胰腺神经内分泌瘤研究热点与趋势:2015~2024年文献计量分析
Research Trends and Hotspots on Pancreatic Neuroendocrine Tumor: A Bibliometric Analysis from 2015 to 2024
DOI: 10.12677/acm.2026.163969, PDF, HTML, XML,   
作者: 袁 瑞, 邓 亮*:重庆医科大学附属第一医院消化内科,重庆;张 可:重庆医科大学附属第一医院放射科,重庆
关键词: 胰腺肿瘤胰腺神经内分泌瘤文献计量分析Pancreatic Neoplasms Pancreatic Neuroendocrine Tumor Bibliometric Analysis
摘要: 背景:胰腺神经内分泌瘤是一种临床罕见且具有高度异质性的肿瘤,其发病率正逐年增加。本研究旨在通过文献计量学方法,系统地分析胰腺神经内分泌瘤领域内的研究现状、热点与趋势,为临床工作者和研究者提供参考。方法:本研究基于Web of Science核心合集数据库,借助VOSviewer、CiteSpace软件对胰腺神经内分泌瘤研究的发文趋势、发文期刊、国际合作情况、机构发文情况及研究热点进行可视化分析。结果:共检索到相关文献2527篇,其中中国是发文数量最多的国家(986篇,39.02%),阿姆斯特丹大学是发文数量最多的研究机构(110篇,4.35%),深度学习与人工智能是目前突现强度最高的关键词,人工智能与免疫浸润已成为该领域关键研究领域。结论:本研究发现深度学习与人工智能是最突出且快速发展的研究主题,免疫浸润也成为重要研究方向。未来胰腺神经内分泌瘤领域的研究热点或许正从肿瘤生物学和治疗策略转向诊断与预后研究。
Abstract: Background: Pancreatic neuroendocrine tumors (pNETs) are rare but clinically heterogeneous neoplasms with increasing incidence. We aimed to conduct a comprehensive bibliometric analysis of publications related to pNET in order to elucidate the current research trends and forecast future hotspots in this field. Methods: Articles correlated with pNET published from 2015 to 2024 were searched from the Web of Science Core Collection. Then, the searched data were analyzed using VOSviewer, CiteSpace, and R language. Finally, burst detection, clustering analysis and thematic map analysis were performed to identify shifts in the research frontier of pNET. Results: Since 2015, a total of 2527 articles on pNET have been published. China was the leading contributor among all countries (986, 39.02%), while the University of Amsterdam ranked first (110, 4.35%) among institutions. Deep learning and artificial intelligence were citation key words with the strongest ongoing bursts. Key research areas include artificial intelligence and immune infiltration. Conclusions: The study identifies deep learning and artificial intelligence as the most prominent and rapidly evolving research themes, with immune infiltration also emerging as a key area of interest. These findings indicate a shift in research hotspots from tumor biology and treatment strategies to diagnostics and prognosis.
文章引用:袁瑞, 张可, 邓亮. 胰腺神经内分泌瘤研究热点与趋势:2015~2024年文献计量分析[J]. 临床医学进展, 2026, 16(3): 1831-1844. https://doi.org/10.12677/acm.2026.163969

1. 引言

胰腺癌是一种预后极差的恶性肿瘤,其中约占90%的病例为胰腺导管腺癌(PDAC),它起源于胰腺导管上皮细胞,是导致胰腺癌高死亡率的主要原因[1]。另外,有一类生物学行为和治疗方式完全不同的肿瘤,称为胰腺神经内分泌肿瘤(pNEN),约占胰腺恶性肿瘤的1%~2% [2]。根据世界卫生组织,胰腺神经内分泌肿瘤上可进一步分为分化良好的胰腺神经内分泌瘤(pNET)、低分化的胰腺神经内分泌癌(pNEC)以及混合性神经内分泌–非神经内分泌肿瘤(MiNEN),根据Ki-67指数和/或核分裂象计数,胰腺神经内分泌肿瘤(pNET)又可分为G1级至G3级[3]。根据pNET患者是否出现因肿瘤分泌相关激素所导致相应临床表现,可将其分为功能性和无功能性,其中最常见的功能性pNET为胰岛素瘤。鉴于pNET肿瘤细胞起源的功能特性和生物学行为的多样性,患者可出现从无症状到激素相关综合征及局部占位压迫等多种表现。pNET作为一种临床表现高度异质性的罕见疾病,近年来发病率正逐渐上升[4]

不同于PDAC,pNET通常预后更好。pNET的五年生存率因疾病分期而异,总体五年生存率为53% [5]。pNET患者可从早期治疗中获益,接受手术干预的患者五年生存率高达95%,而接受药物或保守治疗的患者可达65%。即使在发生肝脏转移的pNET病例中,其五年生存率仍可达40% [6]。然而,仅凭临床表现和医学影像学检查很难精准区分pNET与PDAC [7] [8]。尽早诊断pNET并为患者提供个体化治疗策略,对延长患者无进展生存期(PFS)和提高患者生活质量至关重要。因此,我们拟对近10年pNET相关领域研究文献进行系统分析,旨在为临床工作者和研究者提供参考。

文献计量学分析作为一种强大的工具,能够通过分析和可视化学术文献来揭示研究现状、热点及未来发展趋势,帮助研究者更好地把握前沿进展,并为临床实践提供指导[9]。迄今为止,研究者们对罕见病如pNET关注度日益提高,但该领域的综合性参考资料仍较为有限[10]-[15]。因此,本文基于Web of Science核心合集中的出版物,使用文献计量学方法,系统梳理pNET相关研究与进展概况,为全面理解pNET研究热点与未来方向提供参考依据。

2. 研究资料与方法

本研究选取Web of Science核心合集数据库作为数据源,以(((((TS = (''pancreatic neuroendocrine tumor*'')) OR TS = (''pNET*'')) OR TS = (''pancreatic NET*'')) AND ((TS = (''pancreatic cancer*'')) OR TS = (''pancreatic carcinoma*''))) NOT (((TS = (''pancreatic neuroendocrine cancer*'')) OR TS = (''pNEC*'')) OR TS = (''pancreatic NEC*''))) AND LA = (English)为检索式,对2015-01-01/2024-10-06在Web of Science核心合集数据库中的关于pNET文章进行主题词检索,应用CiteSpace、VOSviewer软件对文献作者、机构、国家、关键词以及文献共被引量进行可视化分析。

3. 研究结果

3.1. 年度发文趋势

从2015年至2024年,胰腺神经内分泌瘤(pNET)相关研究数量增长迅速,并于2022年达到最高值(344篇)。值得注意的是,2016年文献的被引次数相对突出,说明该时期研究可能对后续进展起到了关键推动作用。总体来看,2015年后研究数量的持续增加,标志着该罕见疾病正逐渐成为学术研究的热点之一(图1)。

Figure 1. Number of publication per year

1. 年度发文量

3.2. 国际合作网络分析

共有78个国家参与了胰腺神经内分泌肿瘤(pNET)的相关研究。其中,中国、美国、德国、荷兰、日本和意大利的发文量较高。这些研究以单一国家研究为主,跨国合作研究占比较小(图2(a))。尽管中国在发文总量上位居首位,但美国在跨国合作方面更为活跃,合作国家包括英国、韩国和日本等。该领域的所有国家间均存在合作关系(图2(b))。图中连线宽度代表合作紧密程度,连线越宽表示合作越密切。分析结果显示,当前pNET研究领域的国际合作程度整体较低。

(a)

(b)

Figure 2. (a) National cooperation network diagram; (b) Country collaboration map

2. (a) 国家合作网络图;(b) 国家合作地理分布图

3.3. 高产出机构与作者

根据研究发表量,本文对排名前十的作者及机构进行了分析,以识别pNET领域的关键研究者与核心研究机构(表1图3)。其中,荷兰阿姆斯特丹大学及其学者Marc G Besselink教授的发文量最高。阿姆斯特丹大学共发表相关论文245篇,德克萨斯大学系统发表206篇,二者发文量合计占该领域文献总量的17%。基于发文量与总被引次数,Marc G Besselink均位列作者首位。

(a)

(b)

Figure 3. (a) The top 10 institutions based on publication; (b) Network diagram of institution cooperation

3. (a) 机构发文量前十排名;(b) 机构合作网络可视化图

Table 1. The top 10 most active authors (sorted by article count)

1. 前十位活跃作者(按发文量排序)

Rank

Author

Article counts

Total number of citations

H index

G index

1

BESSELINK MARC G.

62

1588

23

38

2

BUSCH OLIVIER R.

32

892

16

29

3

VAN LAARHOVEN HANNEKE W. M.

23

568

12

23

4

BONSING BERT A.

22

766

11

22

5

DE HINGH IGNACE H. J. T.

24

611

11

24

6

KOERKAMP BAS GROOT

25

653

11

25

7

VAN EIJCK CASPER H. J.

24

636

11

24

8

VAN SANTVOORT HJALMAR C.

26

615

11

24

9

WILMINK JOHANNA W.

28

873

11

28

10

DE HINGH IGNACE H.

14

509

10

14

3.4. 期刊来源分布

截至2024年10月,共有100种SCI期刊发表了2527篇与胰腺神经内分泌肿瘤(pNET)及胰腺癌相关的文献。本研究按总被引频次筛选出发文量最高的前10种期刊(表2),其累计发文量占全部文献的70.38%。其中,ONCOTARGET为被引频次最高的期刊(被引1108次),SCIENTIFIC REPORTS位列第二(被引839次),这两种期刊在pNET领域均具有较高的学术声誉。根据Web of Science分类信息,相关期刊主要涉及肿瘤学、细胞生物学、外科学及胃肠肝病学等领域。图4为期刊双图叠加分析结果,图中左侧为施引期刊分布,右侧为被引期刊分布,展示了相关研究的主题分布特征。该图谱显示,几乎所有pNET相关文献集中发表在“医学–临床”与“分子生物学–免疫学”两个学科群中,而该领域的知识基础主要来源于右侧图谱中的“健康–护理–医学”与“分子生物学–遗传学”两个学科群。

Table 2. The top 10 most active journals (sorted by article count)

2. 前十位活跃期刊(按发文量排序)

Rank

Journal title

Article counts

Total number of citations

H index

G index

1

ONCOTARGET

32

1108

19

32

2

SCIENTIFIC REPORTS

54

839

16

27

3

ANNALS OF SURGICAL ONCOLOGY

30

643

14

25

4

CLINICAL CANCER RESEARCH

18

919

14

18

5

PLOS ONE

27

484

14

21

6

BMC CANCER

36

946

13

30

7

PANCREAS

32

602

13

24

8

FRONTIERS IN ONCOLOGY

56

422

12

17

9

CANCERS

54

467

11

19

10

ONCOLOGY LETTERS

34

402

11

18

Figure 4. Dual-map overlay of journals

4. 期刊双引叠加图

Rank

Title

Journal

Author

Publication year

1

Genomic analyses identify molecular subtypes of pancreatic cancer

NATURE

BAILEY P

2016

2

Neuroendocrine neoplasms of the pancreas at dynamic enhanced CT: comparison between grade 3 neuroendocrine carcinoma and grade 1/2 neuroendocrine tumour

EUR RADIOL

KIM DW

2015

3

Nationwide trends in incidence, treatment and survival of pancreatic ductal adenocarcinoma

EUR J CANCER

LATENSTEIN AEJ

2020

4

Prognostic relevance of molecular subtypes and master regulators in pancreatic ductal adenocarcinoma

BMC CANCER

JANKY R

2016

5

Ten hub genes associated with progression and prognosis of pancreatic carcinoma identified by co-expression analysis

INT J BIOL SCI

ZHOU Z

2018

6

Pancreatic stellate cells support tumour metabolism through autophagic alanine secretion

NATURE

SOUSA CM

2016

7

Underestimation of pancreatic cancer in the national cancer registry - Reconsidering the incidence and survival rates

EUR J CANCER

FEST J

2017

8

Weighted gene co-expression network analysis reveals key genes involved in pancreatic ductal adenocarcinoma development

CELL ONCOL

GIULIETTI M

2016

9

Pancreatic neuroendocrine tumor: prediction of the tumor grade using CT findings and computerized texture analysis

ACTA RADIOL

CHOI TW

2018

10

Contrast enhancement pattern on multidetector CT predicts malignancy in pancreatic endocrine tumours

EUR RADIOL

CAPPELLI C

2015

3.6. 引文突现分析

引文突现是指参考文献在特定时间段内被引频次显著高于通常水平的现象,该分析有助于追踪研究热点随时间的演变趋势。图6展示了突现强度最高的前25篇文献,其中红色线段表示高被引突现阶段,蓝色线段表示低被引阶段。突现强度最高的文献为Daniel D Von Hoff等人发表的《白蛋白结合型紫杉醇联合吉西他滨可延长胰腺癌患者生存期》(突现强度 = 15.87,突现期 = 2015~2018年) [16]

Figure 6. The top 25 references with the strongest citation burst

6. 被引突现性最高的前25篇参考文献

3.7. 关键词分析

(a)

(b)

(c)

Figure 7. (a) Word cloud of key words; (b) The top 25 keywords with the strongest citation burst; (C) Co-occurrence network diagram of high-frequency keywords. Each node resents a key word, and a larger node means higher frequency

7. (a) 关键词词云图;(b) 突现性最高的前25个关键词;(c) 高频关键词共现网络图。图中节点代表关键词,节点大小与其出现频次正相关

关键词是文章核心内容的凝练,有助于观察研究主题间的关联及领域发展方向。本研究提取并聚类了出现频次最高的25个关键词(图7(b)),展示了近十年来pNET领域的关键词突现情况。其中,深度学习、人工智能、影像及炎症等关键主题词在近四年关注度显著上升,且目前仍处于突现阶段,提示其可能成为未来的潜在研究热点。

4. 讨论

本研究利用文献计量分析系统性梳理了2015至2024年间pNET相关研究的热点与进展。我们的分析结果表明,近年来pNET研究热点领域已从肿瘤生物学与治疗策略逐渐转向诊断与预后。其中,促炎因子已成为关注重点,而人工智能在pNET诊断中的应用同样引起了重视。

关键词作为论文研究主题的高度概括,在文献检索与分类中具有重要作用[17]。本文所析出的前25个高频关键词大致可分为三个类别(图7(b))。第一类可分为研究时段早期(2015~2016年),此时pNET领域主要关注肿瘤细胞的组织学来源与经典药物治疗,代表关键词包括链脲佐菌素、替莫唑胺、依维莫司、舒尼替尼等。第二类可分为研究时段中期(2016~2020年),pNET领域研究热点转向细胞周期与环状RNA,该趋势与此前共被引文献的分析结果一致(图5(a)图5(b))。已有研究提示循环肿瘤细胞(CTCs)的存在可能与pNET更高的肿瘤分级、肿瘤负荷、循环CgA浓度及Ki-67指数相关[18] [19]。微小RNA (miRNAs)作为一类调控癌症基因表达的非编码RNA,其血清miR-193b与血浆miR-21水平在pNET患者中显著上调[20] [21],然而其在pNET疾病发生发展中的具体机制仍有待阐明,亦需进一步建立标准化检测体系或开发诊断试剂盒[19]。第三类为近年来(2021~2024年)的研究方向,pNET领域研究研究重点从肿瘤生物学与治疗策略转向诊断与预后评估,高频关键词包括深度学习、人工智能及促炎因子等。

近十年来,人工智能尤其是深度学习在pNET疾病研究与管理中取得显著进展,主要体现在影像分析、预测建模及基因数据挖掘等方面,以提升诊断与预后评估的准确性。例如,基于MRI与CT影像的深度学习算法可识别与肿瘤分级、血管生成及转移潜能相关的影像特征。Luo等开发了一种卷积神经网络模型,用于术前基于增强CT图像预测pNET的病理分级[22],该模型尤其在动脉期影像中表现稳健(AUC = 0.81),优于传统机器学习模型及放射科医师评估。Si等提出一种端到端深度学习模型,涵盖影像筛选、胰腺定位、分割与肿瘤诊断,在独立测试集中准确率达82.7% [23],尽管训练集中pNET病例有限,模型仍表现出识别包括pNET在内的多种胰腺肿瘤的能力。

此外,Masatoshi等利用随机生存森林模型预测pNET切除术后复发风险[24],该模型的Harrell’s C指数为0.841,识别出Ki-67指数、肿瘤大小与淋巴结转移为关键预测因子。Jacques等则基于RNA测序数据构建机器学习模型,用于预测pNET的转移潜能[25],模型筛选出的8基因组合(如AURKA、CDCA8)在转移预测中表现出高灵敏度(87.5%~93.8%)与特异性(78.1%~96.9%)。

然而,当前AI应用仍存在若干局限。模型性能高度依赖于训练数据的质量与多样性,数据集中患者群体的代表性不足可能导致预测偏差,影响其准确性与泛化能力。当前研究热点包括开发能够整合多模态影像数据与生物标志物的更复杂AI模型,以提高预测精度;同时,基于影像组学的pNET特征提取与预后预测也日益受到关注[26]-[29]。未来需进一步解决数据偏差、提升算法可解释性并确保符合监管要求,以推动AI在该领域的深入应用。

“炎症”及相关关键词的出现频次显著,凸显了肿瘤微环境在pNET进展中的重要作用。既往研究表明,pNET是一种高血管生成性肿瘤,血管内皮生长因子(VEGF)家族及其受体呈高表达[30]。与非功能性pNET相比,功能性pNET中IL-6、IL-8及其受体水平更高[31]-[33]。IL-8的过表达可能通过促进血管生成增强肿瘤细胞的增殖、迁移与侵袭能力[34]。由于对IL-6的反应,C反应蛋白的血清水平似可作为pNET患者总生存期的预测指标[35]。这些关键词的突现可能标志着炎症与pNET发展相互关系的研究进入活跃阶段,亦可能为新的治疗靶点探索提供方向。

综上所述,本文通过文献计量分析系统描绘了pNET领域的研究图景,识别出主要发展趋势、重要机构与学者,并指出未来需进一步深入的研究方向。随着pNET发病率的持续上升,此类综合分析将为未来研究规划与患者治疗改善提供重要参考。

致 谢

本研究及论文的完成,得益于多方面的支持与帮助,感谢所有为本研究提供过帮助的人士,谨此致以诚挚谢意。

NOTES

*通讯作者。

参考文献

[1] Kamisawa, T., Wood, L.D., Itoi, T. and Takaori, K. (2016) Pancreatic Cancer. The Lancet (London, England), 388, 73-85. [Google Scholar] [CrossRef] [PubMed]
[2] Roth, G.A., Abate, D., Abate, K.H., Abay, S.M., Abbafati, C., Abbasi, N., et al. (2018) Global, Regional, and National Age-Sex-Specific Mortality for 282 Causes of Death in 195 Countries and Territories, 1980-2017: A Systematic Analysis for the Global Burden of Disease Study 2017. The Lancet, 392, 1736-1788. [Google Scholar] [CrossRef] [PubMed]
[3] Rindi, G., Mete, O., Uccella, S., Basturk, O., La Rosa, S., Brosens, L.A.A., et al. (2022) Overview of the 2022 WHO Classification of Neuroendocrine Neoplasms. Endocrine Pathology, 33, 115-154. [Google Scholar] [CrossRef] [PubMed]
[4] Hallet, J., Law, C.H.L., Cukier, M., Saskin, R., Liu, N. and Singh, S. (2014) Exploring the Rising Incidence of Neuroendocrine Tumors: A Population‐Based Analysis of Epidemiology, Metastatic Presentation, and Outcomes. Cancer, 121, 589-597. [Google Scholar] [CrossRef] [PubMed]
[5] Yadav, S., Sharma, P. and Zakalik, D. (2018) Comparison of Demographics, Tumor Characteristics, and Survival between Pancreatic Adenocarcinomas and Pancreatic Neuroendocrine Tumors: A Population-Based Study. American Journal of Clinical Oncology, 41, 485-491. [Google Scholar] [CrossRef] [PubMed]
[6] O’Grady, H.L. and Conlon, K.C. (2008) Pancreatic Neuroendocrine Tumours. European Journal of Surgical Oncology (EJSO), 34, 324-332. [Google Scholar] [CrossRef] [PubMed]
[7] Kimura, T., Miyamoto, H., Fukuya, A., Kitamura, S., Okamoto, K., Kimura, M., et al. (2016) Neuroendocrine Carcinoma of the Pancreas with Similar Genetic Alterations to Invasive Ductal Adenocarcinoma. Clinical Journal of Gastroenterology, 9, 261-265. [Google Scholar] [CrossRef] [PubMed]
[8] Raman, S.P., Hruban, R.H., Cameron, J.L., Wolfgang, C.L. and Fishman, E.K. (2012) Pancreatic Imaging Mimics: Part 2, Pancreatic Neuroendocrine Tumors and Their Mimics. American Journal of Roentgenology, 199, 309-318. [Google Scholar] [CrossRef] [PubMed]
[9] Hicks, D., Wouters, P., Waltman, L., de Rijcke, S. and Rafols, I. (2015) Bibliometrics: The Leiden Manifesto for Research Metrics. Nature, 520, 429-431. [Google Scholar] [CrossRef] [PubMed]
[10] Crinò, S.F., Napoleon, B., Facciorusso, A., Lakhtakia, S., Borbath, I., Caillol, F., et al. (2023) Endoscopic Ultrasound-Guided Radiofrequency Ablation versus Surgical Resection for Treatment of Pancreatic Insulinoma. Clinical Gastroenterology and Hepatology, 21, 2834-2843.e2. [Google Scholar] [CrossRef] [PubMed]
[11] Santucci, N., Gaujoux, S., Binquet, C., Reichling, C., Lifante, J., Carnaille, B., et al. (2021) Pancreatoduodenectomy for Neuroendocrine Tumors in Patients with Multiple Endocrine Neoplasia Type 1: An AFCE (Association Francophone De Chirurgie Endocrinienne) and GTE (Groupe D’étude Des Tumeurs Endocrines) Study. World Journal of Surgery, 45, 1794-1802. [Google Scholar] [CrossRef] [PubMed]
[12] van Beek, D., Nell, S., Pieterman, C.R.C., de Herder, W.W., van de Ven, A.C., Dekkers, O.M., et al. (2019) Prognostic Factors and Survival in MEN1 Patients with Gastrinomas: Results from the DutchMEN Study Group (DMSG). Journal of Surgical Oncology, 120, 966-975. [Google Scholar] [CrossRef] [PubMed]
[13] Faggiano, A., Modica, R., Lo Calzo, F., Camera, L., Napolitano, V., Altieri, B., et al. (2019) Lanreotide Therapy vs Active Surveillance in MEN1-Related Pancreatic Neuroendocrine Tumors < 2 Centimeters. The Journal of Clinical Endocrinology & Metabolism, 105, 78-84. [Google Scholar] [CrossRef] [PubMed]
[14] Jin, X., Spampatti, M.P., Spitzweg, C. and Auernhammer, C.J. (2018) Supportive Therapy in Gastroenteropancreatic Neuroendocrine Tumors: Often Forgotten but Important. Reviews in Endocrine and Metabolic Disorders, 19, 145-158. [Google Scholar] [CrossRef] [PubMed]
[15] Brugel, M., Walter, T., Goichot, B., Smith, D., Lepage, C., Cao, C.D., et al. (2021) Efficacy of Treatments for Vipoma: A GTE Multicentric Series. Pancreatology, 21, 1531-1539. [Google Scholar] [CrossRef] [PubMed]
[16] Von Hoff, D.D., Ervin, T., Arena, F.P., Chiorean, E.G., Infante, J., Moore, M., et al. (2013) Increased Survival in Pancreatic Cancer with Nab-Paclitaxel Plus Gemcitabine. New England Journal of Medicine, 369, 1691-1703. [Google Scholar] [CrossRef] [PubMed]
[17] Lindeman, P. and Holmquist, J. (1987) Mastoid Volume and Eustachian Tube Function in Ears with Cholesteatoma. The American Journal of Otology, 8, 5-7.
[18] Khan, M.S., Kirkwood, A., Tsigani, T., Garcia-Hernandez, J., Hartley, J.A., Caplin, M.E., et al. (2013) Circulating Tumor Cells as Prognostic Markers in Neuroendocrine Tumors. Journal of Clinical Oncology, 31, 365-372. [Google Scholar] [CrossRef] [PubMed]
[19] Takahashi, D., Kojima, M., Suzuki, T., Sugimoto, M., Kobayashi, S., Takahashi, S., et al. (2018) Profiling the Tumour Immune Microenvironment in Pancreatic Neuroendocrine Neoplasms with Multispectral Imaging Indicates Distinct Subpopulation Characteristics Concordant with WHO 2017 Classification. Scientific Reports, 8, Article No. 13166. [Google Scholar] [CrossRef] [PubMed]
[20] Hussen, B.M., Hidayat, H.J., Salihi, A., Sabir, D.K., Taheri, M. and Ghafouri-Fard, S. (2021) MicroRNA: A Signature for Cancer Progression. Biomedicine & Pharmacotherapy, 138, Article ID: 111528. [Google Scholar] [CrossRef] [PubMed]
[21] Thorns, C., Schurmann, C., Gebauer, N., et al (2014) Global microRNA Profiling of Pancreatic Neuroendocrine Neoplasias. Anticancer Research, 34, 2249-2254.
[22] Luo, Y., Chen, X., Chen, J., Song, C., Shen, J., Xiao, H., et al. (2019) Preoperative Prediction of Pancreatic Neuroendocrine Neoplasms Grading Based on Enhanced Computed Tomography Imaging: Validation of Deep Learning with a Convolutional Neural Network. Neuroendocrinology, 110, 338-350. [Google Scholar] [CrossRef] [PubMed]
[23] Si, K., Xue, Y., Yu, X., Zhu, X., Li, Q., Gong, W., et al. (2021) Fully End-to-End Deep-Learning-Based Diagnosis of Pancreatic Tumors. Theranostics, 11, 1982-1990. [Google Scholar] [CrossRef] [PubMed]
[24] Murakami, M., Fujimori, N., Nakata, K., Nakamura, M., Hashimoto, S., Kurahara, H., et al. (2023) Machine Learning-Based Model for Prediction and Feature Analysis of Recurrence in Pancreatic Neuroendocrine Tumors G1/G2. Journal of Gastroenterology, 58, 586-597. [Google Scholar] [CrossRef] [PubMed]
[25] Greenberg, J.A., Shah, Y., Ivanov, N.A., Marshall, T., Kulm, S., Williams, J., et al. (2024) Developing a Predictive Model for Metastatic Potential in Pancreatic Neuroendocrine Tumor. The Journal of Clinical Endocrinology & Metabolism, 110, 263-274. [Google Scholar] [CrossRef] [PubMed]
[26] Ye, J., Fang, P., Peng, Z., Huang, X., Xie, J. and Yin, X. (2023) A Radiomics-Based Interpretable Model to Predict the Pathological Grade of Pancreatic Neuroendocrine Tumors. European Radiology, 34, 1994-2005. [Google Scholar] [CrossRef] [PubMed]
[27] Gu, W., Chen, Y., Zhu, H., Chen, H., Yang, Z., Mo, S., et al. (2023) Development and Validation of CT-Based Radiomics Deep Learning Signatures to Predict Lymph Node Metastasis in Non-Functional Pancreatic Neuroendocrine Tumors: A Multicohort Study. eClinicalMedicine, 65, Article ID: 102269. [Google Scholar] [CrossRef] [PubMed]
[28] Ma, M., Gu, W., Liang, Y., Han, X., Zhang, M., Xu, M., et al. (2024) A Novel Model for Predicting Postoperative Liver Metastasis in R0 Resected Pancreatic Neuroendocrine Tumors: Integrating Computational Pathology and Deep Learning-Radiomics. Journal of Translational Medicine, 22, Article No. 768. [Google Scholar] [CrossRef] [PubMed]
[29] Wang, X., Qiu, J., Tan, C., Chen, Y., Tan, Q., Ren, S., et al. (2022) Development and Validation of a Novel Radiomics-Based Nomogram with Machine Learning to Preoperatively Predict Histologic Grade in Pancreatic Neuroendocrine Tumors. Frontiers in Oncology, 12, Article ID: 843376. [Google Scholar] [CrossRef] [PubMed]
[30] Teulé, A. and Casanovas, O. (2012) Relevance of Angiogenesis in Neuroendocrine Tumors. Targeted Oncology, 7, 93-98. [Google Scholar] [CrossRef] [PubMed]
[31] Jiménez-Fonseca, P., Martín, M.N., Carmona-Bayonas, A., Calvo, A., Fernández-Mateos, J., Redrado, M., et al. (2018) Biomarkers and Polymorphisms in Pancreatic Neuroendocrine Tumors Treated with Sunitinib. Oncotarget, 9, 36894-36905. [Google Scholar] [CrossRef] [PubMed]
[32] Berković, M.C., Jokić, M., Marout, J., Radošević, S., Zjačić-Rotkvić, V. and Kapitanović, S. (2007) IL-6-174 C/G Polymorphism in the Gastroenteropancreatic Neuroendocrine Tumors (GEP-NETs). Experimental and Molecular Pathology, 83, 474-479. [Google Scholar] [CrossRef] [PubMed]
[33] Hussain, F., Wang, J., Ahmed, R., Guest, S.K., Lam, E.W., Stamp, G., et al. (2010) The Expression of IL-8 and IL-8 Receptors in Pancreatic Adenocarcinomas and Pancreatic Neuroendocrine Tumours. Cytokine, 49, 134-140. [Google Scholar] [CrossRef] [PubMed]
[34] Zurita, A.J., Khajavi, M., Wu, H., Tye, L., Huang, X., Kulke, M.H., et al. (2015) Circulating Cytokines and Monocyte Subpopulations as Biomarkers of Outcome and Biological Activity in Sunitinib-Treated Patients with Advanced Neuroendocrine Tumours. British Journal of Cancer, 112, 1199-1205. [Google Scholar] [CrossRef] [PubMed]
[35] Karakaxas, D., Sioziou, A., Aravantinos, G., Coker, A., Papanikolaou, I.S., Liakakos, T., et al. (2016) Genetic Polymorphisms of Interleukin 1β Gene and Sporadic Pancreatic Neuroendocrine Tumors Susceptibility. World Journal of Gastrointestinal Oncology, 8, 520-525. [Google Scholar] [CrossRef] [PubMed]