Deep learning prediction of overall survival in glioblastoma patients using pre-chemoradiotherapy MRI and clinical data
Abstract
Purpose: Glioblastoma (GBM) exhibits variable treatment response and patients shown a median survival of 15 months. A major challenge lies in the difficulty of reliably assessing treatment response at an early stage, as it can usually only be evaluated on anatomical MRI performed up to three months after the start of treatment, when early interpretation may be complicated by the risk of pseudoprogression. Accurately predicting short-term and long-term survivors before radiotherapy and chemotherapy is therefore crucial. The objective of this study is to develop an AI model designed to predict survival outcomes based exclusively on pre-chemoradiotherapy MRI and clinical data. Material and methods: A total of 1,575 retrospective T1-Gd brain images were obtained from 175 patients treated for GBM between 2018 and 2023. A ResNet-51Q model pretrained on ImageNet was fine-tuned on prechemoradiotherapy MRI using transfer learning. To incorporate clinical data, deep hybrid learning (DHL) models were trained. Results: At patient-level, the AI model achieved 81.08% (CI 95%: 67.57-91.89), 68.42% (CI 95%: 47.06-88.89) and 94.44% (CI 95%: 81.82-1.00) for accuracy, sensitivity, and specificity, respectively, for the classification of short-term and long-term survivors using only pre-chemoradiotherapy MRI. At patient-level, the three-class model using only pre-chemoradiotherapy MRI, achieved 87.18% (CI 95%: 76.92-97.44), 87.18% (CI 95%: 76.68-96.97), and 93.59% (CI 95%: 88.03-98.41) for accuracy, sensitivity, and specificity, respectively. In comparison at slice-level, the three-class model using only prechemoradiotherapy MRI, achieved 81.77% (CI 95%: 70.66-91.45), 81.77% (CI 95%: 71.07-91.33), and 90.88% (CI 95%: 85.25-95.74) for accuracy, sensitivity, and specificity, respectively. In comparison the DHL model with clinical data achieved an accuracy of 84.62% (CI 95%: 71.79-94.87), a sensitivity of 84.62% (CI 95%: 72.54-95.24) and a specificity of 92.31% (CI 95%: 86.07-97.53) and 76.32% (CI 95%: 63.16-89.47), 76.11% (CI 95%: 61.63-88.75) and 92.06% (CI 95%: 87.51-96.23) for four overall survival classification. For multiclass tasks, metrics were calculated using a macro-averaged approach. Conclusion: The combination of pre-chemoradiotherapy MRI and clinical data using the DHL model for early survival prediction; however, adding clinical variables yielded comparable prognostic performance rather than a demonstrable enhancement over imaging features alone. The use of AI models to predict survival outcome in GBM from pre-chemoradiotherapy data may support pre-chemoradiotherapy prognostic stratification.
Related
- Pericyte-derived cancer-associated fibroblasts correlate with poor survival and are enriched after chemoradiotherapy in glioblastoma
- Prediction Model for Detecting Active Pulmonary Tuberculosis in Patients With Head and Neck Cancer Prior to Concurrent Chemoradiotherapy
- Laparoscopic para-aortic and pelvic lymphadenectomy before chemoradiotherapy was not associated with improved survival in patients with FIGO stage IIB-IIIC cervical cancer: a single-center retrospective study.
- DeepOSSA: a deep learning framework for personalized survival prediction in osteosarcoma patients
- Fractional tumor burden refines prognostic stratification beyond MGMT status in glioblastoma after chemoradiotherapy
BibTeX
@article{moreau2026deep,
title = {{Deep learning prediction of overall survival in glioblastoma patients using pre-chemoradiotherapy MRI and clinical data}},
author = {Noémie N Moreau and Alexis Desmonts and Cyril Jaudet and Thomas Leleu and Alexandre G. Leclercq and Carole Brunaud and Dinu Stefan and Samuel Valable and Alexis Lechervy and Aurélien Corroyer-Dulmont},
journal = {Frontiers in Radiology},
year = {2026},
month = sep,
doi = {10.3389/fradi.2026.1963539},
url = {https://normandie-univ.hal.science/hal-05796625v1},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Deep learning prediction of overall survival in glioblastoma patients using pre-chemoradiotherapy MRI and clinical data
AU - Noémie N Moreau
AU - Alexis Desmonts
AU - Cyril Jaudet
AU - Thomas Leleu
AU - Alexandre G. Leclercq
AU - Carole Brunaud
AU - Dinu Stefan
AU - Samuel Valable
AU - Alexis Lechervy
AU - Aurélien Corroyer-Dulmont
PY - 2026
DA - 2026/09/30
JO - Frontiers in Radiology
DO - 10.3389/fradi.2026.1963539
UR - https://normandie-univ.hal.science/hal-05796625v1
AB - Purpose: Glioblastoma (GBM) exhibits variable treatment response and patients shown a median survival of 15 months. A major challenge lies in the difficulty of reliably assessing treatment response at an early stage, as it can usually only be evaluated on anatomical MRI performed up to three months after the start of treatment, when early interpretation may be complicated by the risk of pseudoprogression. Accurately predicting short-term and long-term survivors before radiotherapy and chemotherapy is therefore crucial. The objective of this study is to develop an AI model designed to predict survival outcomes based exclusively on pre-chemoradiotherapy MRI and clinical data. Material and methods: A total of 1,575 retrospective T1-Gd brain images were obtained from 175 patients treated for GBM between 2018 and 2023. A ResNet-51Q model pretrained on ImageNet was fine-tuned on prechemoradiotherapy MRI using transfer learning. To incorporate clinical data, deep hybrid learning (DHL) models were trained. Results: At patient-level, the AI model achieved 81.08% (CI 95%: 67.57-91.89), 68.42% (CI 95%: 47.06-88.89) and 94.44% (CI 95%: 81.82-1.00) for accuracy, sensitivity, and specificity, respectively, for the classification of short-term and long-term survivors using only pre-chemoradiotherapy MRI. At patient-level, the three-class model using only pre-chemoradiotherapy MRI, achieved 87.18% (CI 95%: 76.92-97.44), 87.18% (CI 95%: 76.68-96.97), and 93.59% (CI 95%: 88.03-98.41) for accuracy, sensitivity, and specificity, respectively. In comparison at slice-level, the three-class model using only prechemoradiotherapy MRI, achieved 81.77% (CI 95%: 70.66-91.45), 81.77% (CI 95%: 71.07-91.33), and 90.88% (CI 95%: 85.25-95.74) for accuracy, sensitivity, and specificity, respectively. In comparison the DHL model with clinical data achieved an accuracy of 84.62% (CI 95%: 71.79-94.87), a sensitivity of 84.62% (CI 95%: 72.54-95.24) and a specificity of 92.31% (CI 95%: 86.07-97.53) and 76.32% (CI 95%: 63.16-89.47), 76.11% (CI 95%: 61.63-88.75) and 92.06% (CI 95%: 87.51-96.23) for four overall survival classification. For multiclass tasks, metrics were calculated using a macro-averaged approach. Conclusion: The combination of pre-chemoradiotherapy MRI and clinical data using the DHL model for early survival prediction; however, adding clinical variables yielded comparable prognostic performance rather than a demonstrable enhancement over imaging features alone. The use of AI models to predict survival outcome in GBM from pre-chemoradiotherapy data may support pre-chemoradiotherapy prognostic stratification.
SN - 2673-8740
ER -