Non-invasive decision support for NSCLC treatment using PET/CT radiomics
Wei Mu1, Lei Jiang2, JianYuan Zhang3,4
1Department of Cancer Physiology, H. Lee Moffitt Cancer Center and Research Institute, Tampa, FL, USA.
Abstract:
Two major treatment strategies employed in non-small cell lung cancer, NSCLC, are tyrosine kinase inhibitors, TKIs, and immune checkpoint inhibitors, ICIs. The choice of strategy is based on heterogeneous biomarkers that can dynamically change during therapy. Thus, there is a compelling need to identify comprehensive biomarkers that can be used longitudinally to help guide therapy choice. Herein, we report a 18F-FDG-PET/CT-based deep learning model, which demonstrates high accuracy in EGFR mutation status prediction across patient cohorts from different institutions. A deep learning score (EGFR-DLS) was significantly and positively associated with longer progression free survival (PFS) in patients treated with EGFR-TKIs, while EGFR-DLS is significantly and negatively associated with higher durable clinical benefit, reduced hyperprogression, and longer PFS among patients treated with ICIs. Thus, the EGFR-DLS provides a non-invasive method for precise quantification of EGFR mutation status in NSCLC patients, which is promising to identify NSCLC patients sensitive to EGFR-TKI or ICI-treatments.
Insights
A novel deep learning model accurately predicts EGFR mutation status in non-small cell lung cancer (NSCLC) using 18F-FDG-PET/CT scans. This non-invasive EGFR deep learning score (EGFR-DLS) helps guide personalized treatment with tyrosine kinase inhibitors (TKIs) or immune checkpoint inhibitors (ICIs).
Area of Science:
- Oncology
- Radiology
- Artificial Intelligence in Medicine
Background:
- Non-small cell lung cancer (NSCLC) treatment relies on biomarkers that can change during therapy.
- Current biomarkers necessitate invasive methods and lack longitudinal tracking for treatment guidance.
- There is a critical need for non-invasive, dynamic biomarkers to optimize NSCLC therapeutic strategies.
Purpose of the Study:
- To develop and validate a deep learning model for predicting EGFR mutation status in NSCLC patients.
- To assess the utility of the developed deep learning score (EGFR-DLS) in guiding treatment decisions for EGFR-TKI and ICI therapies.
- To establish a non-invasive method for longitudinal assessment of biomarkers in NSCLC.
Main Methods:
- Utilized 18F-FDG-PET/CT imaging data to train a deep learning model for EGFR mutation status prediction.
- Validated the model's accuracy across diverse patient cohorts from multiple institutions.
- Correlated the derived deep learning score (EGFR-DLS) with treatment outcomes, including progression-free survival (PFS) and clinical benefit, for patients receiving EGFR-TKIs and ICIs.
Main Results:
- The deep learning model achieved high accuracy in predicting EGFR mutation status.
- A higher EGFR-DLS was significantly associated with longer PFS in patients treated with EGFR-TKIs.
- Conversely, a higher EGFR-DLS was negatively associated with durable clinical benefit and positively associated with reduced hyperprogression and longer PFS in patients treated with ICIs.
Conclusions:
- The 18F-FDG-PET/CT-based deep learning model provides a non-invasive and accurate method for quantifying EGFR mutation status in NSCLC.
- The EGFR-DLS shows promise in identifying NSCLC patients likely to benefit from specific treatments, such as EGFR-TKIs or ICIs.
- This approach offers a valuable tool for longitudinal patient monitoring and personalized therapy selection in NSCLC management.
