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

Sebastian R Van der VoortFatih IncekaraMaarten M J WijnengaGeorgios Kapsas Renske GahrmannJoost W SchoutenRishi Nandoe TewarieGeert J LycklamaPhilip C De Witt HamerRoelant Sjouke EijgelaarPim J FrenchHendrikus J DubbinkArnaud J P E VincentWiro J Niessen Martin J Van Den Bent Marion Smits Stefan Klein

Published in: Neuro-oncology (2022)

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.

Keyphrases

deep learning
artificial intelligence
convolutional neural network
palliative care
machine learning