, 40(4): BSR20200520 [2022-07-08]. https://doi.org/10.1042/BSR20200520. DOI: 10.1042/bsr20200520.
[51]
Li B, McCrudden CM, Yuen HF, et al. CD133 in brain tumor: the prognostic factor[J]. Oncotarget, 2017, 8(7): 11144-11159. DOI: 10.18632/oncotarget.14406.
[52]
Wang H, Wang X, Xu L, et al. A pan-cancer perspective analysis reveals the opposite prognostic significance of CD133 in lower grade glioma and papillary renal cell carcinoma[J/OL]. Sci Prog, 2021, 104(2): 368504211010938 [2022-07-08]. https://doi.org/10.1177/00368504211010938. DOI: 10.1177/00368504211010938.
[53]
Wang Z, Tang X, Wu J, et al. Radiomics features based on T2-weighted fluid-attenuated inversion recovery MRI predict the expression levels of CD44 and CD133 in lower grade gliomas[J]. Future Oncol, 2022, 18(7): 807-819. DOI: 10.2217/fon-2021-1173.
[54]
Zhang L, Giuste F, Vizcarra JC, et al. Radiomics Features Predict CIC Mutation Status in Lower Grade Glioma[J/OL]. Front Oncol, 2020, 10: 937 [2022-10-09]. https://doi.org/10.3389/fonc.2020.00937. DOI: 10.3389/fonc.2020.00937.
[55]
Li ZZ, Liu PF, An TT, et al. Construction of a prognostic immune signature for lower grade glioma that can be recognized by MRI radiomics features to predict survival in LGG patients[J/OL]. Transl Oncol, 2021, 14(6): 101065 [2022-07-08]. https://doi.org/10.1016/j.tranon.2021.101065. DOI: 10.1016/j.tranon.2021.101065.

上一篇 深度学习在脑卒中诊断与防治中的研究进展
下一篇 弥散磁共振成像在自身免疫性脑炎的研究进展
  
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