UMIN-CTR Clinical Trial
| Unique ID issued by UMIN | UMIN000060342 |
|---|---|
| Receipt number | R000069009 |
| Scientific Title | Deep learning model using 3D convolutional neural network to predict the outcome of biliary cannulation |
| Date of disclosure of the study information | 2026/02/01 |
| Last modified on | 2026/01/13 18:21:05 |
* This page includes information on clinical trials registered in UMIN clinical trial registed system.
* We don't aim to advertise certain products or treatments
Basic information
Public title
Deep learning model using 3D convolutional neural network to predict the outcome of biliary cannulation
Acronym
Deep learning model using 3D convolutional neural network to predict the outcome of biliary cannulation
Scientific Title
Deep learning model using 3D convolutional neural network to predict the outcome of biliary cannulation
Scientific Title:Acronym
Deep learning model using 3D convolutional neural network to predict the outcome of biliary cannulation
Region
| Japan |
Condition
Condition
Hepato-biliopancreatic dieases
Classification by specialty
| Gastroenterology |
Classification by malignancy
Malignancy
Genomic information
NO
Objectives
Narrative objectives1
To establish deep learning model to predict the outcome of biliary cannulation during ERCP-related procedure
Basic objectives2
Efficacy
Basic objectives -Others
Trial characteristics_1
Trial characteristics_2
Developmental phase
Assessment
Primary outcomes
Diagnostic accuracy of deep learning model to predict the outcome of biliary cannulation (conventional or rescue methods)
Key secondary outcomes
Base
Study type
Observational
Study design
Basic design
Randomization
Randomization unit
Blinding
Control
Stratification
Dynamic allocation
Institution consideration
Blocking
Concealment
Intervention
No. of arms
Purpose of intervention
Type of intervention
Interventions/Control_1
Interventions/Control_2
Interventions/Control_3
Interventions/Control_4
Interventions/Control_5
Interventions/Control_6
Interventions/Control_7
Interventions/Control_8
Interventions/Control_9
Interventions/Control_10
Eligibility
Age-lower limit
| Not applicable |
Age-upper limit
| Not applicable |
Gender
Male and Female
Key inclusion criteria
Patients with native papilla who underwent biliary ERCP recorded on digital video from April 2017 to December 2024.
Key exclusion criteria
Patients with surgically altered anatomy, such as Billroth II or Roux-en-Y reconstruction
Target sample size
800
Research contact person
Name of lead principal investigator
| 1st name | Hiroo |
| Middle name | |
| Last name | Imazu |
Organization
Teikyo University School of Medicine
Division name
Department of Internal Medicine
Zip code
173-8605
Address
Kaga, 2-11-1, Itabashi-ku, Tokyo
TEL
03-3964-1211
imazu.hiroo.cx@teikyo-u.ac.jp
Public contact
Name of contact person
| 1st name | Hiroo |
| Middle name | |
| Last name | Imazu |
Organization
Teikyo University School of Medicine
Division name
Department of Internal Medicine
Zip code
173-8605
Address
Kaga, 2-11-1, Itabashi-ku, Tokyo
TEL
03-3964-1211
Homepage URL
imazu.hiroo.cx@teikyo-u.ac.jp
Sponsor or person
Institute
Teikyo University School of Medicine
Institute
Department
Personal name
Imazu Hiroo
Funding Source
Organization
None
Organization
Division
Category of Funding Organization
Other
Nationality of Funding Organization
Other related organizations
Co-sponsor
Name of secondary funder(s)
IRB Contact (For public release)
Organization
Teikyo University School of Medicine
Address
Kaga, 2-11-1, Itabashi-ku, Tokyo
Tel
03-3964-1211
imazu.hiroo.cx@teikyo-u.ac.jp
Secondary IDs
Secondary IDs
NO
Study ID_1
Org. issuing International ID_1
Study ID_2
Org. issuing International ID_2
IND to MHLW
Institutions
Institutions
Other administrative information
Date of disclosure of the study information
| 2026 | Year | 02 | Month | 01 | Day |
Related information
URL releasing protocol
Publication of results
Unpublished
Result
URL related to results and publications
Number of participants that the trial has enrolled
Results
Results date posted
Results Delayed
Results Delay Reason
Date of the first journal publication of results
Baseline Characteristics
Participant flow
Adverse events
Outcome measures
Plan to share IPD
IPD sharing Plan description
Progress
Recruitment status
Preinitiation
Date of protocol fixation
| 2025 | Year | 05 | Month | 20 | Day |
Date of IRB
Anticipated trial start date
| 2025 | Year | 05 | Month | 20 | Day |
Last follow-up date
| 2026 | Year | 12 | Month | 31 | Day |
Date of closure to data entry
Date trial data considered complete
Date analysis concluded
Other
Other related information
This is observational study. Consecutive patients at Teikyo University Hospital who underwent ERCP-related procedures between April 1, 2017, and December 31, 2024, and had no prior history of ERCP-related procedures are enrolled. The aim of study is to develop a convolutional neural network (CNN)-based diagnostic model to assess the difficulty of biliary cannulation using recorded ERCP procedure videos from the study cohort. The model will be trained on ERCP video segments comprising (1) footage captured when the direction of the catheter tip toward the biliary orifice is fixed (immediately before cannulation) and (2) footage that depicts the morphology of the papilla, together with the corresponding cannulation outcomes (cannulation difficulty). Difficulty will be classified as (1) standard technique or (2) rescue techniques (operator change, device switch, pancreatic duct guidewire technique, precut). Using the constructed CNN model, we will determine the difficulty of biliary cannulation on ERCP procedure videos from study subjects not used for training as test samples and evaluate its diagnostic accuracy.
Management information
Registered date
| 2026 | Year | 01 | Month | 13 | Day |
Last modified on
| 2026 | Year | 01 | Month | 13 | Day |
Link to view the page
Value
https://center6.umin.ac.jp/cgi-open-bin/ctr_e/ctr_view.cgi?recptno=R000069009
