Keywords: Tumors (Post-Treatment), Treatment Response
Motivation: This study addresses the challenge of non-invasively distinguishing treatment-induced effects (TxE) from tumor recurrence (rTumor) in glioma patients.
Goal(s): The goal is to enhance classification accuracy by integrating multi-parametric MRI and MR spectroscopy data into a multi-modal machine learning framework.
Approach: Using ensemble classifiers and oversampling techniques, the combined model demonstrates superior discriminative power, improving generalizability and reliability over individual data models, underscoring the potential for more reliable clinical decision-making.
Results: The two data modalities offer complementary insights, as reflected in the feature importance across classifiers. Results show an increase in AUC scores of up to 38%.
Impact: Our integrated framework improves differentiation of TxE from rTumor, reducing misdiagnosis risk and guiding treatment decisions. Future work could explore personalized treatment strategies based on imaging biomarkers, improving patient outcomes. Researchers gain avenues to optimize multi-modal ML approaches in neuro-oncology.
How to access this content:
For one year after publication, abstracts and videos are only open to registrants of this annual meeting. Registrants should use their existing login information. Non-registrant access can be purchased via the ISMRM E-Library.
After one year, current ISMRM & ISMRT members get free access to both the abstracts and videos. Non-members and non-registrants must purchase access via the ISMRM E-Library.
After two years, the meeting proceedings (abstracts) are opened to the public and require no login information. Videos remain behind password for access by members, registrants and E-Library customers.
Keywords