2023 World Conference on Lung Cancer (Posters)-P2.09. MRI Radiomics Approach to Predict the Intracranial Efficacy of the Third Generation EGFR-TKI Osimertinib in NSCLC Patients with Brain Metastases

P2.09. MRI Radiomics Approach to Predict the Intracranial Efficacy of the Third Generation EGFR-TKI Osimertinib in NSCLC Patients with Brain Metastases - PDF(Slides)

Back to course

Pdf Summary

Researchers investigated the use of brain MRI radiomics to predict the effectiveness of the third-generation EGFR-TKI osimertinib in treating brain metastases in non-small cell lung cancer (NSCLC) patients. Osimertinib is known to be more effective than earlier generation EGFR-TKIs in treating brain metastases due to its ability to penetrate the blood-brain barrier. However, not all patients with brain metastases benefit from it, and there are currently no effective tools to predict its efficacy.<br /><br />The study involved 60 NSCLC patients with brain metastases who received osimertinib as second-line treatment. The researchers used tumor delineation, image preprocessing, and radiomics extraction techniques to analyze the MRI images. They employed a 5-fold cross-validation strategy and applied various feature selectors and machine learning classifiers to construct radiomic models.<br /><br />After analysis, 42 radiomics features were identified. The model constructed using the mRMR feature selector and stepwise logistic regression classifier achieved the highest predictive accuracy, with an area under the receiver operating characteristic curve (AUC) of 0.879 in the training cohort and 0.786 in the validation cohort. In comparison, a clinical-MRI morphological model that included age, ring enhancement, and peritumoral edema had a lower AUC.<br /><br />The radiomic model also performed well in terms of calibration and decision curves. Using a radiomic score of 199 as a cut-off, patients were divided into two groups with significantly different median intracranial progression-free survival.<br /><br />Overall, this study demonstrates that the MRI radiomic model shows promise in predicting the effectiveness of osimertinib in NSCLC patients with brain metastases. The model could potentially assist clinicians in making personalized treatment strategies.

Asset Subtitle

Xin Tang

Meta Tag

Speaker Xin Tang

Topic Metastatic NSCLC: Targeted Therapy - EGFR/HER2

Keywords

brain MRI radiomics

third-generation EGFR-TKI osimertinib

treating brain metastases

non-small cell lung cancer

NSCLC patients

blood-brain barrier

predictive accuracy

radiomic model

intracranial progression-free survival

personalized treatment strategies