Glioblastoma survival prediction through MRI and clinical data integration with transfer learning
Open Access
- 4 December 2025
- journal article
- research article
- Published by Springer Nature in International Journal of Computer Assisted Radiology and Surgery
- Vol. 21 (3) , 473-482
Abstract
Purpose: 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. Methods: 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. Results: 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. Conclusion: 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.Keywords
Funding Information
- Ministero della Salute (T4-AN.09)
This publication has 28 references indexed in Scilit:
- Time-to-event overall survival prediction in glioblastoma multiforme patients using magnetic resonance imaging radiomicsLa radiologia medica, 2023
- An MRI radiomics approach to predict survival and tumour-infiltrating macrophages in gliomasBrain, 2022
- Uncertainty-Driven Refinement of Tumor-Core Segmentation Using 3D-to-2D Networks with Label Uncertainty2021
- Context aware deep learning for brain tumor segmentation, subtype classification, and survival prediction using radiology imagesScientific Reports, 2020
- Automated brain extraction of multisequence MRI using artificial neural networksHuman Brain Mapping, 2019
- Artificial intelligence, machine (deep) learning and radio(geno)mics: definitions and nuclear medicine imaging applicationsEuropean Journal of Nuclear Medicine and Molecular Imaging, 2019
- Clinical practice guidelines for the diagnosis and treatment of adult diffuse glioma‐related epilepsyCancer Medicine, 2019
- 3D MRI Brain Tumor Segmentation Using Autoencoder Regularization2019
- IDH1 mutation is sufficient to establish the glioma hypermethylator phenotypeNature, 2012
- MGMTGene Silencing and Benefit from Temozolomide in GlioblastomaNew England Journal of Medicine, 2005