What type of study is this?

This is a Quantitative Study study.

September 17, 2025

Predicting Microsatellite Instability in Endometrial Cancer by Multi-modal MRI-based Radiomics Combined with Clinical Risk Factors

Key Points

The machine learning model demonstrated significant predictive efficacy for assessing microsatellite instability in endometrial cancer, enhancing clinical decision-making.
Combination of multimodal MRI data with clinical risk factors yielded a model with performance comparable to existing imaging omics models.
Patients unsuitable for surgery can benefit from this non-invasive method for microsatellite instability assessment, potentially influencing treatment options.
These models may improve prognosis evaluation and the feasibility of immunotherapy approaches in advanced endometrial cancer patients.

Abstract

Motivation: Endometrial cancer（EC） is a common malignant tumor of the female reproductive system, and the incidence is still rising. Goal(s): To develop a machine learning model to noninvasively assess microsatellite instability（MSI） in endometrial cancer. Approach: Different machine learning models were constructed based on T2WI, DWI, arterial phase, equilibrium phase images as well as clinical and pathological data, and then the model with the best performance was selected. Results: The predictive efficacy of the combined model Nomogram is comparable to that of the multimodal imaging omics model, and both have higher clinical decision benefits. Impact: These machine learning models can perform non-invasive MSI status assessment for patients who are not suitable for surgery, help clinical better assess patient prognosis, evaluate the feasibility of immunotherapy in advanced patients, and provide clinical decision support.

اسأل الذكاء الاصطناعي

Bookmark