Related Experiment Video
Updated: Jul 4, 2025
Modeling Brain Metastases Through Intracranial Injection and Magnetic Resonance Imaging
Published on: June 7, 2020
MRI radiomics for predicting intracranial progression in non-small-cell lung cancer patients with brain metastases
1Department of Radiology, and Functional and Molecular Imaging Key Laboratory of Sichuan Province, West China Hospital of Sichuan University, Chengdu, China; Huaxi MR Research Center (HMRRC), West China Hospital of Sichuan University, Chengdu, China; Research Unit of Psychoradiology, Chinese Academy of Medical Sciences, Chengdu, China.
Predicting intracranial progression in non-small-cell lung cancer (NSCLC) patients with brain metastases (BMs) is possible. A model combining EGFR-19del mutation, third-generation tyrosine kinase inhibitor (TKI) treatment, and radiomics score shows strong predictive value.
Area of Science:
- Oncology
- Radiology
- Medical Imaging
Background:
- Non-small-cell lung cancer (NSCLC) patients with brain metastases (BMs) often experience intracranial progression (IP) after EGFR-TKI treatment.
- Predicting IP is crucial for optimizing treatment strategies and improving patient outcomes.
Purpose of the Study:
- To identify clinical and MRI radiomics predictors for intracranial progression (IP) in NSCLC patients with BMs receiving first-line EGFR-TKI therapy.
- To develop and evaluate a predictive model for IP.
Main Methods:
- Seventy EGFR-mutated NSCLC patients with BMs were analyzed.
- Radiomics features were extracted from pre-treatment contrast-enhanced T1-weighted MRI.
- A radiomics score (rad-score) and mean rad-score per patient were calculated.
- Logistic regression identified independent predictors, and prediction models were constructed and validated.
Main Results:
- 33 patients (47.1%) developed IP.
- EGFR-19del mutation, third-generation TKI treatment, and mean rad-score were independent predictors of IP.
- A combined model integrating these factors achieved an AUC of 0.86 in the training set and 0.84 in the validation set.
Conclusions:
- A predictive model combining EGFR-19del mutation, third-generation TKI treatment, and mean rad-score demonstrates good predictive value for IP.
- This model can aid in managing NSCLC patients with BMs undergoing EGFR-TKI therapy.
