1. Home
  2. Deep Learning for Automated Ventricle and Periventricular Space Segmentation on CT and T1CE MRI in Neuro-Oncology Patients

Deep Learning for Automated Ventricle and Periventricular Space Segmentation on CT and T1CE MRI in Neuro-Oncology Patients

Authors: 
Mart Wubbels, Marvin Ribeiro, Jelmer M. Wolterink, Wouter van Elmpt, Inge Compter, David Hofstede, Nikolina E. Birimac, Femke Vaassen, Kati Palmgren, Hendrik H. G. Hansen, Hiska L. van der Weide, Charlotte L. Brouwer, Miranda C. A. Kramer, Daniëlle B. P. Eekers, Catharina M. L. Zegers
Paper's DOI: 
10.3390/cancers17101598
Year: 
2025
Wubbels at al. developed and validate a deep learning model to automatically segment the ventricles and periventricular space on CT and MRI scans to improve treatment planning for patients receiving intracranial radiotherapy. The resulting model (nnU-Net) was tested alongside an existing model (SynthSeg) to see which performed better at segmenting the brain ventricles. The results showed that the new model, nnU-Net, performed more accurately and was preferred by radiotherapy technicians. These findings could improve the process of contouring organs at risk in brain cancer patients undergoing radiation therapy. To aid the use of the developed model, we provide additional documentation /code of the model which can be found in GitLab: https://gitlab.com/ventricle_segmentation/nnunet-ventricle-segmentation [img]/system/files/publications/2025_Mart-Wubbels_Deep-Learning-for-Automated-Ventricle-and-Periventricular-Space-Segmentation_1375x928.png[/img]