Multimodal Deep Learning Improves Recurrence Risk Prediction in Pediatric Low-Grade Gliomas

Maryamalsadat Mahootiha; Divyanshu Tak; Zezhong Ye; Anna Zapaishchykova; Jirapat Likitlersuang; Juan Carlos Climent Pardo; Aidan Boyd; Sridhar Vajapeyam; Rishi Chopra; Sanjay P Prabhu; Kevin X Liu; Hesham Elhalawani; Ali Nabavizadeh; Ariana Familiar; Sabine Mueller; Hugo J W L Aerts; Pratiti Bandopadhayay; Keith L Ligon; Daphne Haas-Kogan; Tina Y Poussaint; Hemin Ali Qadir; Ilangko Balasingham; Benjamin H Kann

doi:10.1093/neuonc/noae173

Multimodal Deep Learning Improves Recurrence Risk Prediction in Pediatric Low-Grade Gliomas

Neuro Oncol. 2024 Aug 30:noae173. doi: 10.1093/neuonc/noae173. Online ahead of print.

Authors

Maryamalsadat Mahootiha^{1

2

3

4}, Divyanshu Tak^{1

2}, Zezhong Ye^{1

2}, Anna Zapaishchykova^{1

2}, Jirapat Likitlersuang^{1

2}, Juan Carlos Climent Pardo^{1

2}, Aidan Boyd^{1

2}, Sridhar Vajapeyam⁵, Rishi Chopra^{1

2}, Sanjay P Prabhu⁵, Kevin X Liu², Hesham Elhalawani², Ali Nabavizadeh^{6

7}, Ariana Familiar^{6

8}, Sabine Mueller^{9

10

11}, Hugo J W L Aerts^{1

2

12

13}, Pratiti Bandopadhayay¹⁴, Keith L Ligon¹⁵, Daphne Haas-Kogan², Tina Y Poussaint⁵, Hemin Ali Qadir³, Ilangko Balasingham^{3

16}, Benjamin H Kann^{1

2}

Affiliations

¹ Artificial Intelligence in Medicine (AIM) Program, Mass General Brigham, Harvard Medical School, Boston, MA, USA.
² Department of Radiation Oncology, Dana-Farber Cancer Institute | Brigham and Women's Hospital | Boston Children's Hospital, Harvard Medical School, Boston, MA, USA.
³ The Intervention Centre, Oslo University Hospital, Oslo, Norway.
⁴ Faculty of Medicine, University of Oslo, Oslo, Norway.
⁵ Department of Radiology, Boston Children's Hospital, Harvard Medical School, Boston, MA, USA.
⁶ Center for Data-Driven Discovery in Biomedicine (D3b), Children's Hospital of Philadelphia, Philadelphia, PA, USA.
⁷ Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA.
⁸ Department of Neurosurgery, Children's Hospital of Philadelphia, Philadelphia, PA, USA.
⁹ Department of Neurology, University of California San Francisco, San Francisco, CA. USA.
¹⁰ Department of Pediatrics, University of California San Francisco, San Francisco, CA, USA.
¹¹ Department of Neurological Surgery, University of California San Francisco, San Francisco, CA, USA.
¹² Department of Radiology, Brigham and Women's Hospital, Dana-Farber Cancer Institute, Harvard Medical School, Boston, MA, USA.
¹³ Radiology and Nuclear Medicine, CARIM & GROW, Maastricht University, Maastricht, the Netherlands.
¹⁴ Department of Pediatric Oncology, Dana-Farber Cancer Institute, Boston Children's Hospital, Harvard Medical School, Boston, MA, USA.
¹⁵ Department of Pathology, Dana-Farber Cancer Institute, Boston Children's Hospital, Harvard Medical School, Boston, A, USA.
¹⁶ Department of Electronic Systems, Norwegian University of Science and Technology, Trondheim, Norway.

PMID: 39211987
DOI: 10.1093/neuonc/noae173

Abstract

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 of MRI tumor features could improve postoperative pLGG risk stratification.

Methods: We used pre-trained deep learning (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 two institutions: Dana Farber/Boston Children's Hospital (DF/BCH) and the Children's Brain Tumor Network (CBTN). We trained three 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<0.0001).

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.

Keywords: MRI; cancer prognosis; deep learning; event-free survival; pediatric low-grade glioma.