Keywords: Diagnosis/Prediction, Diagnosis/Prediction
Motivation: Glioblastomas are aggressive, heterogeneous brain tumors. Accurate prognosis is vital for personalized treatment, but the complexity and variability of gliomas complicate predictions. Developing an automated deep learning model is essential for reliably predicting glioma outcomes.
Goal(s): Integrating multiple MRI modalities aims to capture comprehensive tumor characteristics, enabling more accurate and reliable glioma prognosis predictions.
Approach: A multi-CNN parallel neural network was designed to fuse four MRI modalities—ADC, T1c, T2, and FLAIR. This deep network integrates modality-specific features, leveraging complementary information to improve prediction accuracy.
Results: The fusion model significantly outperformed single-modality models, achieving an AUC of 0.990 in training and 0.949 in testing.
Impact: The fusion model enhances glioma prognosis prediction by integrating information from multiple MRI modalities, achieving higher accuracy than single-modality approaches. This model can improve personalized treatment strategies and decision-making.
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