Skip to content

Multimodal MRI radiomics machine learning in predicting lymphovascular space invasion (LVSI) in endometrial cancer

Multimodal MRI radiomics machine learning in predicting lymphovascular space invasion (LVSI) in endometrial cancer

Status
Active, not recruiting
Phases
Unknown
Study type
Observational
Source
ChiCTR
Registry ID
ChiCTR2500099639
Enrollment
Unknown
Registered
2025-03-26
Start date
2025-04-01
Completion date
Unknown
Last updated
2025-03-31

For informational purposes only — not medical advice. Sourced from public registries and may not reflect the latest updates. Terms

Conditions

Endometrial cancer

Interventions

Gold Standard:Pathological diagnosis::Endometrial cancer
Pathological immunohistochemical diagnosis:Lymphatic vessel invasion.
Index test:Analyzing MRI images through radiomics and machine learning methods to predict lymphatic vessel invasion in endometrial cancer.

Sponsors

Yuebei People’s Hospital
Lead Sponsor

Eligibility

Sex/Gender
Female
Age
20 Years to 80 Years

Inclusion criteria

Inclusion criteria: 1.The histopathological findings indicate endometrial carcinoma, including endometrioid carcinoma, mucinous carcinoma, serous carcinoma, clear cell carcinoma, and undifferentiated carcinoma, but excluding carcinosarcoma. 2.Lvsi immunohistochemistry results are available. 3.MRI examination has been completed, and comprehensive clinical information is available. 4.The maximum diameter of the endometrial carcinoma lesion on MRI is greater than 0.5 cm. 5.The expected survival period is estimated to be at least greater than 6 months. 6.Aged between 20 and 80 years, without severe heart disease, and without significant liver or kidney dysfunction.

Exclusion criteria

Exclusion criteria: 1.Incomplete clinical and Radiological data. 2.Radiotherapy or chemotherapy for endometrial cancer before enrollment. 3.The MRI images contain artifacts, making them unsuitable for radiomics and deep learning analysis. 4.Deemed unsuitable for participation in this study as determined by the investigator.

Design outcomes

Primary

MeasureTime frame
Radiomics characterisation of ROI that semi-automatically separates endometrial cancer lesions by hand,Including geometric features, intensity features, and texture features;

Secondary

MeasureTime frame
Lymphovascular space invasion status;

Countries

China

Contacts

Public ContactSun Junqi

Yuebei People’s Hospital

sunjunqi1233668@sina.com+86 751 6913361

Outcome results

None listed

Source: ChiCTR (via WHO ICTRP) · Data processed: Feb 4, 2026