临床参数结合CT放射组学特征预测儿童神经母细胞瘤长期疗效的研究进展
Research Advances in Predicting Long-Term Efficacy of Pediatric Neuroblastoma Using Clinical Parameters Combined with CT Radiomics Features
DOI: 10.12677/acm.2025.1592538, PDF, HTML, XML,   
作者: 李金融, 徐 晔*:重庆医科大学附属儿童医院儿科学院放射科,儿童发育疾病研究教育部重点实验室,儿童发育重大疾病国家国际科技合作基地,结构性出生缺陷与器官修复重建重庆市重点实验室,重庆
关键词: 神经母细胞瘤放射组学增强CT预后Neuroblastoma Radiomics Enhanced CT Prognosis
摘要: 神经母细胞瘤(Neuroblastoma, NB)是儿童最常见的实体性恶性肿瘤之一,预后存在较明显的个体间差异。治疗前,准确预测NB患儿的长期疗效对制定个体化的治疗方案至关重要,既往文献对影响NB疗效的各种因素均做了较深入研究。然而,鉴于恶性肿瘤生物学特征的复杂性,独立地研究个别和少数几个特征难以充分反映NB的危险性和治疗的效果。近年,放射组学作为新兴的影像分析技术受到普遍重视,该技术通过提取医学影像中的大量定量特征,为肿瘤的诊断、治疗和预后提供了新的思路。本文就近5年文献对NB的预后评估及放射组学在NB诊断的应用研究进展予以综述。
Abstract: Neuroblastoma (NB) is one of the most common solid malignancies in children, and its prognosis varies considerably among individual patients. Therefore, accurately predicting the long-term outcomes of NB children before treatment implementation is crucial for formulating individualized therapeutic regimens. The literature has conducted in-depth research on various factors influencing NB treatment efficacy. However, given the complexity of the biological characteristics of malignant tumors, studying individual or a few features in isolation is insufficient to fully reflect the risk profile of NB and the effectiveness of treatment. In recent years, radiomics, as an emerging medical image analysis technique, has provided new insights into tumor diagnosis, treatment, and prognosis by extracting large numbers of quantitative features from medical images. This article provides a review of research progress over the past five years concerning prognostic assessment in NB and the application of radiomics in NB diagnosis.
文章引用:李金融, 徐晔. 临床参数结合CT放射组学特征预测儿童神经母细胞瘤长期疗效的研究进展[J]. 临床医学进展, 2025, 15(9): 645-652. https://doi.org/10.12677/acm.2025.1592538

1. 引言

神经母细胞瘤(Neuroblastoma, NB)是儿童时期最常见的颅外实体肿瘤,占全部儿童肿瘤的6%~10%及儿童恶性肿瘤死亡病例的10%~15% [1],被俗称为“儿童癌症之王”,属于恶性程度高、预后差的恶性肿瘤。因此,准确识别NB患儿的生物学特性及评估治疗预后至关重要,直接关系到个体化治疗方案的制定与实施,以提升其生存率。

近年研究表明,NB的微环境临床特征及分子标志可在一定程度上预测患儿预后,为临床治疗方案的选择提供了有力依据[2]。随着治疗进步,低危NB患儿的预后已显著改善,但高危NB患儿的预后仍不乐观,其死亡率仍高达50%左右[3]

放射组学作为新兴领域,它通过深度学习从影像图像中提取大量定量特征,如肿瘤体积、边缘特征、纹理特征等,用以预测肿瘤分类和预后等。已有研究显示,某些放射组学特征与NB的临床预后存在关联[4]。本文拟综述近5年来NB预后评估和放射组学在NB诊断中应用的研究进展。

2. NB的临床特点

2.1. 流行病学

NB是好发于幼儿的恶性肿瘤,我国0~14岁儿童中,其发病率约为每百万人口8.8例,而在15~19岁青少年中则降至每百万人口0.8例[5]。NB起源于神经嵴细胞,该细胞参与肾上腺髓质和交感神经系统的发育,其原发部位沿神经崤发育迁移路径分布,可见于交感神经链任何部位[6],包括颈部、胸部、腹部、肾上腺及盆腔交感神经节。罕见情况下,可发生于睾丸旁,甚或缺乏明确原发灶[7]。NB的确切病因尚未完全阐明,研究提示遗传和环境因素可能是主要诱因。基因突变可导致神经母细胞异常失控增殖,某些环境暴露也可能增加风险。常见的相关基因突变涉及TRK、ALK、NMYC和MYCN等[8]-[11]

2.2. NB的诊断

目前,NB的病理诊断已较为成熟。然而,由于肿瘤存在个体差异且肿瘤细胞基因组持续演变,现有的诊断评估体系缺乏统一标准,临床实践仍在不断修订和完善。NB诊断仍以组织病理学检查为基础,需结合实验室检查、影像学检查及患者临床表现等进行综合评估[12]。目前国内外通用的临床诊断标准如下:① 病理组织活检确诊为NB;② 骨髓涂片或穿刺发现NB细胞;③ 24 h 尿香草扁桃酸定量检测显著升高;④ 影像学检查显示主要好发部位存在肿瘤,并呈现包绕、钙化等典型特征[13]。符合标准①即可确诊;若无明确病理结果,则需满足其余项中至少两项。

2.3. NB的异质性

近年研究证实,NB在组织学与临床行为方面均具有高度异质性[14] [15]。这种异质性是治疗失败和肿瘤复发的重要因素,赋予肿瘤适应性,导致其临床行为多样且复杂,极大增加了诊疗难度[16]。迄今,尚无单一生物标志物可精准预测NB预后。因此,临床诊疗通常需结合儿茶酚胺代谢物检测、影像学检查、细胞表面标志物分析、染色体及肿瘤DNA遗传学分析等多种技术,以提高诊断和风险评估准确性[17]

同时,尽管NB治疗手段近年取得显著发展,手术、靶向药物、干细胞治疗及化疗等多种方法的合理应用与联合使用极大地改善了疗效,部分发达地区中低危患儿的五年生存率已接近100% [18] [19]。需注意的是,NB患儿预后呈极端不确定性:部分患儿仅需少量干预,肿瘤即可自发消退,而另一些患者即使接受多模式强效治疗,结局仍可能不佳[20]。此外,由于极高的异质性,发生转移NB通常侵袭性更强,患者五年生存率显著低于无转移者[21] [22]。组织学指标、神经母细胞分化程度和有丝分裂–核分裂指数(MKI)对N预后有一定提示价值,但建立其与异质性导致的临床结果间的明确关联仍具挑战[23]

3. 临床指标和实验室指标对NB预后的评估

3.1. NB的临床分期与分型

当前,NB的预后预测主要依据临床分期、诊断年龄和病理组织学。最常用的分类系统包括Shimada分型、国际神经母细胞瘤分期系统(International Neuroblastoma Staging System, INSS)和国际神经母细胞瘤风险组分期系统(International Neuroblastoma Risk Group Staging System, INRGSS) [24] [25]。为更全面评估个体差异,国际儿童肿瘤协作组(Children’s Oncology Group, COG)制定了治疗前风险分层系统,该系统综合临床和分子特征,例如年龄组(<18个月与≥18个月)、INRGSS分期(L1/L2/M/MS)、组织学分类、肿瘤分化程度、DNA倍性、11q染色体状态和MYCN扩增状态(非扩增与扩增),将患者划分为极低、低、中和高风险四组[26]。此分类能直观展示患儿状况等级,对设计治疗策略及评估风险至关重要。然而,现有分期标准被认为存在不足:同一风险组内肿瘤异质性可能导致标准化治疗面临治疗不足或过度治疗风险。此外,部分最初诊断为低风险的患者可能复发,且复发肿瘤常更具侵袭性和难治性[27]。因此,探寻更多有效的预后相关因素对于优化风险分层及治疗方案制定至关重要。

3.2. 与NB预后相关的其他危险因素

除临床分期外,更多的危险因素近年被发现与预后相关[28]。例如,部分实验室参数(如高水平的铁蛋白、神经元特异性烯醇化酶(NSE)、乳酸脱氢酶(LDH)、尿儿茶酚胺代谢产物)、分子病理特征(如MYCN癌基因扩增、1p36染色体缺失)以及骨/骨髓受累状态,均可用于评估治疗反应及预后[29]-[33]。与传统临床指标相似,这些检测信息共同构成了NB预后评估的重要环节,有助于临床医生更准确地判定风险等级,进而制定合理治疗方案。然而,即使有精密的风险评估系统支持,因NB的高度异质性,对高危患儿的精准分层与预后判断仍面临巨大挑战[34] [35]。现有预后评估系统仍存缺陷,临床实践中依此治疗导致治疗过度或不足的情况并不少见。例如,MYCN过度表达是预后不良的标志,但仅见于40%~50%的高危患儿[36]。许多高危患儿并不存在MYCN高表达,表明现有标志物尚不能完全满足诊疗需求,亟需更多评估手段以精准分层风险,指导合理治疗,从而提升患者生存率并减少治疗副作用。

4. 放射组学在NB预后评估中的应用

4.1. 放射组学用于儿科疾病研究的意义

发展无创或微创检查技术是临床的重要方向。放射组学(radiomics)作为一种非侵入性技术,在肿瘤诊断与预后评估中具有独特优势,多项研究已证实其对恶性肿瘤患者预后的预测价值[37]

放射组学利用先进的计算分析技术,将医学图像转化为定量特征,通过高通量数据分析获取与疾病诊疗相关的数字化影像信息[38] [39]。其目标在于提升决策支持和预测的可靠性,同时兼具成本低、无创的优势[40]。这些创新方法为改善风险分层和预后评估提供了新角度,有望为NB提供更个性化、更有效的治疗策略。目前,部分研究已证实放射组学应用于NB研究的巨大潜力。

4.2. 18F-FDG PET/CT放射组学在NB中的应用

正电子发射体层摄影术(positron emission tomography,PET)利用正电子核素示踪剂显像,可提供生理与代谢过程信息。临床最常用的示踪剂18氟–脱氧葡萄糖(18F-fluorodeoxyglucose, 18F-FDG)能显示肿瘤代谢活性,有助于NB的病理改变检测及转移灶判断。

研究表明,基于18F-FDG PET/CT的放射组学可预测肿瘤复发风险[41] [42]。例如,一项纳入84例高危NB患者的研究,结合临床参数与放射组学特征构建预测模型,该模型显示出对复发的良好预测高能力及高区分度[43]。该类模型高效简便,有望成为指导高危NB患者健康管理的临床决策支持工具。需注意的是,PET/CT成本较高,且对微小病灶的检测存在局限[44],其广泛推广仍需时日。

4.3. MRI放射组学在NB中的应用

相较于其它影像技术,MRI具有优异的软组织分辨率和无辐射优势,在儿童实体瘤诊断中的应用日益普遍。然而,目前多数NB放射组学研究集中于CT和PET/CT图像,针对MRI的研究报道较少。

Wang H等人[45]研究发现,T2WI放射组学特征结合初诊年龄,可为NB与神经节神经母细胞瘤/神经节细胞瘤的鉴别提供定量方法。MRI在评估肿瘤范围、邻近器官侵犯及转移灶(尤其肝脏和骨髓转移)方面具有优势,且无辐射风险,已成为NB评估的首选成像方式[46]。其局限性在于检查时间较长、噪音较大,对低龄患儿的应用存在一定挑战。

4.4. CT放射组学在NB中的应用

CT是NB诊疗中最常用的影像学手段,可评估原发肿瘤、局部侵袭及转移灶,并为手术设计提供依据[47]。增强CT不仅能早期发现病变,还能明确肿瘤位置、大小、血供及与周围结构的关系,为穿刺和手术提供关键信息,在NB诊疗中价值显著[28] [29]

病理学家在准确区分NB的病理分型时经常面临挑战,Wang H等人[48]在他们的研究中利用297名患者的CT增强影像进行放射组学分析并构建模型,研究发现在训练组中,CT增强放射组学模型的曲线下面积(AUC)达到了0.851,在测试组中,放射组学模型的AUC达到了0.816。Zhao L [49]等人的研究同样表明,CT放射组学分类器预测NB病理亚型的总体准确率达80.8%,体现出CT的放射组学分析显示出在区分NB病理分型方面的良好诊断能力。

MYCN扩增在对NB患者的高危亚组进行分类方面发挥着关键作用,Wang H等人[50]的研究中纳入78名患者,将放射组学特征与临床因素相结合建立模型以预测儿科NB患者MYCN基因的扩增,与单独的临床模型相比,基于放射组学特征和两个临床因素的临床放射组学列线图显示出更好的预测性能(训练队列的AUC:0.95 vs. 0.82,测试队列的AUC:0.91 vs. 0.70)。此外,基于增强CT的放射组学显示出识别高危NB的能力,并可能为识别高危病例提供补充图像生物标志物[51]

在另一项双中心研究中,Zhang Y等[52]纳入289例患儿,利用17个增强CT放射组学特征构建模型。其列线图在训练(AUC = 0.87)、测试(AUC = 0.83)及外部验证(AUC = 0.84)队列中的AUC值均高于其他对比模型。

Liu G [4]等人结合机器学习模型提取放射组学特征,可更有效地挖掘与预后相关的信息,突显CT放射组学在NB预后评估中的潜力。鉴于CT的普遍性和成像优势,其放射组学研究对NB至关重要。

综上可见,放射组学具有极其卓越的活力,相较于传统的检测方法,CT放射组学可以对整个肿瘤进行分析,不仅仅局限于活检取样的局部区域,而是提供更全面的肿瘤特征信息,并且通过计算机算法提取和分析影像特征,减少了人为主观因素的影响,提高了评估的客观性和可重复性,还可以同时分析肿瘤的形态、密度、纹理等多个维度的特征,提供更丰富的预后相关信息以建立预测模型,为每个患者提供个体化的预后评估。值得注意的是,应用放射组学虽然可以发现影像特征与预后的相关性,然而其背后的生物学机制往往不清楚,如何将放射组学结果与临床、病理、分子等其他预后因素有效整合,仍需进一步研究,在样本量有限的情况下,模型可能存在过拟合风险,影响其在新数据上的泛化能力,此外一些复杂的机器学习算法可能难以解释,这将影响临床医生对结果的理解和接受。

5. 讨论与展望

NB的治疗和预后评估是当前研究热点。单一临床参数或传统影像学检查均难以全面表征肿瘤,现有预后预测方法仍存在局限。放射组学的引入为NB的预后研究提供了极具潜力的新途径,展现出广阔的应用前景。目前,基于CT、MRI及PET/CT的放射组学研究已在NB领域取得显著成果。然而,作为影像分析工具,放射组学也面临应用范围的局限。需通过更多研究克服当前挑战(如特征标准化、模型可解释性及多中心验证),以提升其临床实用价值。未来,整合放射组学与临床、病理、生化和基因学,例如影像基因组学,有望更全面揭示NB发生发展规律,从而提升预后判断准确性,并优化个体化诊疗策略。

NOTES

*通讯作者。

参考文献

[1] Irwin, M.S. and Park, J.R. (2015) Neuroblastoma: Paradigm for precision Medicine. Pediatric Clinics of North America, 62, 225-256.
https://doi.org/10.1016/j.pcl.2014.09.015
[2] Cheng, H., Zhang, L., Yang, S., Ren, Q., Chang, S., Jin, Y., et al. (2023) Integration of Clinical Characteristics and Molecular Signatures of the Tumor Microenvironment to Predict the Prognosis of Neuroblastoma. Journal of Molecular Medicine, 101, 1421-1436.
https://doi.org/10.1007/s00109-023-02372-x
[3] Moreno, L., Guo, D., Irwin, M.S., Berthold, F., Hogarty, M., Kamijo, T., et al. (2020) A Nomogram of Clinical and Biologic Factors to Predict Survival in Children Newly Diagnosed with High‐Risk Neuroblastoma: An International Neuroblastoma Risk Group Project. Pediatric Blood & Cancer, 68, e28794.
https://doi.org/10.1002/pbc.28794
[4] Liu, G., Poon, M., Zapala, M.A., Temple, W.C., Vo, K.T., Matthay, K.K., et al. (2022) Incorporating Radiomics into Machine Learning Models to Predict Outcomes of Neuroblastoma. Journal of Digital Imaging, 35, 605-612.
https://doi.org/10.1007/s10278-022-00607-w
[5] Okawa, S. and Saika, K. (2022) International Variations in Neuroblastoma Incidence in Children and Adolescents. Japanese Journal of Clinical Oncology, 52, 656-658.
https://doi.org/10.1093/jjco/hyac079
[6] Jiang, M., Stanke, J. and Lahti, J.M. (2011) The Connections between Neural Crest Development and Neuroblastoma. Current Topics in Developmental Biology, 94, 77-127.
https://doi.org/10.1016/b978-0-12-380916-2.00004-8
[7] Muntean, L., Falup-Pecurariu, O., Voda, D. and Papa, A. (2022) Primary Paratesticular Neuroblastoma in a Newborn—Case Presentation and Literature Review. Pediatrics & Neonatology, 63, 315-316.
https://doi.org/10.1016/j.pedneo.2021.11.006
[8] Hong, S.H., Wietlisbach, L., Galli, S., Mahajan, A., Zhu, S., Tilan, J., et al. (2017) Abstract 1940: Prenatal Stress Increases Malignancy of Neuroblastoma Tumors in TH-MYCN Animal Model. Cancer Research, 77, 1940-1940.
https://doi.org/10.1158/1538-7445.am2017-1940
[9] Brodeur, G.M., Minturn, J.E., Ho, R., Simpson, A.M., Iyer, R., Varela, C.R., et al. (2009) TRK Receptor Expression and Inhibition in Neuroblastomas. Clinical Cancer Research, 15, 3244-3250.
https://doi.org/10.1158/1078-0432.ccr-08-1815
[10] Longo, L., Panza, E., Schena, F., Seri, M., Devoto, M., Romeo, G., et al. (2007) Genetic Predisposition to Familial Neuroblastoma: Identification of Two Novel Genomic Regions at 2p and 12p. Human Heredity, 63, 205-211.
https://doi.org/10.1159/000099997
[11] Mossé, Y.P., Laudenslager, M., Longo, L., Cole, K.A., Wood, A., Attiyeh, E.F., et al. (2008) Identification of ALK as a Major Familial Neuroblastoma Predisposition Gene. Nature, 455, 930-935.
https://doi.org/10.1038/nature07261
[12] Schumacher‐Kuckelkorn, R., Volland, R., Gradehandt, A., Hero, B., Simon, T. and Berthold, F. (2016) Lack of Immunocytological GD2 Expression on Neuroblastoma Cells in Bone Marrow at Diagnosis, during Treatment, and at Recurrence. Pediatric Blood & Cancer, 64, 46-56.
https://doi.org/10.1002/pbc.26184
[13] 中国抗癌协会小儿肿瘤专业委员会, 中华医学会小儿外科学分会肿瘤学组. 儿童神经母细胞瘤诊疗专家共识CCCG-NB-2021方案[J]. 中华小儿外科杂志, 2022, 43(7): 588-598.
[14] Maris, J.M., Hogarty, M.D., Bagatell, R. and Cohn, S.L. (2007) Neuroblastoma. The Lancet, 369, 2106-2120.
https://doi.org/10.1016/s0140-6736(07)60983-0
[15] Caron, H.N. (2010) Are Thoracic Neuroblastomas Really Different? Pediatric Blood & Cancer, 54, 867-867.
https://doi.org/10.1002/pbc.22470
[16] McGranahan, N. and Swanton, C. (2017) Clonal Heterogeneity and Tumor Evolution: Past, Present, and the Future. Cell, 168, 613-628.
https://doi.org/10.1016/j.cell.2017.01.018
[17] Johnsen, J.I., Dyberg, C. and Wickström, M. (2019) Neuroblastoma—A Neural Crest Derived Embryonal Malignancy. Frontiers in Molecular Neuroscience, 12, Article 9.
https://doi.org/10.3389/fnmol.2019.00009
[18] Nuchtern, J.G., London, W.B., Barnewolt, C.E., Naranjo, A., McGrady, P.W., Geiger, J.D., et al. (2012) A Prospective Study of Expectant Observation as Primary Therapy for Neuroblastoma in Young Infants. Annals of Surgery, 256, 573-580.
https://doi.org/10.1097/sla.0b013e31826cbbbd
[19] Whittle, S.B., Smith, V., Doherty, E., Zhao, S., McCarty, S. and Zage, P.E. (2017) Overview and Recent Advances in the Treatment of Neuroblastoma. Expert Review of Anticancer Therapy, 17, 369-386.
https://doi.org/10.1080/14737140.2017.1285230
[20] Pinto, N.R., Applebaum, M.A., Volchenboum, S.L., Matthay, K.K., London, W.B., Ambros, P.F., et al. (2015) Advances in Risk Classification and Treatment Strategies for Neuroblastoma. Journal of Clinical Oncology, 33, 3008-3017.
https://doi.org/10.1200/jco.2014.59.4648
[21] Jamal-Hanjani, M., Quezada, S.A., Larkin, J. and Swanton, C. (2015) Translational Implications of Tumor Heterogeneity. Clinical Cancer Research, 21, 1258-1266.
https://doi.org/10.1158/1078-0432.ccr-14-1429
[22] Ramón y Cajal, S., Sesé, M., Capdevila, C., Aasen, T., De Mattos-Arruda, L., Diaz-Cano, S.J., et al. (2020) Clinical Implications of Intratumor Heterogeneity: Challenges and Opportunities. Journal of Molecular Medicine, 98, 161-177.
https://doi.org/10.1007/s00109-020-01874-2
[23] Teshiba, R., Kawano, S., Wang, L.L., He, L., Naranjo, A., London, W.B., et al. (2014) Age-Dependent Prognostic Effect by Mitosis-Karyorrhexis Index in Neuroblastoma: A Report from the Children’s Oncology Group. Pediatric and Developmental Pathology, 17, 441-449.
https://doi.org/10.2350/14-06-1505-oa.1
[24] Monclair, T., Brodeur, G.M., Ambros, P.F., Brisse, H.J., Cecchetto, G., Holmes, K., et al. (2009) The International Neuroblastoma Risk Group (INRG) Staging System: An INRG Task Force Report. Journal of Clinical Oncology, 27, 298-303.
https://doi.org/10.1200/jco.2008.16.6876
[25] Cohn, S.L., Pearson, A.D.J., London, W.B., Monclair, T., Ambros, P.F., Brodeur, G.M., et al. (2009) The International Neuroblastoma Risk Group (INRG) Classification System: An INRG Task Force Report. Journal of Clinical Oncology, 27, 289-297.
https://doi.org/10.1200/jco.2008.16.6785
[26] Campbell, K., Kao, P., Naranjo, A., Kamijo, T., Ramanujachar, R., London, W.B., et al. (2022) Clinical and Biological Features Prognostic of Survival after Relapse or Progression of INRGSS Stage MS Pattern Neuroblastoma: A Report from the International Neuroblastoma Risk Group (INRG) Project. Pediatric Blood & Cancer, 70, e30054.
https://doi.org/10.1002/pbc.30054
[27] Chang, H., Liu, Y., Lu, M., Jou, S., Yang, Y., Lin, D., et al. (2016) A Multidisciplinary Team Care Approach Improves Outcomes in High-Risk Pediatric Neuroblastoma Patients. Oncotarget, 8, 4360-4372.
https://doi.org/10.18632/oncotarget.13874
[28] Spix, C., Pastore, G., Sankila, R., Stiller, C.A. and Steliarova-Foucher, E. (2006) Neuroblastoma Incidence and Survival in European Children (1978-1997): Report from the Automated Childhood Cancer Information System Project. European Journal of Cancer, 42, 2081-2091.
https://doi.org/10.1016/j.ejca.2006.05.008
[29] Brodeur, G.M. (2003) Neuroblastoma: Biological Insights into a Clinical Enigma. Nature Reviews Cancer, 3, 203-216.
https://doi.org/10.1038/nrc1014
[30] Brodeur, G.M., Fong, C.T., Morita, M., Griffith, R., Hayes, F.A. and Seeger, R.C. (1988) Molecular Analysis and Clinical Significance of N-Myc Amplification and Chromosome 1p Monosomy in Human Neuroblastomas. Progress in Clinical and Biological Research, 271, 3-15.
[31] Brodeur, G.M., Seeger, R.C., Barrett, A., Berthold, F., Castleberry, R.P., D’Angio, G., et al. (1988) International Criteria for Diagnosis, Staging, and Response to Treatment in Patients with Neuroblastoma. Journal of Clinical Oncology, 6, 1874-1881.
https://doi.org/10.1200/jco.1988.6.12.1874
[32] Brodeur, G.M., Seeger, R.C., Schwab, M., Varmus, H.E. and Bishop, J.M. (1984) Amplification of N-myc in Untreated Human Neuroblastomas Correlates with Advanced Disease Stage. Science, 224, 1121-1124.
https://doi.org/10.1126/science.6719137
[33] Cheung, N.V., Ostrovnaya, I., Kuk, D. and Cheung, I.Y. (2015) Bone Marrow Minimal Residual Disease Was an Early Response Marker and a Consistent Independent Predictor of Survival after Anti-GD2 Immunotherapy. Journal of Clinical Oncology, 33, 755-763.
https://doi.org/10.1200/jco.2014.57.6777
[34] Smith, V. and Foster, J. (2018) High-Risk Neuroblastoma Treatment Review. Children, 5, Article 114.
https://doi.org/10.3390/children5090114
[35] Tolbert, V.P. and Matthay, K.K. (2018) Neuroblastoma: Clinical and Biological Approach to Risk Stratification and Treatment. Cell and Tissue Research, 372, 195-209.
https://doi.org/10.1007/s00441-018-2821-2
[36] Depuydt, P., Boeva, V., Hocking, T.D., Cannoodt, R., Ambros, I.M., Ambros, P.F., et al. (2018) Genomic Amplifications and Distal 6q Loss: Novel Markers for Poor Survival in High-Risk Neuroblastoma Patients. JNCI: Journal of the National Cancer Institute, 110, 1084-1093.
https://doi.org/10.1093/jnci/djy022
[37] Lambin, P., Rios-Velazquez, E., Leijenaar, R., Carvalho, S., van Stiphout, R.G.P.M., Granton, P., et al. (2012) Radiomics: Extracting More Information from Medical Images Using Advanced Feature Analysis. European Journal of Cancer, 48, 441-446.
https://doi.org/10.1016/j.ejca.2011.11.036
[38] Zhang, X., Zhang, Y., Zhang, G., Qiu, X., Tan, W., Yin, X., et al. (2022) Deep Learning with Radiomics for Disease Diagnosis and Treatment: Challenges and Potential. Frontiers in Oncology, 12, Article 773840.
https://doi.org/10.3389/fonc.2022.773840
[39] Sarker, I.H. (2021) Deep Learning: A Comprehensive Overview on Techniques, Taxonomy, Applications and Research Directions. SN Computer Science, 2, Article No. 420.
https://doi.org/10.1007/s42979-021-00815-1
[40] Liu, S., Sun, W., Yang, S., Duan, L., Huang, C., Xu, J., et al. (2021) Deep Learning Radiomic Nomogram to Predict Recurrence in Soft Tissue Sarcoma: A Multi-Institutional Study. European Radiology, 32, 793-805.
https://doi.org/10.1007/s00330-021-08221-0
[41] Kirienko, M., Sollini, M., Corbetta, M., Voulaz, E., Gozzi, N., Interlenghi, M., et al. (2021) Radiomics and Gene Expression Profile to Characterise the Disease and Predict Outcome in Patients with Lung Cancer. European Journal of Nuclear Medicine and Molecular Imaging, 48, 3643-3655.
https://doi.org/10.1007/s00259-021-05371-7
[42] Eertink, J.J., van de Brug, T., Wiegers, S.E., Zwezerijnen, G.J.C., Pfaehler, E.A.G., Lugtenburg, P.J., et al. (2021) 18F-FDG PET Baseline Radiomics Features Improve the Prediction of Treatment Outcome in Diffuse Large B-Cell Lymphoma. European Journal of Nuclear Medicine and Molecular Imaging, 49, 932-942.
https://doi.org/10.1007/s00259-021-05480-3
[43] Feng, L., Qian, L., Yang, S., Ren, Q., Zhang, S., Qin, H., et al. (2022) Clinical Parameters Combined with Radiomics Features of PET/CT Can Predict Recurrence in Patients with High-Risk Pediatric Neuroblastoma. BMC Medical Imaging, 22, Article No. 102.
https://doi.org/10.1186/s12880-022-00828-z
[44] 苏勇, 赵充, 谢传淼, 等. 鼻咽癌咽后淋巴结转移的CT、MRI和PET-CT诊断的对比研究[J]. 癌症, 2006, 25(5): 521-525.
https://doi.org/10.3969/j.issn.1000-467X.2006.05.001
[45] Wang, H., Chen, X., Yu, W., Xie, M., Zhang, L., Ding, H., et al. (2023) Whole-Tumor Radiomics Analysis of T2-Weighted Imaging in Differentiating Neuroblastoma from Ganglioneuroblastoma/Ganglioneuroma in Children: An Exploratory Study. Abdominal Radiology, 48, 1372-1382.
https://doi.org/10.1007/s00261-023-03862-9
[46] Callahan, M.J., MacDougall, R.D., Bixby, S.D., Voss, S.D., Robertson, R.L. and Cravero, J.P. (2017) Ionizing Radiation from Computed Tomography versus Anesthesia for Magnetic Resonance Imaging in Infants and Children: Patient Safety Considerations. Pediatric Radiology, 48, 21-30.
https://doi.org/10.1007/s00247-017-4023-6
[47] Burnand, K., Barone, G., McHugh, K. and Cross, K. (2019) Preoperative Computed Tomography Scanning for Abdominal Neuroblastomas Is Superior to Magnetic Resonance Imaging for Safe Surgical Planning. Pediatric Blood & Cancer, 66, e27955.
https://doi.org/10.1002/pbc.27955
[48] Wang, H., Xie, M., Chen, X., Zhu, J., Zhang, L., Ding, H., et al. (2023) Radiomics Analysis of Contrast-Enhanced Computed Tomography in Predicting the International Neuroblastoma Pathology Classification in Neuroblastoma. Insights into Imaging, 14, Article No. 106.
https://doi.org/10.1186/s13244-023-01418-5
[49] Zhao, L., Shi, L., Huang, S., Cai, T., Guo, W., Gao, X., et al. (2023) Identification and Validation of Radiomic Features from Computed Tomography for Preoperative Classification of Neuroblastic Tumors in Children. BMC Pediatrics, 23, Article No. 262.
https://doi.org/10.1186/s12887-023-04057-3
[50] Wu, H., Wu, C., Zheng, H., Wang, L., Guan, W., Duan, S., et al. (2020) Radiogenomics of Neuroblastoma in Pediatric Patients: CT-Based Radiomics Signature in Predicting MYCN Amplification. European Radiology, 31, 3080-3089.
https://doi.org/10.1007/s00330-020-07246-1
[51] Wang, H., Xie, M., Chen, X., Zhu, J., Ding, H., Zhang, L., et al. (2023) Development and Validation of a CT‐Based Radiomics Signature for Identifying High‐Risk Neuroblastomas under the Revised Children’s Oncology Group Classification System. Pediatric Blood & Cancer, 70, e30280.
https://doi.org/10.1002/pbc.30280
[52] Zhang, Y., Yang, Y., Ning, G., Wu, X., Yang, G. and Li, Y. (2023) Contrast Computed Tomography-Based Radiomics Is Correlation with COG Risk Stratification of Neuroblastoma. Abdominal Radiology, 48, 2111-2121.
https://doi.org/10.1007/s00261-023-03875-4