EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Combined molecular subtyping, grading, and segmentation of glioma using multi-task deep learning

Sebastian R van der Voort iD, Fatih Incekara, Maarten M J Wijnenga, Georgios Kapsas iD, Renske Gahrmann iD, Joost W Schouten, Rishi Nandoe Tewarie, Geert J Lycklama, Philip C De Witt Hamer, Roelant S Eijgelaar iD, Pim J French, Hendrikus J Dubbink und 5 weitere

Neuro-Oncology · 14.02.2023 · 25 (2) · 279-289

DOI: 10.1093/neuonc/noac166 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Neuro-Oncology, online erschienen am 05.07.2022. Verfasst von Sebastian R van der Voort und 16 weiteren Autor:innen. Beteiligte Einrichtung: Biomedical Imaging Group Rotterdam, Department of Radiology and Nuclear Medicine, Erasmus MC University Medical Centre Rotterdam, Rotterdam, the Neth…. Hauptthemen laut MEDLINE: Brain Neoplasms, Deep Learning, Glioma. Die Arbeit wurde bisher 175-mal zitiert (Crossref) und nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Dutch Cancer Society, European Union’s Horizon 2020 Research and Innovation Programme.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Accurate characterization of glioma is crucial for clinical decision making. A delineation of the tumor is also desirable in the initial decision stages but is time-consuming. Previously, deep learning methods have been developed that can either non-invasively predict the genetic or histological features of glioma, or that can automatically delineate the tumor, but not both tasks at the same time. Here, we present our method that can predict the molecular subtype and grade, while simultaneously providing a delineation of the tumor.

Methods

We developed a single multi-task convolutional neural network that uses the full 3D, structural, preoperative MRI scans to predict the IDH mutation status, the 1p/19q co-deletion status, and the grade of a tumor, while simultaneously segmenting the tumor. We trained our method using a patient cohort containing 1508 glioma patients from 16 institutes. We tested our method on an independent dataset of 240 patients from 13 different institutes.

Results

In the independent test set, we achieved an IDH-AUC of 0.90, an 1p/19q co-deletion AUC of 0.85, and a grade AUC of 0.81 (grade II/III/IV). For the tumor delineation, we achieved a mean whole tumor Dice score of 0.84.

Conclusions

We developed a method that non-invasively predicts multiple, clinically relevant features of glioma. Evaluation in an independent dataset shows that the method achieves a high performance and that it generalizes well to the broader clinical population. This first-of-its-kind method opens the door to more generalizable, instead of hyper-specialized, AI methods.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Brain NeoplasmsDeep LearningGliomaHumansMagnetic Resonance ImagingChromosome AberrationsIsocitrate DehydrogenaseMutationNeoplasm Grading

Stichwörter der Autor:innen

deep learninggliomamulti-taskradiomicssegmentation

Substanzen

Isocitrate Dehydrogenase

Autor:innen und Institutionen

  • Biomedical Imaging Group Rotterdam, Department of Radiology and Nuclear Medicine, Erasmus MC University Medical Centre Rotterdam, Rotterdam, the Netherlands.
  • Department of Radiology and Nuclear Medicine, Erasmus MC University Medical Centre Rotterdam, Rotterdam, the Netherlands.
  • Department of Neurosurgery, Brain Tumor Center, Erasmus MC University Medical Centre Rotterdam, Rotterdam, the Netherlands.
  • Department of Neurology, Brain Tumor Center, Erasmus MC Cancer Institute, Rotterdam, the Netherlands.
  • Department of Neurosurgery, Haaglanden Medical Center, the Hague, the Netherlands.
  • Department of Radiology, Haaglanden Medical Center, the Hague, the Netherlands.

ORCID-Profile: Sebastian R van der Voort, Georgios Kapsas, Renske Gahrmann, Roelant S Eijgelaar, Wiro J Niessen, Martin J van den Bent, Marion Smits, Stefan Klein

Förderung

  • Dutch Cancer Society
  • European Union’s Horizon 2020 Research and Innovation Programme

Zitieren

APA

van der Voort, S. R., Incekara, F., Wijnenga, M. M. J., Kapsas, G., Gahrmann, R., Schouten, J. W., Nandoe Tewarie, R., Lycklama, G. J., De Witt Hamer, P. C., Eijgelaar, R. S., French, P. J., Dubbink, H. J., Vincent, A. J. P. E., Niessen, W. J., van den Bent, M. J., Smits, M., & Klein, S. (2023). Combined molecular subtyping, grading, and segmentation of glioma using multi-task deep learning. Neuro-Oncology, 25(2), 279-289. https://doi.org/10.1093/neuonc/noac166

Vancouver

van der Voort SR, Incekara F, Wijnenga MMJ, Kapsas G, Gahrmann R, Schouten JW, et al. Combined molecular subtyping, grading, and segmentation of glioma using multi-task deep learning. Neuro-Oncology. 2023;25(2):279-289. doi:10.1093/neuonc/noac166

BibTeX
@article{vanderVoort2023,
  author = {van der Voort, Sebastian R and Incekara, Fatih and Wijnenga, Maarten M J and Kapsas, Georgios and Gahrmann, Renske and Schouten, Joost W and Nandoe Tewarie, Rishi and Lycklama, Geert J and De Witt Hamer, Philip C and Eijgelaar, Roelant S and French, Pim J and Dubbink, Hendrikus J and Vincent, Arnaud J P E and Niessen, Wiro J and van den Bent, Martin J and Smits, Marion and Klein, Stefan},
  title = {Combined molecular subtyping, grading, and segmentation of glioma using multi-task deep learning},
  journal = {Neuro-Oncology},
  year = {2023},
  volume = {25},
  number = {2},
  pages = {279--289},
  doi = {10.1093/neuonc/noac166}
}
Kostenlos starten →