Radiomics-Based Non-Invasive MRI Differentiation of Uterine Sarcomas and Fibroids

Launched by TONGJI HOSPITAL · Aug 18, 2025

Keywords

ClinConnect Summary

This study is an observational project that aims to build and test an artificial intelligence (AI) tool using many kinds of patient data (medical history, exam findings, MRI scans, lab results, and pathology) to tell apart uterine fibroids (leiomyoma), which are usually benign, from uterine sarcoma, a type of cancer. It uses past records from several hospitals in China and analyzes data after the fact (retrospective) to see how well the AI can differentiate these conditions based on MRI and other information.

Who may be eligible? The study focuses on women 18 years and older who have a confirmed diagnosis of either uterine fibroids or uterine sarcoma and who had a preoperative MRI within about two months of surgery. People with tumors smaller than 2 cm, cancers that started elsewhere and spread to the uterus, or other pelvic cancers are not included. This is an observational study with no new treatment given; it looks at how accurately the diagnostic model can identify fibroids versus sarcoma, using measures like accuracy, sensitivity, specificity, and the chances that a positive or negative result is correct. The project is currently enrolling by invitation, involves multiple Chinese centers, and is not regulated as a new drug or device by the FDA. Data handling follows ethics approvals, and results will also explore how the model explains its decisions and how different model setups compare.

Gender

FEMALE

Eligibility criteria

• Inclusion Criteria:
• • 1. Histopathological confirmation of uterine sarcoma or leiomyoma.
• • 2. Availability of preoperative MRI, includingT2WI and DWI, performed within 2 months of the surgery.
• Exclusion Criteria:
• • 1. Tumors smaller than 2 cm. Small tumors may be difficult to accurately perform segmentation and feature extraction, which may affect the accuracy and reliability of the model.
• • 2. Non-primary uterine sarcomas. Sarcomas from other sites with metastasis to the uterus were excluded because the biological characteristics and imaging findings of these tumors may differ from those of primary uterine sarcomas and may lead to bias in the diagnostic model.
• • 3. Concurrent pelvic malignancies. To avoid the influence of other types of tumors on the imaging features of uterine sarcoma and leiomyoma, and to ensure the pertinence and accuracy of the model.