# Glioblastoma survival prediction through MRI and clinical data integration with transfer learning

## TL;DR

This study uses deep learning and MRI data to predict survival in glioblastoma patients, outperforming traditional methods.

## Contribution

A novel deep learning framework integrating MRI and clinical data for improved glioblastoma survival prediction.

## Key findings

- A deep learning model achieved strong OS prediction metrics (F1 = 0.71, AUC = 0.74) using multimodal MRI data.
- Integration of encoder-derived features with clinical variables improved performance over traditional radiomics.
- The framework demonstrated robustness across different datasets and modality configurations.

## Abstract

Accurate prediction of overall survival (OS) in glioblastoma patients is critical for advancing personalized treatments and improving clinical trial design. Conventional radiomics approaches rely on manually engineered features, which limit their ability to capture complex, high-dimensional imaging patterns. This study employs a deep learning architecture to process MRI data for automated glioma segmentation and feature extraction, leveraging high-level representations from the encoder’s latent space.

Multimodal MRI data from the BraTS2020 dataset and a proprietary dataset from Fondazione IRCCS Istituto Neurologico Carlo Besta (Milan, Italy) were processed independently using a U-Net-like model pre-trained on BraTS2018 and fine-tuned on BraTS2020. Features extracted from the encoder’s latent space represented hierarchical imaging patterns. These features were combined with clinical variable (patient’s age) and reduced via principal component analysis (PCA) to enhance computational efficiency. Machine learning classifiers—including random forest, XGBoost, and a fully connected neural network—were trained on the reduced feature vectors for OS classification.

In the four-modality BraTS4CH setting, the multi-layer perceptron achieved the best performance (F1 = 0.71, AUC = 0.74, accuracy = 0.71). When limited to two modalities on BraTS2020 (BraTS2CH), MLP again led (F1 = 0.67, AUC = 0.70, accuracy = 0.67). On the IRCCS Besta two-modality cohort (Besta2CH), XGBoost produced the highest F1-score and accuracy (F1 = 0.65, accuracy = 0.66), while MLP obtained the top AUC (0.70). These results are competitive with—and in some metrics exceed—state-of-the-art reports, demonstrating the robustness and scalability of our automated framework relative to traditional radiomics and AI-driven approaches.

Integrating encoder-derived features from multimodal MRI data with clinical variables offers a scalable and effective approach for OS prediction in glioblastoma patients. This study demonstrates the potential of deep learning to address traditional radiomics limitations, paving the way for more precise and personalized prognostic tools.