| CTRI Number |
CTRI/2025/12/099178 [Registered on: 16/12/2025] Trial Registered Prospectively |
| Last Modified On: |
16/12/2025 |
| Post Graduate Thesis |
No |
| Type of Trial |
Observational |
|
Type of Study
|
Retrospective study |
| Study Design |
Other |
|
Public Title of Study
|
Study using artificial intelligence to examine microscope pictures of breast cancer tissue to identify risk of their breast cancer. |
|
Scientific Title of Study
|
Deep Learning on Histopathological Images for Risk Stratification in Indian Breast Cancer Patients |
| Trial Acronym |
Nil |
|
Secondary IDs if Any
|
| Secondary ID |
Identifier |
| NIL |
NIL |
|
|
Details of Principal Investigator or overall Trial Coordinator (multi-center study)
|
| Name |
Dr Sudeep Gupta |
| Designation |
Director TMC and Professor Medical Oncology |
| Affiliation |
Tata Memorial Center |
| Address |
Department of Medical Oncology
Room no 1109, 11 floor,
Homi Bhabha Building
Mumbai
MAHARASHTRA
400012
India |
| Phone |
8591555030 |
| Fax |
|
| Email |
sudeepgupta04@yahoo.com |
|
Details of Contact Person
Scientific Query
|
| Name |
Dr Sudeep Gupta |
| Designation |
Director TMC and Professor Medical Oncology |
| Affiliation |
Tata Memorial Center |
| Address |
Department of Medical Oncology
Room no 1109, 11 floor,
Homi Bhabha Building
MAHARASHTRA
400012
India |
| Phone |
8591555030 |
| Fax |
|
| Email |
sudeepgupta04@yahoo.com |
|
Details of Contact Person
Public Query
|
| Name |
Yogesh Kembhavi |
| Designation |
Research Manager |
| Affiliation |
Tata Memorial Center |
| Address |
1109, 11 floor,
Homi Bhabha Building
Tata Memorial Hospital
Mumbai
MAHARASHTRA
400012
India |
| Phone |
8591555030 |
| Fax |
|
| Email |
yogeshkembhavi1@gmail.com |
|
|
Source of Monetary or Material Support
|
| Tata Memorial Centre
E Borges Marg
Parel, Mumbai 400012 |
|
|
Primary Sponsor
|
| Name |
Tata Memorial Centre |
| Address |
Tata Memorial Hospital
E Borges Marg,
Parel 400012 |
| Type of Sponsor |
Other [Government Hospital] |
|
|
Details of Secondary Sponsor
|
| Name |
Address |
| Not applicable |
Nil |
|
|
Countries of Recruitment
|
India |
|
Sites of Study
|
| No of Sites = 1 |
| Name of Principal
Investigator |
Name of Site |
Site Address |
Phone/Fax/Email |
| Dr Sudeep Gupta |
Tata Memorial Centre |
Room no:1109, 11th floor, Homi Bhabha Building
Mumbai
MAHARASHTRA |
8591555030
sudeepgupta04@yahoo.com |
|
|
Details of Ethics Committee
|
| No of Ethics Committees= 1 |
| Name of Committee |
Approval Status |
| Tata Memorial Centre |
Approved |
|
|
Regulatory Clearance Status from DCGI
|
|
|
Health Condition / Problems Studied
|
| Health Type |
Condition |
| Patients |
(1) ICD-10 Condition: C509||Malignant neoplasm of breast of unspecified site, |
|
|
Intervention / Comparator Agent
|
| Type |
Name |
Details |
| Intervention |
Nil |
Nil |
| Intervention |
Not applicable |
Not applicable |
| Comparator Agent |
Not applicable |
Not applicable |
|
|
Inclusion Criteria
|
| Age From |
18.00 Year(s) |
| Age To |
99.00 Year(s) |
| Gender |
Female |
| Details |
Female patients diagnosed with invasive HRpositive, HER2-negative breast cancer.
Histologically-confirmed invasive carcinoma of the breast, stage I to stage III
Available archival H&E slide from diagnostic core biopsy or primary surgery.
Must have the following recorded clinicopathologic variables, for eligibility and for applying the AI model: grade, age, ER, PR, HER2 at diagnosis. Recorded follow-up events and time to events, with a minimum of 5 years to last contact or or documented death before 5 years.
Age at diagnosis more than 18 years
To reduce bias, a consecutive patient data collection is important, where all eligible patients diagnosed within a fixed period of time will be included. i.e. all consecutively-diagnosed eligible patients diagnosed between 2014 to 2015, if required study will be extended to 2016. |
|
| ExclusionCriteria |
| Details |
Patients with distant metastases at diagnosis should be excluded.
Patients with non-available or Poor quality pathology material will be excluded.
Patients with no follow up update beyond 3 years will be excluded. |
|
|
Method of Generating Random Sequence
|
Not Applicable |
|
Method of Concealment
|
Not Applicable |
|
Blinding/Masking
|
Not Applicable |
|
Primary Outcome
|
| Outcome |
TimePoints |
To determine the association of the AI-generated risk score (both as continuous and categorical variables) with 5-year patient outcomes. The primary endpoint is distant recurrence-free interval
Protocol_Version__1.0 dated 22 Aug 2025 Page 4 of 7(DRFI). Secondary endpoints include recurrence-free interval (RFI), disease-free survival (DFS), and breast cancer-specific survival |
2 years |
|
|
Secondary Outcome
|
| Outcome |
TimePoints |
| To perform a utility analysis to estimate the proportion of patients whose chemotherapy treatment decisions might potentially change based on the AI-derived risk classification. |
2 year |
|
|
Target Sample Size
|
Total Sample Size="1000"
Sample Size from India="1000"
Final Enrollment numbers achieved (Total)= "Applicable only for Completed/Terminated trials"
Final Enrollment numbers achieved (India)="Applicable only for Completed/Terminated trials" |
|
Phase of Trial
|
N/A |
|
Date of First Enrollment (India)
|
31/12/2025 |
| Date of Study Completion (India) |
Applicable only for Completed/Terminated trials |
| Date of First Enrollment (Global) |
Date Missing |
| Date of Study Completion (Global) |
Applicable only for Completed/Terminated trials |
|
Estimated Duration of Trial
|
Years="2"
Months="0"
Days="0" |
|
Recruitment Status of Trial (Global)
|
Not Applicable |
| Recruitment Status of Trial (India) |
Not Yet Recruiting |
|
Publication Details
|
N/A |
|
Individual Participant Data (IPD) Sharing Statement
|
Will individual participant data (IPD) be shared publicly (including data dictionaries)?
Response - NO
|
|
Brief Summary
|
This is a single-center, retrospective observational study involving no patient intervention or direct patient contact. Existing archival hematoxylin and eosin (H&E)-stained slides from eligible hormone receptor-positive (HR+), HER2-negative breast cancer patients treated at TMC will be utilized. These slides have been previously processed as part of routine clinical management. Patients included will have available clinical data and a minimum of 5-year follow-up post-treatment.
Whole-slide images will be digitized at a standardized magnification and resolution, converted into analyzable image sections (tiles), and processed using specialized image-analysis software. Imagederived features will be extracted using a self-supervised learning (SSL) model at Technion, Israel. The multimodal deep-learning model developed at Technion will integrate these features with recorded clinical variables (including patient age, tumor size, tumor grade, ER and PR status) to generate an AI-derived risk score per patient. A calibrated AI risk score will subsequently be determined.
Statistical analyses will assess the association of the AI risk scores with patient outcomes, including distant recurrence-free interval (DRFI), recurrence-free interval (RFI), disease-free survival (DFS), and breast cancer-specific survival (BCSS). Patient data will be analyzed in batches, and power estimates will be refined as necessary based on interim analyses |