# Multimodal Deep Learning to Differentiate Tumor Recurrence from Treatment Effect in Human Glioblastoma

## TL;DR

This study explores the use of dynamic FDG PET combined with MRI and deep learning to improve differentiation between tumor recurrence and treatment effects in glioblastoma, showing promising accuracy improvements.

## Contribution

It introduces a novel application of convolutional neural networks with dynamic PET and MRI features for better classification of tumor status in glioblastoma patients.

## Key findings

- Ki features achieved 0.71 accuracy alone.
- Combining MR and Ki features increased accuracy to 0.74.
- Dynamic PET features enhance differentiation between TP and TN.

## Abstract

Differentiating tumor progression (TP) from treatment-related necrosis (TN) is critical for clinical management decisions in glioblastoma (GBM). Dynamic FDG PET (dPET), an advance from traditional static FDG PET, may prove advantageous in clinical staging. dPET includes novel methods of a model-corrected blood input function that accounts for partial volume averaging to compute parametric maps that reveal kinetic information. In a preliminary study, a convolution neural network (CNN) was trained to predict classification accuracy between TP and TN for $35$ brain tumors from $26$ subjects in the PET-MR image space. 3D parametric PET Ki (from dPET), traditional static PET standardized uptake values (SUV), and also the brain tumor MR voxels formed the input for the CNN. The average test accuracy across all leave-one-out cross-validation iterations adjusting for class weights was $0.56$ using only the MR, $0.65$ using only the SUV, and $0.71$ using only the Ki voxels. Combining SUV and MR voxels increased the test accuracy to $0.62$. On the other hand, MR and Ki voxels increased the test accuracy to $0.74$. Thus, dPET features alone or with MR features in deep learning models would enhance prediction accuracy in differentiating TP vs TN in GBM.