UMIN-CTR Clinical Trial
| Unique ID issued by UMIN | UMIN000060069 |
|---|---|
| Receipt number | R000068690 |
| Scientific Title | Construction of a Large-Scale Database for Machine Learning in Brain Imaging |
| Date of disclosure of the study information | 2025/12/26 |
| Last modified on | 2025/12/12 15:46:50 |
* 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
Construction of a Large-Scale Database for Machine Learning in Brain Imaging
Acronym
Construction of a Large-Scale Database for Machine Learning in Brain Imaging
Scientific Title
Construction of a Large-Scale Database for Machine Learning in Brain Imaging
Scientific Title:Acronym
Construction of a Large-Scale Database for Machine Learning in Brain Imaging
Region
| Japan |
Condition
Condition
Mental Disorders and Healthy Controls
Classification by specialty
| Psychiatry | Adult |
Classification by malignancy
Others
Genomic information
YES
Objectives
Narrative objectives1
Purpose of this research: In this research, we will collect MRI images from an open dataset and process them using a common preprocessing pipeline to create a database for secondary machine learning of brain images. Using the collected image data, we will create a standard model based on labels that are expected to be minimally attached to the image data, such as age and gender. By performing transfer learning based on this standard model, we aim to reduce the effort (time, manpower, and funds) required to create large amounts of labeled data for model creation, and to use transfer learning to create highly accurate models for problems where obtaining large amounts of labeled brain images is clinically difficult.
Significance of this research: If this research creates a database for secondary brain image machine learning, it will solve a fundamental problem associated with creating AI for brain images (the effort (time, manpower, and funds) required to create large amounts of labeled data). Furthermore, transfer learning will enable the creation of highly accurate models for problems where obtaining large amounts of labeled brain images is clinically difficult.
Basic objectives2
Safety,Efficacy
Basic objectives -Others
Trial characteristics_1
Trial characteristics_2
Developmental phase
Assessment
Primary outcomes
This is an analysis plan for dataset creation and utilization of the created database.
<Inclusion Criteria>
1. Brain images acquired via MRI are available.
2. Information regarding age or gender is available.
Cases meeting the above inclusion criteria will be included.
<Analysis>
Common preprocessing will be applied to the acquired brain image data. These preprocessed images will serve as the final input images for machine learning, enabling the creation of high-accuracy models based on age and gender. For high-accuracy model creation, deep learning will be employed in addition to conventional machine learning. Using the age and gender prediction models created from the large dataset above, the following models will be developed using a dataset rich in clinical information available at the Department of Psychiatry, Keio University School of Medicine: a cognitive function prediction model, a mental disorder prediction model, a mental disorder treatment effect prediction model, and a brain substance prediction model.
Key secondary outcomes
Base
Study type
Others,meta-analysis etc
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
| 18 | years-old | <= |
Age-upper limit
| 100 | years-old | >= |
Gender
Male and Female
Key inclusion criteria
Inclusion Criteria
1. MRI brain images are available.
2. Information regarding age or sex is available.
Include cases that meet the above inclusion criteria.
Include cases with available MRI brain images and age/sex information necessary for creating a baseline model based on age and sex.
Key exclusion criteria
Participation in the study will be discontinued for a subject if any of the following criteria apply:
1) The subject requests to withdraw from the study or withdraws consent.
2) Ineligibility is determined after enrollment.
3) A major violation of the study protocol is identified.
4) Other circumstances deemed necessary by the Principal Investigator or Co-Investigator
[Withdrawal Procedure]
(a) Patients withdrawn from the study will not undergo further evaluations for the study.
(b) There are no plans to add additional cases due to early withdrawal of research subjects.
Target sample size
Research contact person
Name of lead principal investigator
| 1st name | Jinichi |
| Middle name | |
| Last name | Hirano |
Organization
Keio University
Division name
School of Medicine
Zip code
160-8582
Address
35 Shinanomachi, Shinjuku-ku, Tokyo, 160-8582, Japan
TEL
03-5363-3971
hjinichi@keio.jp
Public contact
Name of contact person
| 1st name | Jinichi |
| Middle name | |
| Last name | Hirano |
Organization
Keio University
Division name
School of Medicine
Zip code
160-8582
Address
35 Shinanomachi, Shinjuku-ku, Tokyo, 160-8582, Japan
TEL
03-5363-3971
Homepage URL
hjinichi@keio.jp
Sponsor or person
Institute
Keio University
Institute
Department
Personal name
Funding Source
Organization
No
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
Keio University
Address
35 Shinanomachi, Shinjuku-ku, Tokyo, 160-8582, Japan
Tel
03-5363-3503
med-nintei-jimu@adst.keio.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
| 2025 | Year | 12 | Month | 26 | 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
Enrolling by invitation
Date of protocol fixation
| 2022 | Year | 03 | Month | 10 | Day |
Date of IRB
| 2022 | Year | 03 | Month | 10 | Day |
Anticipated trial start date
| 2022 | Year | 04 | Month | 01 | Day |
Last follow-up date
| 2028 | Year | 03 | Month | 31 | Day |
Date of closure to data entry
Date trial data considered complete
Date analysis concluded
Other
Other related information
None
Management information
Registered date
| 2025 | Year | 12 | Month | 12 | Day |
Last modified on
| 2025 | Year | 12 | Month | 12 | Day |
Link to view the page
Value
https://center6.umin.ac.jp/cgi-open-bin/ctr_e/ctr_view.cgi?recptno=R000068690
