Artificial Intelligence-Assisted EUS for Risk Stratification of Pancreatic Cystic Lesions: A Narrative Review of Current Evidence and Future Directions for Predicting High-Grade Dysplasia, Invasive Cancer, and the Need for Surgical Referral
Downloads
DOI:
https://doi.org/10.71079/ASIDE.GI.082826830Abstract
Background: Pancreatic cystic lesions are increasingly detected on cross-sectional imaging, yet accurate risk stratification remains challenging. A clinically important minority, particularly intraductal papillary mucinous neoplasms and mucinous cystic neoplasms, may progress to high-grade dysplasia or invasive carcinoma. EUS plays a central role in cyst evaluation, but interpretation remains operator-dependent, and guideline-based risk categories have imperfect predictive accuracy.
Methods: This narrative review was conducted using a structured literature search of PubMed, Scopus, Web of Science, and Embase with terms including artificial intelligence, deep learning, machine learning, endoscopic ultrasound, pancreatic cystic lesions, intraductal papillary mucinous neoplasm, high-grade dysplasia, and pancreatic cancer. Studies reporting AI applications in EUS image interpretation, multimodal risk prediction, radiomics, and cyst-fluid or molecular marker integration were included. A qualitative synthesis was performed given the heterogeneity of study designs and AI methodologies.
Results: AI may enhance EUS-based assessment by extracting quantitative imaging features and integrating EUS data with CT, MRI, cyst-fluid biomarkers, cytology, molecular markers, and longitudinal cyst behavior. The most clinically meaningful goal — though not yet established — is individualized prediction of high-grade dysplasia and invasive cancer to support surgical referral decisions, particularly where guideline-based criteria are discordant or borderline. Current models remain preliminary and require prospective validation. Retrospective designs, small datasets, lack of external validation, and uncertainty regarding explainability and clinical integration limit evidence.
Conclusions: Future prospective multicentre studies should determine whether AI-assisted EUS improves patient-centered outcomes by reducing unnecessary surgery while preventing delayed diagnosis of advanced neoplasia.
Keywords:
Pancreatic cancer, High-grade dysplasia, Pancreatic cystic lesions, Endoscopic ultrasound, Artificial intelligence, Intraductal papillary mucinous neoplasmKey finding
Future prospective multicentre studies should determine whether AI-assisted EUS improves patient-centered outcomes by reducing unnecessary surgery while preventing delayed diagnosis of advanced neoplasia.
From the authors' abstract.
中文摘要
人工智能辅助内镜超声在胰腺囊性病变风险分层中的应用：对预测高级别异型增生、侵袭性癌症及手术转诊需求的现有证据与未来方向的叙述性综述
背景：胰腺囊性病变在横断面影像学检查中越来越多被发现，但准确的风险分层仍然具有挑战性。临床上重要的少数病例，尤其是导管内乳头状黏液性肿瘤（IPMN）和黏液性囊性肿瘤（MCN），可能进展为高级别异型增生或侵袭性癌症。内镜超声（EUS）在囊性病变评估中起核心作用，但其解读仍受操作者影响，基于指南的风险类别预测准确性不完善。
方法：本叙述性综述采用结构化文献检索，检索数据库包括 PubMed、Scopus、Web of Science 和 Embase，检索词包括人工智能（AI）、深度学习、机器学习、内镜超声、胰腺囊性病变、导管内乳头状黏液性肿瘤、IPMN、高级别异型增生、胰腺癌等。纳入报告 AI 在 EUS 图像解读、多模态风险预测、放射组学以及囊液或分子标志物整合方面应用的研究。鉴于研究设计和 AI 方法的异质性，采用定性综合分析。
结果：AI 可通过提取定量影像特征并将 EUS 数据与 CT、MRI、囊液生物标志物、细胞学、分子标志物以及囊性病变的纵向行为整合，提升基于 EUS 的评估。最具临床意义的目标——尚未确立——是个体化预测高级别异型增生和侵袭性癌症，以支持手术转诊决策，尤其在基于指南的标准存在分歧或边界情况时。当前模型仍处于初步阶段，需要前瞻性验证。回顾性设计、数据集规模小、缺乏外部验证以及对可解释性和临床整合的不确定性限制了证据。
结论：未来的前瞻性多中心研究应确定 AI 辅助 EUS 是否通过减少不必要手术并防止晚期肿瘤诊断延误，从而改善以患者为中心的结局。
本中文摘要为机器辅助翻译，仅供参考；以英文摘要为准。 Machine-assisted Chinese translation of the English abstract; the English abstract is the version of record.
References
1. Vege SS, Ziring B, Jain R, et al. American Gastroenterological Association Institute guideline on the diagnosis and management of asymptomatic neoplastic pancreatic cysts. Gastroenterology. 2015. doi:10.1053/j.gastro.2015.01.015. PMID: 25805375. DOI: https://doi.org/10.1053/j.gastro.2015.01.015
2. European Study Group on Cystic Tumors of the Pancreas. European evidence-based guidelines on pancreatic cystic neoplasms. Gut. 2018;67(5):789-804. doi:10.1136/gutjnl-2018-316027. PMID: 29574408. DOI: https://doi.org/10.1136/gutjnl-2018-316027
3. Ohtsuka T, Fernandez-Del Castillo C, et al. International evidence-based Kyoto guidelines for the management of intraductal papillary mucinous neoplasm of the pancreas. Pancreatology. 2024;24(2):255-270. doi:10.1016/j.pan.2023.12.009. PMID: 38182527. DOI: https://doi.org/10.1016/j.pan.2023.12.009
4. Guilabert L, Nikolic S, de-Madaria E, et al. Endoscopic ultrasound for pancreatic cystic lesions: a narrative review. BMJ Open Gastroenterol. 2025. doi:10.1136/bmjgast-2025-001893. PMID: 40998473. DOI: https://doi.org/10.1136/bmjgast-2025-001893
5. Kuwahara T, Hara K, Mizuno N, et al. Usefulness of Deep Learning Analysis for the Diagnosis of Malignancy in Intraductal Papillary Mucinous Neoplasms of the Pancreas. Clin Transl Gastroenterol. 2019. doi:10.14309/ctg.0000000000000045. PMID: 31117111. DOI: https://doi.org/10.14309/ctg.0000000000000045
6. Machicado JD, Chao WL, Carlyn DE, et al. High performance in risk stratification of intraductal papillary mucinous neoplasms by confocal laser endomicroscopy image analysis with convolutional neural networks (with video). Gastrointest Endosc. 2021;94(1):78-87.e2. doi:10.1016/j.gie.2020.12.054. PMID: 33465354. DOI: https://doi.org/10.1016/j.gie.2020.12.054
7. Brugge WR, Lewandrowski K, Lee-Lewandrowski E, et al. Diagnosis of pancreatic cystic neoplasms: a report of the cooperative pancreatic cyst study. Gastroenterology. 2004. doi:10.1053/j.gastro.2004.02.013. PMID: 15131794. DOI: https://doi.org/10.1053/j.gastro.2004.02.013
8. Tanaka M, Fernandez-Del Castillo C, Kamisawa T, et al. Revisions of international consensus Fukuoka guidelines for the management of IPMN of the pancreas. Pancreatology. 2017;17(5):738-753. doi:10.1016/j.pan.2017.07.007. PMID: 28735806. DOI: https://doi.org/10.1016/j.pan.2017.07.007
9. McCarty TR, Garg R, Rustagi T. Pancreatic cyst fluid glucose in differentiating mucinous from nonmucinous pancreatic cysts: a systematic review and meta-analysis. Gastrointest Endosc. 2021;94(4):698-712.e6. doi:10.1016/j.gie.2021.04.025. PMID: 33964311. DOI: https://doi.org/10.1016/j.gie.2021.04.025
10. Carr RA, Yip-Schneider MT, Simpson RE, et al. Pancreatic cyst fluid glucose: rapid, inexpensive, and accurate diagnosis of mucinous pancreatic cysts. Surgery. 2018;163(3):600-605. doi:10.1016/j.surg.2017.09.051. PMID: 29241991. DOI: https://doi.org/10.1016/j.surg.2017.09.051
11. Singhi AD, McGrath K, Brand RE, et al. Preoperative next-generation sequencing of pancreatic cyst fluid is highly accurate in cyst classification and detection of advanced neoplasia. Gut. 2018;67(12):2131-2141. doi:10.1136/gutjnl-2016-313586. PMID: 28970292. PMCID: PMC6241612. DOI: https://doi.org/10.1136/gutjnl-2016-313586
12. Pfluger MJ, Jamouss KT, Afghani E, et al. Predictive ability of pancreatic cyst fluid biomarkers: A systematic review and meta-analysis. Pancreatology. 2023;23(7):868-877. doi:10.1016/j.pan.2023.05.005. PMID: 37230894. DOI: https://doi.org/10.1016/j.pan.2023.05.005
13. Springer S, Wang Y, Dal Molin M, et al. A combination of molecular markers and clinical features improves the classification of pancreatic cysts. Gastroenterology. 2015;149(6):1501-10. doi:10.1053/j.gastro.2015.07.041. PMID: 26253305. PMCID: PMC4782782. DOI: https://doi.org/10.1053/j.gastro.2015.07.041
14. Kurita Y, Kuwahara T, Hara K, et al. Diagnostic ability of artificial intelligence using deep learning analysis of cyst fluid in differentiating malignant from benign pancreatic cystic lesions. Sci Rep. 2019. doi:10.1038/s41598-019-43314-3. PMID: 31053726. DOI: https://doi.org/10.1038/s41598-019-43314-3
15. Lee TC, Angelina CL, Kongkam P, et al. Deep-Learning-Enabled Computer-Aided Diagnosis in the Classification of Pancreatic Cystic Lesions on Confocal Laser Endomicroscopy. Diagnostics (Basel). 2023;13(7):1289. doi:10.3390/diagnostics13071289. PMID: 37046507. PMCID: PMC10093377. DOI: https://doi.org/10.3390/diagnostics13071289
16. Nakai Y, Isayama H, Shinoura S, et al. Confocal laser endomicroscopy in gastrointestinal and pancreatobiliary diseases. Dig Endosc. 2014;26 Suppl 1:86-94. doi:10.1111/den.12152. PMID: 24033351. DOI: https://doi.org/10.1111/den.12152
17. Wu CCH, Lim SJM, Tan DMY. Endoscopic ultrasound-guided needle-based confocal laser endomicroscopy for pancreatic cystic lesions: current status and prospects. Clin Endosc. 2024;57(4):434-445. doi:10.5946/ce.2023.157. PMID: 38978396. PMCID: PMC11294861. DOI: https://doi.org/10.5946/ce.2023.157
18. Rangwani S, Ardeshna DR, Rodgers B, et al. Application of Artificial Intelligence in the Management of Pancreatic Cystic Lesions. Biomimetics (Basel). 2022;7(2):79. doi:10.3390/biomimetics7020079. PMID: 35735595. PMCID: PMC9221027. DOI: https://doi.org/10.3390/biomimetics7020079
19. Balduzzi A, Janssen BV, De Pastena M, et al. Artificial intelligence-based models to assess the risk of malignancy on radiological imaging in patients with intraductal papillary mucinous neoplasm of the pancreas: scoping review. Br J Surg. 2023. doi:10.1093/bjs/znad201. PMID: 37402951. DOI: https://doi.org/10.1093/bjs/znad201
20. Qadir MI, Baril JA, Yip-Schneider MT, et al. Artificial intelligence in pancreatic intraductal papillary mucinous neoplasm imaging: a systematic review. PLOS Digit Health. 2025. doi:10.1371/journal.pdig.0000920. PMID: 40700385. DOI: https://doi.org/10.1101/2025.01.08.25320130
21. Nagendran M, Chen Y, Lovejoy CA, et al. Artificial intelligence versus clinicians: systematic review of design, reporting standards, and claims of deep learning studies. BMJ. 2020. doi:10.1136/bmj.m689. PMID: 32213531. DOI: https://doi.org/10.1136/bmj.m689
22. Correa-Gallego C, Do R, Lafemina J, et al. Predicting dysplasia and invasive carcinoma in intraductal papillary mucinous neoplasms of the pancreas: development of a preoperative nomogram. Ann Surg Oncol. 2013;20(13):4348-55. doi:10.1245/s10434-013-3207-z. PMID: 24046103. DOI: https://doi.org/10.1245/s10434-013-3207-z
23. Li B, Shi X, Gao S, et al. Nomogram for the Prediction of High-Grade Dysplasia and Invasive Carcinoma in Patients With Intraductal Papillary Mucinous Neoplasms of the Pancreas Based on Variables of Noninvasive Examination. Front Oncol. 2021. doi:10.3389/fonc.2021.609187. PMID: 33767983. DOI: https://doi.org/10.3389/fonc.2021.609187
24. Pergolini I, Sahora K, Ferrone CR, et al. Long-term risk of pancreatic malignancy in patients with branch-duct intraductal papillary mucinous neoplasm in a referral center. Gastroenterology. 2017;153(5):1284-1294. doi:10.1053/j.gastro.2017.07.019. PMID: 28739282. DOI: https://doi.org/10.1053/j.gastro.2017.07.019
25. Kang JS, Lee C, Song W, et al. Risk prediction for malignant intraductal papillary mucinous neoplasm of the pancreas: logistic regression versus machine learning. Sci Rep. 2020. doi:10.1038/s41598-020-76974-7. PMID: 33208887. DOI: https://doi.org/10.1038/s41598-020-76974-7
26. Lennon AM, Wolfgang CL, Canto MI, et al. The early detection of pancreatic cancer: what will it take to diagnose and treat curable pancreatic neoplasia? Cancer Res. 2014;74(13):3381-9. doi:10.1158/0008-5472.CAN-14-0734. PMID: 24924775. PMCID: PMC4085574. DOI: https://doi.org/10.1158/0008-5472.CAN-14-0734
27. He X, Fan R, Sun J, et al. A model for predicting degree of malignancy in patients with intraductal papillary mucinous neoplasm. Front Oncol. 2023. doi:10.3389/fonc.2023.1087852. PMID: 36761937. DOI: https://doi.org/10.3389/fonc.2023.1087852
28. Lavista Ferres JM, Oviedo F, Robinson C, et al. Performance of explainable artificial intelligence in guiding the management of patients with a pancreatic cyst. Pancreatology. 2024;24(7):1182-1191. doi:10.1016/j.pan.2024.09.001. PMID: 39261223. DOI: https://doi.org/10.1016/j.pan.2024.09.001
29. Hanania AN, Bantis LE, Feng Z, et al. Quantitative imaging to evaluate malignant potential of IPMNs. Oncotarget. 2016. doi:10.18632/oncotarget.11769. PMID: 27588410. DOI: https://doi.org/10.18632/oncotarget.11769
30. Permuth JB, Choi J, Balarunathan Y, et al. Combining radiomic features with a miRNA classifier may improve prediction of malignant pathology for pancreatic intraductal papillary mucinous neoplasms. Oncotarget. 2016. doi:10.18632/oncotarget.11768. PMID: 27589689. DOI: https://doi.org/10.18632/oncotarget.11768
31. Chakraborty J, Midya A, Gazit L, et al. CT radiomics to predict high-risk intraductal papillary mucinous neoplasms of the pancreas. Med Phys. 2018;45(11):5019-5029. doi:10.1002/mp.13159. PMID: 30176047. PMCID: PMC8050835. DOI: https://doi.org/10.1002/mp.13159
32. Cui S, Tang T, Su Q, et al. Radiomic nomogram based on MRI to predict grade of branching type intraductal papillary mucinous neoplasms of the pancreas: a multicenter study. Cancer Imaging. 2021. doi:10.1186/s40644-021-00395-6. PMID: 33750453. DOI: https://doi.org/10.1186/s40644-021-00395-6
33. Flammia F, Innocenti T, Galluzzo A, et al. Branch duct-intraductal papillary mucinous neoplasms (BD-IPMNs): an MRI-based radiomic model to determine the malignant degeneration potential. Radiol Med. 2023;128(4):383-392. doi:10.1007/s11547-023-01609-6. PMID: 36826452. DOI: https://doi.org/10.1007/s11547-023-01609-6
34. Lou F, Li M, Chu T, et al. Comprehensive analysis of clinical data and radiomic features from contrast-enhanced CT for differentiating benign and malignant pancreatic intraductal papillary mucinous neoplasms. Sci Rep. 2024. doi:10.1038/s41598-024-68067-6. PMID: 39060387. DOI: https://doi.org/10.1038/s41598-024-68067-6
35. Liu X, Faes L, Kale AU, et al. A comparison of deep learning performance against health-care professionals in detecting diseases from medical imaging: a systematic review and meta-analysis. Lancet Digit Health. 2019;1(6):e271-e297. doi:10.1016/S2589-7500(19)30123-2. PMID: 33323251. DOI: https://doi.org/10.1016/S2589-7500(19)30123-2
36. Collins GS, Moons KGM, Dhiman P, et al. TRIPOD+AI statement: updated guidance for reporting clinical prediction models that use regression or machine learning methods. BMJ. 2024. doi:10.1136/bmj-2023-078378. PMID: 38626948. DOI: https://doi.org/10.1136/bmj-2023-078378
37. Kelly CJ, Karthikesalingam A, Suleyman M, et al. Key challenges for delivering clinical impact with artificial intelligence. BMC Med. 2019. doi:10.1186/s12916-019-1426-2. PMID: 31665002. DOI: https://doi.org/10.1186/s12916-019-1426-2
38. Vasey B, Nagendran M, Campbell B, et al. Reporting guideline for the early stage clinical evaluation of decision support systems driven by artificial intelligence: DECIDE-AI. BMJ. 2022. doi:10.1136/bmj-2022-070904. PMID: 35584845. DOI: https://doi.org/10.1136/bmj-2022-070904
39. Wiens J, Saria S, Sendak M, et al. Do no harm: a roadmap for responsible machine learning for health care. Nat Med. 2019;25(9):1337-1340. doi:10.1038/s41591-019-0548-6. PMID: 31427808. DOI: https://doi.org/10.1038/s41591-019-0548-6
Data Availability Statement
No new datasets were generated or analysed for this review article. All information discussed is derived from previously published studies and publicly available literature.
License
Copyright (c) 2026 Ahmed Salman
This work is licensed under a Creative Commons Attribution 4.0 International License.
Copyright and Licensing
All articles published in ASIDE Gastroenterology are open access and freely available online immediately upon publication, without embargo.
This journal applies the terms of the Creative Commons Attribution 4.0 International License (CC BY 4.0). Under this license, anyone may copy, redistribute, remix, transform, and build upon the material for any purpose, even commercially, provided that proper credit is given to the original author(s), a link to the license is provided, and any changes made are indicated.
-
License link: https://creativecommons.org/licenses/by/4.0/
-
Machine-readable license metadata is embedded in each article and its DOI record.
Copyright Holder
Copyright in all articles remains with the author(s). ASIDE Gastroenterology is published and owned by PubPorta Publishing LLC. By submitting a manuscript, authors agree to grant the publisher a non-exclusive license to publish, distribute, archive, and identify itself as the original publisher of the work under the terms of the CC BY 4.0 license.
Academic oversight and scholarly guidance are provided by the American Society for Inclusion, Diversity, and Equity in Healthcare (ASIDE). Copyright and licensing arrangements are administered by the publisher.
Third-party Material
Any material (e.g., images, figures, or tables) not covered by CC BY 4.0 will be clearly indicated in the article. Users must obtain permission directly from the copyright holder for reuse of such third-party material.
Author Rights and Self-Archiving
Authors are permitted to deposit all versions of their work (preprint, author’s accepted manuscript, and version of record) in institutional or subject repositories of their choice immediately upon publication, without embargo, provided that the DOI and license information are included.
Downloads
Published
Issue
Section
How to Cite
Article history
- Received
- 7 May 2026
- Received in revised form
- 20 Jun 2026
- Accepted
- 17 Jul 2026
- Published
- 28 Aug 2026
