| CTRI Number |
CTRI/2018/06/014569 [Registered on: 19/06/2018] Trial Registered Prospectively |
| Last Modified On: |
31/01/2022 |
| Post Graduate Thesis |
No |
| Type of Trial |
Observational |
|
Type of Study
|
Data Collection |
| Study Design |
Other |
|
Public Title of Study
|
A Study for identifying eye pressure problem through deep learning algorithm |
|
Scientific Title of Study
|
Deep Learning Algorithms Applied to Optical Coherence Tomography Images of the Optic Nerve Head for Improved Glaucoma Diagnosis |
| Trial Acronym |
|
|
Secondary IDs if Any
|
| Secondary ID |
Identifier |
| NIL |
NIL |
|
|
Details of Principal Investigator or overall Trial Coordinator (multi-center study)
|
| Name |
Dr A Vijayalakshmi |
| Designation |
Medical Consultant |
| Affiliation |
Aravind Eye Hospital and PG Institute of Ophthalmology |
| Address |
Glaucoma Clinic
Room no 300
3rd Floor
OPD Block
Anna Nagar
Madurai
TAMIL NADU
625020
India |
| Phone |
914524356304 |
| Fax |
914522530984 |
| Email |
vijimmc@gmail.com |
|
Details of Contact Person
Scientific Query
|
| Name |
Dr SR Krishnadas |
| Designation |
Senior Consultant |
| Affiliation |
Aravind Eye Hospital and PG Institute of Ophthalmology |
| Address |
Glaucoma Clinic
Room no 300
3rd Floor
OPD Block
Anna Nagar
Madurai
TAMIL NADU
625020
India |
| Phone |
914524356303 |
| Fax |
914522530984 |
| Email |
krishnadas@aravind.org |
|
Details of Contact Person
Public Query
|
| Name |
Dr SR Krishnadas |
| Designation |
Senior Consultant |
| Affiliation |
Aravind Eye Hospital and PG Institute of Ophthalmology |
| Address |
Glaucoma Clinic
Room no 300
3rd Floor
OPD Block
Anna Nagar
TAMIL NADU
625020
India |
| Phone |
914524356303 |
| Fax |
914522530984 |
| Email |
krishnadas@aravind.org |
|
|
Source of Monetary or Material Support
|
| National University of Singapore
21 Lower Kent Ridge Road
Singapore 119077 |
|
|
Primary Sponsor
|
| Name |
National University of Singapore |
| Address |
21 Lower Kent Ridge Road Singapore 119077 |
| Type of Sponsor |
Other [Autonomous Research University] |
|
|
Details of Secondary Sponsor
|
|
|
Countries of Recruitment
|
Russian Federation
Australia
China
India
Philippines
Singapore
United Arab Emirates
United States of America |
|
Sites of Study
|
| No of Sites = 1 |
| Name of Principal
Investigator |
Name of Site |
Site Address |
Phone/Fax/Email |
| Dr A Vijayalakshmi |
Aravind Eye Hospital and PG Institute of Ophthalmology |
Glaucoma Clinic
Room no 300
3rd Floor
OPD Block
1 Anna Nagar
Madurai
TAMIL NADU |
914524356304
914522530984
vijimmc@gmail.com |
|
|
Details of Ethics Committee
|
| No of Ethics Committees= 1 |
| Name of Committee |
Approval Status |
| Institutional Ethics Committee |
Approved |
|
|
Regulatory Clearance Status from DCGI
|
|
Health Condition / Problems Studied
Modification(s)
|
| Health Type |
Condition |
| Patients |
(1) ICD-10 Condition: H400||Glaucoma suspect, |
|
|
Intervention / Comparator Agent
|
| Type |
Name |
Details |
| Intervention |
Nil |
Nil |
| Comparator Agent |
Nil |
Nil |
|
|
Inclusion Criteria
|
| Age From |
35.00 Year(s) |
| Age To |
70.00 Year(s) |
| Gender |
Both |
| Details |
1. All ethnicities
2. All refractive errors
3. All ophthalmic conditions/pathologies
4. All visual fields and
5. All other conditions (e.g. Alzheimer).
|
|
| ExclusionCriteria |
| Details |
1. We will exclude subjects in which the ONH tissues (neural and connective) are not visible with OCT, as assessed manually.
|
|
|
Method of Generating Random Sequence
|
Not Applicable |
|
Method of Concealment
|
Not Applicable |
|
Blinding/Masking
|
Not Applicable |
|
Primary Outcome
|
| Outcome |
TimePoints |
| To identify whether deep learning (artificial intelligence) can provide better diagnostic power than that derived from any other glaucoma index. If so, we would like to predict the diagnosis and the risk factor for the patients for glaucoma merely from OCT images. Time: 2 yrs (1 yr data collection + 6 months training and testing of the algorithm + 6 months validation) |
24 months |
|
|
Secondary Outcome
|
| Outcome |
TimePoints |
"To compare the performance of deep learning based diagnosis from OCT images against other clinicial methods currently being used.
|
06 Months |
|
|
Target Sample Size
|
Total Sample Size="100000"
Sample Size from India="4000"
Final Enrollment numbers achieved (Total)= "1506"
Final Enrollment numbers achieved (India)="1506" |
|
Phase of Trial
|
N/A |
|
Date of First Enrollment (India)
|
02/07/2018 |
| Date of Study Completion (India) |
31/10/2019 |
| Date of First Enrollment (Global) |
02/01/2017 |
| Date of Study Completion (Global) |
29/11/2019 |
|
Estimated Duration of Trial
|
Years="0"
Months="11"
Days="30" |
Recruitment Status of Trial (Global)
Modification(s)
|
Completed |
| Recruitment Status of Trial (India) |
Completed |
Publication Details
Modification(s)
|
Published in Optical Society of America |
|
Individual Participant Data (IPD) Sharing Statement
|
Will individual participant data (IPD) be shared publicly (including data dictionaries)?
Response - NO
|
Brief Summary
Modification(s)
|
To summarize, we demonstrate as a proof of concept that it is possible to develop DL segmentation tools that are easily translatable across OCT devices without ever needing additional manual segmentation data. The core contributions of this study to achieve the same included: (1) the development of ONH-Net – a highly modular DL approach for the segmentation of 3D OCT volumes of the ONH; and (2) the development of the enhancer – a DL approach to enhance the OCT image quality from multiple devices and simultaneously reduce the differences in the device-specific image characteristics. Through our core contributions, we were able to address (as a proof of concept) the device-specific nature of DL algorithms, an important factor that limits the translations and wide-spread adoption of DL algorithms in clinics. Finally, we hope the proposed framework can potentially help patients for the longitudinal follow-up on multiple devices, and encourage multi-center glaucoma studies also. |