ClinicalTrials.gg
RecruitingNCT07543263Updated Nov 5, 2026

An Artificial Intelligence System for Multimodal, Multi-class Diagnosis of Pancreatic Cystic Lesions Based on Endoscopic Ultrasonography

An observational study in Pancreatic Cystic Lesion (PCL), sponsored by Qilu Hospital of Shandong University. Recruiting at 1 site in China. Open to participants aged 18 Years and older. Per ClinicalTrials.gov, last updated 2026-11-05.

Sponsored by Qilu Hospital of Shandong University · Observational

How we know

From the registry’s dates

  • Started Apr 2026; still recruiting 7 months later.

Help build ClinicalTrials.gg — short surveys, remote interviews or testing, in your language. Take part →

Study type
Observational
Model
Cohort
Time perspective
Prospective
Enrollment
176
Ages
18 Years and older
Sex
All
01

Study summary

The aim of this study is to develop and validate an artificial intelligence system named iEUS-PCL (intelligent endoscopic ultrasound system-pancreatic cystic lesions) for detecting and multimodal, multi-class diagnosing pancreatic cystic lesions (PCL) during endoscopic ultrasound (EUS) examination.

Read the detailed description

This multicenter, prospective cohort study aims to develop and validate a multimodal artificial intelligence system named iEUS-PCL for the detection and differential diagnosis of PCL. The model was developed based on retrospectively collected EUS images, EUS features, clinical data and radiological imaging features of patients who underwent EUS examination. The diagnostic performance of iEUS-PCL will be evaluated prospectively in real-time EUS videos and compared with endosonographers' performance.

02

Conditions studied

  • Pancreatic Cystic Lesion (PCL)

Keywords

  • endoscopic ultrasound
  • pancreatic cystic lesion
  • machine learning
03

In context

Lead sponsor

Qilu Hospital of Shandong University is the lead sponsor of 311 studies on the registry; 188 are open to participants now.

Counted across the registry records on this site, refreshed daily.

04

Who can participate

Ages eligible
18 Years and older
Sexes eligible
All
Accepts healthy volunteers
No
Sampling method
Non-probability sample

Study population

Adult patients with suspected pancreatic cystic lesions undergoing EUS.

Go through the criteria one by one — yes, no or not sure — and take the list to your doctor or the study team. Kept in this browser only.

Inclusion criteria

  1. Patients aged ≥18 years scheduled for EUS with suspected pancreatic cystic lesions based on clinical symptoms, medical history, laboratory tests or radiological examinations, and who agree to participate in the research and voluntarily sign the .
  2. Patients with no prior history of treatment for pancreatic lesions.

Exclusion criteria

Exclusion Criteria:

  1. Patients with absolute to EUS examination.
  2. Pregnancy or lactating.
  3. Uncorrectable coagulopathy (>50 seconds or INR>1.5) and/or uncorrectable thrombocytopenia( count\<50×109/L).
  4. Upper gastrointestinal obstruction.
  5. Patients who underwent surgical treatment or anatomical alterations of the pancreas due to lesions in other thoracic and/or abdominal organs, as well as patients with congenital anatomical abnormalities.
  6. Patients who have undergone biliary/pancreatic duct stent placement.
  7. Patients who refuse to sign the .
Terms in these criteria, in plain language(4)

Underlined terms in the criteria open these too. Explained by clinicaltrials.gg, not part of the registry record. The study team decides who can take part.

Informed consent

Before you join, the study team explains what taking part involves — its purpose, what happens, the risks and possible benefits — and answers your questions, so you can decide freely. Consent is usually recorded on a form (the informed consent form, ICF) signed by you or, where the law allows, by someone legally authorized to decide for you.

You can keep asking questions during the study, you are told of new information that matters, and you can choose to leave at any time.

Contraindication

A reason a treatment, test or procedure should not be given to a particular person, such as an allergy, another illness or a medicine they take.

INR, PT and aPTT (clotting tests)

Blood tests of how long blood takes to clot. The INR is the prothrombin time (PT) put on a common scale; about 1 is usual for someone not taking a blood thinner.

Criteria often make an exception for people on a blood thinner such as warfarin, whose INR is raised on purpose.

Platelets

Blood cells that help blood clot. Too few raises the risk of bleeding and bruising. A usual adult range is about 150–400 × 10⁹/L (150,000–400,000 per µL); each lab has its own reference range.

05

Study design

Observational model
Cohort
Time perspective
Prospective
Enrollment
176 participants (estimated)
Patient registry
No
Biospecimen retention
Samples without dna

Groups and cohorts

  • Patients undergoing EUS

    Patients aged ≥18 years scheduled for EUS with suspected pancreatic cystic lesions based on clinical symptoms, medical history, laboratory tests or radiological examinations are eligible upon agreement to participate in the research and voluntary signing of the informed consent.

    Device: iEUS-PCL(intelligent endoscopic ultrasound system- pancreatic cystic lesion)

Interventions

  • DeviceiEUS-PCL(intelligent endoscopic ultrasound system- pancreatic cystic lesion)

    The iEUS-PCL will automatically detect pancreatic cystic lesions and integrate the patients' EUS images, EUS features, clinical data and radiological imaging features to perform three classification tasks: 1. binary classification: benign/malignant lesions; 2. binary classification: mucinous/non-mucinous lesions; 3. four-category classification: intraductal papillary mucinous neoplasm/ mucinous cystic neoplasm/ serous cyst neoplasm/ pancreatic cyst.

06

What researchers measure

Primary outcomes

  1. The accuracy of iEUS-PCL for pancreatic cystic lesions

    The primary outcome of the study is to evaluate the accuracy of the iEUS-PCL in identifying the pancreatic cystic lesions (benign/malignant; mucinous/non-mucinous; 4-category).

    Time frame: During procedure

  2. The sensitivity of iEUS-PCL for pancreatic cystic lesions

    The primary outcome of the study is to evaluate the sensitivity of the iEUS-PCL in identifying the pancreatic cystic lesions (benign/malignant; mucinous/non-mucinous; 4-category).

    Time frame: During procedure

  3. The specificicy of iEUS-PCL for pancreatic cystic lesions

    The primary outcome of the study is to evaluate the specificity of the iEUS-PCL in identifying the pancreatic cystic lesions (benign/malignant; mucinous/non-mucinous; 4-category).

    Time frame: During procedure

  4. The postive predictive value of iEUS-PCL for pancreatic cystic lesions

    The primary outcome of the study is to evaluate the postive predictive value of the iEUS-PCL in identifying the pancreatic cystic lesions (benign/malignant; mucinous/non-mucinous; 4-category).

    Time frame: During procedure

  5. The negative predictive value of iEUS-PCL for pancreatic cystic lesions

    The primary outcome of the study is to evaluate the negative predictive value of the iEUS-PCL in identifying the pancreatic cystic lesions (benign/malignant; mucinous/non-mucinous; 4-category).

    Time frame: During procedure

Secondary outcomes

  1. Comparison of the accuracy between iEUS-PCL and endosonographers

    The secondary outcome of the study is to comparing the accuracy between iEUS-PCL and different-level endosonographers in identifying the pancreatic cystic lesions (benign/malignant; mucinous/non-mucinous; 4-category).

    Time frame: During procedure

  2. Comparison of the sensitivity between iEUS-PCL and endosonographers

    The secondary outcome of the study is to comparing the sensitivity between iEUS-PCL and different-level endosonographers in identifying in identifying the pancreatic cystic lesions (benign/malignant; mucinous/non-mucinous; 4-category).

    Time frame: During procedure

  3. Comparison of the specificity between iEUS-PCL and endosonographers

    The secondary outcome of the study is to comparing the specificity between iEUS-PCL and different-level endosonographers in identifying in identifying the pancreatic cystic lesions (benign/malignant; mucinous/non-mucinous; 4-category).

    Time frame: During procedure

  4. Comparison of the postive predictive value between iEUS-PCL and endosonographers

    The secondary outcome of the study is to comparing the postive predictive value between iEUS-PCL and different level endosonographers in identifying in identifying the pancreatic cystic lesions (benign/malignant; mucinous/non-mucinous; 4-category).

    Time frame: During procedure

  5. Comparison of the negative predictive value between iEUS-PCL and endosonographers

    The secondary outcome of the study is to comparing the negative predictive value between iEUS-PCL and different-level endosonographers in identifying in identifying the pancreatic cystic lesions (benign/malignant; mucinous/non-mucinous; 4-category).

    Time frame: During procedure

07

Study locations

1 of 1 sites recruiting
08

References and documents

Publications

  • Goyal H, Sherazi SAA, Gupta S, Perisetti A, Achebe I, Ali A, Tharian B, Thosani N, Sharma NR. Application of artificial intelligence in diagnosis of pancreatic malignancies by endoscopic ultrasound: a systemic review. Ther Adv Gastroenterol. 2022 Apr 29;15:17562848221093873. doi: 10.1177/17562848221093873. eCollection 2022. PubMed 35509425 ↗
  • Qin X, Ran T, Chen Y, Zhang Y, Wang D, Zhou C, Zou D. Artificial Intelligence in Endoscopic Ultrasonography-Guided Fine-Needle Aspiration/Biopsy (EUS-FNA/B) for Solid Pancreatic Lesions: Opportunities and Challenges. Diagnostics (Basel). 2023 Sep 26;13(19):3054. doi: 10.3390/diagnostics13193054. PubMed 37835797 ↗
  • Tian G, Xu D, He Y, Chai W, Deng Z, Cheng C, Jin X, Wei G, Zhao Q, Jiang T. Deep learning for real-time auxiliary diagnosis of pancreatic cancer in endoscopic ultrasonography. Front Oncol. 2022 Oct 7;12:973652. doi: 10.3389/fonc.2022.973652. eCollection 2022. PubMed 36276094 ↗
  • Kloth C, Haggenmuller B, Beck A, Wagner M, Kornmann M, Steinacker JP, Steinacker-Stanescu N, Vogele D, Beer M, Juchems MS, Schmidt SA. Diagnostic, Structured Classification and Therapeutic Approach in Cystic Pancreatic Lesions: Systematic Findings with Regard to the European Guidelines. Diagnostics (Basel). 2023 Jan 26;13(3):454. doi: 10.3390/diagnostics13030454. PubMed 36766560 ↗
  • Vilela A, Quingalahua E, Vargas A, Hawa F, Shannon C, Carpenter ES, Shi J, Krishna SG, Lee UJ, Chalhoub JM, Machicado JD. Global Prevalence of Pancreatic Cystic Lesions in the General Population on Magnetic Resonance Imaging: A Systematic Review and Meta-analysis. Clin Gastroenterol Hepatol. 2024 Sep;22(9):1798-1809.e6. doi: 10.1016/j.cgh.2024.02.018. Epub 2024 Feb 28. PubMed 38423346 ↗
  • Elta GH, Enestvedt BK, Sauer BG, Lennon AM. ACG Clinical Guideline: Diagnosis and Management of Pancreatic Cysts. Am J Gastroenterol. 2018 Apr;113(4):464-479. doi: 10.1038/ajg.2018.14. Epub 2018 Feb 27. PubMed 29485131 ↗
  • European Study Group on Cystic Tumours of the Pancreas. European evidence-based guidelines on pancreatic cystic neoplasms. Gut. 2018 May;67(5):789-804. doi: 10.1136/gutjnl-2018-316027. Epub 2018 Mar 24. PubMed 29574408 ↗
  • Rangwani S, Ardeshna DR, Rodgers B, Melnychuk J, Turner R, Culp S, Chao WL, Krishna SG. Application of Artificial Intelligence in the Management of Pancreatic Cystic Lesions. Biomimetics (Basel). 2022 Jun 14;7(2):79. doi: 10.3390/biomimetics7020079. PubMed 35735595 ↗
  • Oh S, Kim YJ, Park YT, Kim KG. Automatic Pancreatic Cyst Lesion Segmentation on EUS Images Using a Deep-Learning Approach. Sensors (Basel). 2021 Dec 30;22(1):245. doi: 10.3390/s22010245. PubMed 35009788 ↗
  • Jiang J, Chao WL, Cao T, Culp S, Napoleon B, El-Dika S, Machicado JD, Pannala R, Mok S, Luthra AK, Akshintala VS, Muniraj T, Krishna SG. Improving Pancreatic Cyst Management: Artificial Intelligence-Powered Prediction of Advanced Neoplasms through Endoscopic Ultrasound-Guided Confocal Endomicroscopy. Biomimetics (Basel). 2023 Oct 19;8(6):496. doi: 10.3390/biomimetics8060496. PubMed 37887627 ↗
  • Hwang J, Kim YK, Min JH, Jeong WK, Hong SS, Kim HJ. Comparison between MRI with MR cholangiopancreatography and endoscopic ultrasonography for differentiating malignant from benign mucinous neoplasms of the pancreas. Eur Radiol. 2018 Jan;28(1):179-187. doi: 10.1007/s00330-017-4926-5. Epub 2017 Aug 4. PubMed 28779397 ↗
  • Huang W, Xu Y, Li Z, Li J, Chen Q, Huang Q, Wu Y, Chen H. Enhancing noninvasive pancreatic cystic neoplasm diagnosis with multimodal machine learning. Sci Rep. 2025 May 12;15(1):16398. doi: 10.1038/s41598-025-01502-4. PubMed 40355497 ↗
  • Gheorghiu MI, Seicean A, Pojoga C, Hagiu C, Seicean R, Sparchez Z. Contrast-enhanced guided endoscopic ultrasound procedures. World J Gastroenterol. 2024 May 7;30(17):2311-2320. doi: 10.3748/wjg.v30.i17.2311. PubMed 38813054 ↗
  • Vilas-Boas F, Ribeiro T, Afonso J, Cardoso H, Lopes S, Moutinho-Ribeiro P, Ferreira J, Mascarenhas-Saraiva M, Macedo G. Deep Learning for Automatic Differentiation of Mucinous versus Non-Mucinous Pancreatic Cystic Lesions: A Pilot Study. Diagnostics (Basel). 2022 Aug 24;12(9):2041. doi: 10.3390/diagnostics12092041. PubMed 36140443 ↗
  • Nguon LS, Seo K, Lim JH, Song TJ, Cho SH, Park JS, Park S. Deep Learning-Based Differentiation between Mucinous Cystic Neoplasm and Serous Cystic Neoplasm in the Pancreas Using Endoscopic Ultrasonography. Diagnostics (Basel). 2021 Jun 8;11(6):1052. doi: 10.3390/diagnostics11061052. PubMed 34201066 ↗
  • Kuwahara T, Hara K, Mizuno N, Okuno N, Matsumoto S, Obata M, Kurita Y, Koda H, Toriyama K, Onishi S, Ishihara M, Tanaka T, Tajika M, Niwa Y. Usefulness of Deep Learning Analysis for the Diagnosis of Malignancy in Intraductal Papillary Mucinous Neoplasms of the Pancreas. Clin Transl Gastroenterol. 2019 May 22;10(5):1-8. doi: 10.14309/ctg.0000000000000045. PubMed 31117111 ↗
  • Schulz D, Heilmaier M, Phillip V, Treiber M, Mayr U, Lahmer T, Mueller J, Demir IE, Friess H, Reichert M, Schmid RM, Abdelhafez M. Accurate prediction of histological grading of intraductal papillary mucinous neoplasia using deep learning. Endoscopy. 2023 May;55(5):415-422. doi: 10.1055/a-1971-1274. Epub 2022 Nov 2. PubMed 36323331 ↗
  • Lipkova J, Chen RJ, Chen B, Lu MY, Barbieri M, Shao D, Vaidya AJ, Chen C, Zhuang L, Williamson DFK, Shaban M, Chen TY, Mahmood F. Artificial intelligence for multimodal data integration in oncology. Cancer Cell. 2022 Oct 10;40(10):1095-1110. doi: 10.1016/j.ccell.2022.09.012. PubMed 36220072 ↗
  • Tian S, Shi H, Chen W, Li S, Han C, Du F, Wang W, Wen H, Lei Y, Deng L, Tang J, Zhang J, Lin J, Shi L, Ning B, Zhao K, Miao J, Wang G, Hou H, Huang X, Kong W, Jin X, Ding Z, Lin R. Artificial intelligence-based diagnosis of standard endoscopic ultrasonography scanning sites in the biliopancreatic system: a multicenter retrospective study. Int J Surg. 2024 Mar 1;110(3):1637-1644. doi: 10.1097/JS9.0000000000000995. PubMed 38079604 ↗
  • Wu HL, Yao LW, Shi HY, Wu LL, Li X, Zhang CX, Chen BR, Zhang J, Tan W, Cui N, Zhou W, Zhang JX, Xiao B, Gong RR, Ding Z, Yu HG. Validation of a real-time biliopancreatic endoscopic ultrasonography analytical device in China: a prospective, single-centre, randomised, controlled trial. Lancet Digit Health. 2023 Nov;5(11):e812-e820. doi: 10.1016/S2589-7500(23)00160-7. Epub 2023 Sep 27. PubMed 37775472 ↗

Individual participant data

Plan to share: No

09

Timeline

1 registry update since Sep 25, 2026
ElapsedEstimatedEstimated, not yet reached

Started Apr 2026 (actual). Primary completion is estimated for Jun 2028, 26 months after the start.

How these figures are worked out, and which studies are left out of them.

Registered
Apr 15, 2026
First posted
Apr 21, 2026
StartActual
Apr 20, 2026
Primary completionEst.
Jun 30, 2028
CompletionEst.
Jun 30, 2028
Last update
Nov 5, 2026
What these dates mean
Start.
When the first participant enrolled; while estimated, when the study expects to open to recruitment.
Primary completion.
When the last participant was examined or treated to collect data for the study's main question, its primary outcome. A study that stopped early gives the date its data collection stopped.
Completion.
When the last participant's last visit took place, for every outcome, secondary ones and side effects included: the end of the study. Often later than primary completion, sometimes the same day.
Actual and Est.
Actual means the registry says the date has happened. Est. (estimated) is a date the sponsor plans or expects. It can still move, and the sponsor is expected to change it to actual once it has passed.
Minor edits
Nothing that changes what the study is or who can join. Edited: verification date and references
1 update, last Nov 5, 2026
Show all 1 update
  1. Nov 5, 2026
    Minor edits only
    + 2 other changes: verification date and references

From the registry record's own update history. This site started tracking changes on Sep 25, 2026; for anything earlier, see the record history on ClinicalTrials.gov ↗

10

Registry details

Key details

Study ID
NCT07543263
Collaborators
Liaocheng People's Hospital, Taian City Central Hospital, Qilu Hospital of Shandong University (Qingdao), Binzhou People's Hospital, Shandong Provincial Hospital, The Affiliated Hospital of Qingdao University, Qianfoshan Hospital, Shengli Oilfield Hospital, Binzhou Medical University
Responsible party
Sponsor
First posted
Apr 21, 2026
Start date
Apr 20, 2026
Primary completion
Jun 30, 2028 (estimated)
Completion
Jun 30, 2028 (estimated)
Last update
Nov 5, 2026

Study contacts

Zhen Li
Contact
qilulizhen@sdu.edu.cn
86+18560086106

Oversight

FDA-regulated drug
No
FDA-regulated device
No
View the source record on ClinicalTrials.gov ↗

Interested in this study?

Eligibility is decided by the study team. Share this record with your doctor or contact the team directly.

Contact study team

Follow this study

Get an email when the registry record changes — status, dates, results — or when someone posts here.

Sign in to follow

Discussion

Questions and observations about this study, from anyone following it. Not medical advice, and not a channel to the study team — their contact details are on the registry record.

Sign in to join the discussion. Reading takes no account; posting does. You choose a display name, and a pseudonym is the default.

Nothing here yet. If you are running this trial, taking part in it, or weighing whether to, this is the place to say so.

Start the discussion