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

NCT05783986 | Unknown

• 1 other identifier: SYSKY-2023-084-01
• Study Type: observational
• Target: 600
• Locations: 0 countries
• Sites: N/A

Brief Summary

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).

Conditions

Endometrial Cancer

Keywords

deep learning, MMR, MRI

Outcome Measures

Primary Outcomes (1)

• 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

Study Arms (3)

Testing group

375 patients of our hosipital,randomly divided.

Other: randomly divided

Internal validation group

125 patients of our hosipital,randomly divided.

Other: randomly divided

External validation group

100 patients of Sun Yat-sen University Cancer Center

Interventions

randomly divided OTHER

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; Testing group

Eligibility Criteria

• Sex: female
• Healthy Volunteers: No
• Age Groups: Child (0-17), Adult (18-64), Older Adult (65+)
• Sampling Method: Non-Probability Sample

Study Population

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

You may qualify if:

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

You may not qualify if:

• (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

Sponsors & Collaborators

• Sun Yat-Sen Memorial Hospital of Sun Yat-Sen University: lead
• Sun Yat-sen University: collaborator

MeSH Terms

Conditions

Endometrial Neoplasms

Condition Hierarchy (Ancestors)

Uterine Neoplasms; Genital Neoplasms, Female; Urogenital Neoplasms; Neoplasms by Site; Neoplasms; Uterine Diseases; Genital Diseases, Female; Female Urogenital Diseases; Female Urogenital Diseases and Pregnancy Complications; Urogenital Diseases; Genital Diseases

Study Officials

• Jing Li

  Sun Yat-Sen Memorial Hospital of Sun Yat-Sen University

  PRINCIPAL INVESTIGATOR

Central Study Contacts

Jing Li

CONTACT

15915893493; lijing228@mail.sysu.edu.cn

Study Design

• Study Type: observational
• Observational Model: OTHER
• Time Perspective: RETROSPECTIVE
• Sponsor Type: OTHER
• Responsible Party: SPONSOR

Study Record Dates

• First Submitted: March 13, 2023
• First Posted: March 24, 2023
• Study Start: April 17, 2023
• Primary Completion: June 30, 2024
• Study Completion: December 31, 2024
• Last Updated: March 24, 2023

Record last verified: 2023-03

Data Sharing

• IPD Sharing: Will not share