Developing a MRI-based Deep Learning Model to Predict MMR Status

Developing a MRI-based Deep Learning Model to Predict MMR Status of Endometrial Carcinoma

In order to develop a convenient, cheap and comprehensive method to preoperatively predict dMMR and reduce the number of people requiring dMMR-related immunohistochemical or genetic testing after surgery, this study aims to establish a deep learning model based on MRI to predict the MMR status of endometrial cancer. Patients diagnosed with endometrial cancer after surgery and who had completed pelvic MRI before surgery were collected. Deep learning was used to combine the clinical model with MR Image data to build the model. ROC curves were constructed for the testing group, internal verification group and external verification group, and the area under ROC curves were calculated to evaluate the diagnostic effect and stability of the model.

The dual threshold triage strategy was used to screen out the pMMR population (below the lower threshold), dMMR population (above the upper threshold) and the uncertain part of the population (between the thresholds).

Study Overview

• Status: Not yet recruiting
• Conditions: Endometrial Cancer
• Intervention / Treatment: Other: randomly divided

Detailed Description

In this study, patients diagnosed with endometrial cancer after surgery and who had completed pelvic MRI before surgery were collected from 2017 to 2022. It is expected to collect 500 cases in our hospital, which are divided into 375 cases (experimental group) and 125 cases (internal verification group).

100 cases of Sun Yat-sen University Cancer Center for external verification. Clinical data (age, gender, BMI, CA125, CA19-9, MR-T staging, immunohistochemical results of MMR-related proteins) of the study population were collected and logistics regression analysis was conducted to establish clinical models. Extract, segment, integrate and enhance MR Image data.

Deep learning was used to combine the clinical model with MR Image data to build the model. ROC curves were constructed for the testing group, internal verification group and external verification group, and the area under ROC curves were calculated to evaluate the diagnostic effect and stability of the model.

The dual threshold triage strategy was used to screen out the pMMR population (below the lower threshold), dMMR population (above the upper threshold) and the uncertain part of the population (between the thresholds). If the predictive score is above the lower threshold, the patient is advised to undergo further immunohistochemical or genetic testing to confirm MMR status or dMMR type

• Study Type: Observational
• Enrollment (Anticipated): 600

Contacts and Locations

• Study Contact: Name: Jing Li; Phone Number: 15915893493; Email: lijing228@mail.sysu.edu.cn

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Child; Adult; Older Adult
• Accepts Healthy Volunteers: No
• Genders Eligible for Study: Female

• Sampling Method: Non-Probability Sample

Study Population

Patients diagnosed with endometrial cancer after surgery and who had completed pelvic MRI before surgery

Description

Inclusion Criteria:

• Patients diagnosed with endometrial cancer after surgery and who had completed pelvic MRI before surgery from 2017 to 2022

Exclusion Criteria:

• (1) There was no immunohistochemical detection result of MMR-related protein; (2) Radiotherapy and chemotherapy before MRI; (3) small tumors that are difficult to identify on the image (<5mm) ; (4) The T2-weighted imaging quality is insufficient to plot ROI, such as obvious motion artifacts; (5) There are other gynecological malignancies

Study Plan

How is the study designed?

Number of groups / cohorts

3

Cohorts and Interventions

Group / Cohort	Intervention / Treatment
Testing group; 375 patients of our hosipital,randomly divided.	Other: randomly divided; 500 patients of our hospital were randomly divided into testing group and internal validation group, and 100 patients in collabrative hospital were external validation group.
Internal validation group; 125 patients of our hosipital,randomly divided.	Other: randomly divided; 500 patients of our hospital were randomly divided into testing group and internal validation group, and 100 patients in collabrative hospital were external validation group.
External validation group; 100 patients of Sun Yat-sen University Cancer Center

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Area under receiver operating characteristic curve (AUROC)	The area under receiver operating characteristic curve (AUROC) was used to evaluate the performance of the models	one year

Collaborators and Investigators

• Sponsor: Sun Yat-Sen Memorial Hospital of Sun Yat-Sen University
• Collaborators: Sun Yat-sen University
• Investigators: Principal Investigator: Jing Li, Sun Yat-sen Memorial Hospital，Sun Yat-sen University

Study record dates

Study Major Dates

• Study Start (Anticipated): April 17, 2023
• Primary Completion (Anticipated): June 30, 2024
• Study Completion (Anticipated): December 31, 2024

Study Registration Dates

• First Submitted: March 13, 2023
• First Submitted That Met QC Criteria: March 13, 2023
• First Posted (Actual): March 24, 2023

Study Record Updates

• Last Update Posted (Actual): March 24, 2023
• Last Update Submitted That Met QC Criteria: March 13, 2023
• Last Verified: March 1, 2023

More Information

Terms related to this study

• Keywords: deep learning, MMR, MRI
• Additional Relevant MeSH Terms: Neoplasms; Urogenital Neoplasms; Neoplasms by Site; Uterine Neoplasms; Genital Neoplasms, Female; Uterine Diseases; Endometrial Neoplasms
• Other Study ID Numbers: SYSKY-2023-084-01

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO
• IPD Plan Description: there is not a plan to make individual participant data (IPD) available to other researchers.

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No