Multimodal deep learning improves recurrence risk prediction in pediatric low-grade gliomas
Neuro-Oncology · 2025
DOI: 10.1093/neuonc/noae173 ↗Kurz gefasst
Fachartikel in der Zeitschrift Neuro-Oncology, 2025. Verfasst von Maryamalsadat Mahootiha und 22 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Medicine, University of Oslo, Oslo, Norway. Hauptthemen laut MEDLINE: Deep Learning, Glioma, Brain Neoplasms, Neoplasm Recurrence, Local. Die Arbeit wurde bisher 30-mal zitiert (Crossref) und nennt 55 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NCI NIH HHS, NIH HHS, NIDCR NIH HHS.
Abstract (Originalsprache)
Background
Postoperative recurrence risk for pediatric low-grade gliomas (pLGGs) is challenging to predict by conventional clinical, radiographic, and genomic factors. We investigated if deep learning (DL) of magnetic resonance imaging (MRI) tumor features could improve postoperative pLGG risk stratification.
Methods
We used a pretrained DL tool designed for pLGG segmentation to extract pLGG imaging features from preoperative T2-weighted MRI from patients who underwent surgery (DL-MRI features). Patients were pooled from 2 institutions: Dana Farber/Boston Children’s Hospital (DF/BCH) and the Children’s Brain Tumor Network (CBTN). We trained 3 DL logistic hazard models to predict postoperative event-free survival (EFS) probabilities with (1) clinical features, (2) DL-MRI features, and (3) multimodal (clinical and DL-MRI features). We evaluated the models with a time-dependent Concordance Index (Ctd) and risk group stratification with Kaplan–Meier plots and log-rank tests. We developed an automated pipeline integrating pLGG segmentation and EFS prediction with the best model.
Results
Of the 396 patients analyzed (median follow-up: 85 months, range: 1.5–329 months), 214 (54%) underwent gross total resection and 110 (28%) recurred. The multimodal model improved EFS prediction compared to the DL-MRI and clinical models (Ctd: 0.85 (95% CI: 0.81–0.93), 0.79 (95% CI: 0.70–0.88), and 0.72 (95% CI: 0.57–0.77), respectively). The multimodal model improved risk-group stratification (3-year EFS for predicted high-risk: 31% versus low-risk: 92%, P < .0001).
Conclusions
DL extracts imaging features that can inform postoperative recurrence prediction for pLGG. Multimodal DL improves postoperative risk stratification for pLGG and may guide postoperative decision-making. Larger, multicenter training data may be needed to improve model generalizability.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Faculty of Medicine, University of Oslo, Oslo, Norway.
- The Intervention Centre, Oslo University Hospital, Oslo, Norway.
- Department of Radiation Oncology, Dana-Farber Cancer Institute, Brigham and Women's Hospital, Boston Children's Hospital, Harvard Medical School, Boston, Massachusetts, USA.
- Artificial Intelligence in Medicine (AIM) Program, Mass General Brigham, Harvard Medical School, Boston, Massachusetts, USA.
- Department of Radiology, Boston Children's Hospital, Harvard Medical School, Boston, Massachusetts, USA.
- Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA.
ORCID-Profile: Maryamalsadat Mahootiha, Ali Nabavizadeh, Pratiti Bandopadhayay, Daphne Haas-Kogan
Förderung
- NCI NIH HHS
- NIH HHS
- NIDCR NIH HHS
- National Institutes of Health
- National Cancer Institute
Zitieren
APA
Mahootiha, M., Tak, D., Ye, Z., Zapaishchykova, A., Likitlersuang, J., Climent Pardo, J. C., Boyd, A., Vajapeyam, S., Chopra, R., Prabhu, S. P., Liu, K. X., Elhalawani, H., Nabavizadeh, A., Familiar, A., Mueller, S., Aerts, H. J. W. L., Bandopadhayay, P., Ligon, K. L., Haas-Kogan, D., …, & Kann, B. H. (2025). Multimodal deep learning improves recurrence risk prediction in pediatric low-grade gliomas. Neuro-Oncology. https://doi.org/10.1093/neuonc/noae173
Vancouver
Mahootiha M, Tak D, Ye Z, Zapaishchykova A, Likitlersuang J, Climent Pardo JC, et al. Multimodal deep learning improves recurrence risk prediction in pediatric low-grade gliomas. Neuro-Oncology. 2025. doi:10.1093/neuonc/noae173
BibTeX
@article{Mahootiha2025,
author = {Mahootiha, Maryamalsadat and Tak, Divyanshu and Ye, Zezhong and Zapaishchykova, Anna and Likitlersuang, Jirapat and Climent Pardo, Juan Carlos and Boyd, Aidan and Vajapeyam, Sridhar and Chopra, Rishi and Prabhu, Sanjay P and Liu, Kevin X and Elhalawani, Hesham and Nabavizadeh, Ali and Familiar, Ariana and Mueller, Sabine and Aerts, Hugo J W L and Bandopadhayay, Pratiti and Ligon, Keith L and Haas-Kogan, Daphne and Poussaint, Tina Y and Qadir, Hemin Ali and Balasingham, Ilangko and Kann, Benjamin H},
title = {Multimodal deep learning improves recurrence risk prediction in pediatric low-grade gliomas},
journal = {Neuro-Oncology},
year = {2025},
doi = {10.1093/neuonc/noae173}
}
EUVIMED