Deep learning (nnUNet) model for the EPTN contouring guidelines for OARs in neuro-oncology

Ana M. Barragán-Montero, Margerie Huet-Dastarac, Dario di Perri, David Hofstede, Nikolina E Birimac, Benjamin Roberfroid, Emilien Quéré, John Lee, Wouter Van Elmpt, Danielle BP Eekers, Catharina M.L.Zegers

 

A representation of a model trained on neurological images to form a contouring atlas

The European Particle Therapy Network (EPTN) has undertaken a major effort to harmonize OAR contouring practices in neuro-oncology. In 2018, EPTN published the first consensus-based guidelines for the delineation of 15 brain OARs (10.17195/candat.2017.08.1), expanded in 2021 to include 10 additional structures (10.17195/candat.2021.02.1). To aid adoption, EPTN also produced explanatory videos (10.17195/candat.2022.02.1), but the broad implementation of these guidelines remains limited due to the complexity and time-consuming contouring. In this context, deep learning (DL) offers a promising solution. Expert-trained DL models can encode complex anatomical knowledge and replicate expert-level contouring.

To this end, an nnUNet architecture has been trained and made public here. The model was trained using a 5-fold cross validation on 74 patients treated at Maastro Clinic, contoured according to the EPTN guidelines. The model receives as input a planning CT scan with intravenous iodine contrast, along with 3T MRI scan gadolinium-enhanced T1-weighted sequence. CT and MR image should be rigidly registered. The output of the model are the 25 OARs defined in the EPTN consensus guidelines.

 

The code to run and pre- / post-process the data from DICOM to nnUNet readable format (nifti) and viceversa is freely available at https://gitlab.com/ai4miro/nnunet_workflow_eptn  

 

Please site as follows:

Ana M. Barragán-Montero, Margerie Huet-Dastarac, Dario di Perri, David Hofstede, Nikolina E Birimac, Benjamin Roberfroid, 
Emilien Quéré, John Lee, Wouter Van Elmpt, Danielle BP Eekers, Catharina M.L.Zegers
Deep learning (nnUNet) model for the EPTN contouring guidelines for OARs in neuro-oncology
CancerData, 2025; doi:10.17195/candat.2025.10.1

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

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

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 (based on 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 nnU-Net-based model, 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 this repository: nnU-Net Ventricle Segmentation (GitLab).

EPTN International Neurological Contouring Atlas (INCA) instruction videos

David Hofstede, Dario Di Perri, Erik Roelofs, Alida Postma, Esther Troost, Daniëlle Eekers
 
Ten new organs at risk (OAR) were recently introduced in the update of the EPTN neurological contouring atlas (Eekers, 2021, doi:10.17195/candat.2021.02.1): amygdala, caudate nucleus, corpus callosum, fornix, macula, optic tract, orbitofrontal cortex, periventricular space, pineal gland, and thalamus. These are thought to be associated with cognition, vision, or radiological changes after irradiation of the brain. Accurate delineation of these OARs on a large scale is essential to gather dosimetric data usable as input for normal tissue complication probability models.
 
In this context, educational movies were developed in order to facilitate the contouring of these OARs and to reduce inter- and intra-individual delineation variability. The movies are designed to be used by all the professionals involved in contouring. Each movie describes the anatomical limits of one of the ten new OARs and provides tips & tricks to help with common difficulties faced during delineation.

Please site this set of instructions as follows:

Hofstede D, Di Perri D, Roelofs E, Postma A, Troost EG, Eekers DBP
EPTN International Neurological Contouring Atlas (INCA) instruction videos
CancerData, 2022; doi:10.17195/candat.2022.02.1

EPTN consensus-based toxicity scoring standard for the follow-up of adult brain and base of skull tumours after radiotherapy

Laurien De Roeck, Hiska L van der Weide, Daniëlle BP Eekers, Erik Roelofs, Esther GC Troost, Maarten Lambrecht

De Roeck et al. have published a guideline for consistent toxicity scoring and follow-up in adult brain tumour patients in consensus with the European Particle Therapy Network (EPTN). The purpose of this framework is to enable the collection of uniform toxicity data of brain tumour patients treated with photon and particle therapy. This will facilitate collaboration and further propel the research field of radiation-induced toxicities relevant for these patients.

 

Please site this table as follows:

Laurien De Roeck, Hiska L van der Weide, Daniëlle BP Eekers, Erik Roelofs, Esther GC Troost, Maarten Lambrecht
EPTN consensus-based toxicity scoring standard for the follow-up of adult brain and base of skull tumours after radiotherapy
CancerData, 2021; doi:10.17195/candat.2021.09.1

EPTN International Neurological Contouring Atlas - 2021 Update

Daniëlle Eekers, Dario Di Perri, Erik Roelofs, Alida Postma, Esther Troost

Eekers et al. have published an international neurological atlas for contouring of organs at risk in consensus with the European Particle Therapy Network (EPTN) in 2018 and an update in 2021. The purpose of this consensus atlas is to decrease inter- and intra-observer variability in delineating OARs relevant for neuro-oncology.

Included are all OARs known to be relevant for radiation-induced toxicity in neuro-oncology: brain, brainstem (midbrain, pons, medulla oblongata), chiasm, cerebellum (anterior & posterior), cochlea, cornea, hippocampus (anterior & posterior), hypothalamus, lens, lacrimal gland, optic nerve, pituitary, skin, and vestibular & semicircular canals. To further facilitate research on cognition, vision and radiological changes after irradiation of the brain, potential clinically-relevant OARs are included: amygdala, caudate nucleus, cerebellum (anterior & posterior), corpus callosum, fornix, macula, optic tract, orbitofrontal cortex, periventricular space (PVS), pineal gland, and thalamus.

We propose this atlas is used in photon and particle therapy in order to derive consistent dosimetric data. When required this atlas will be updated according to new insights.

Three-dimensional delineation of the 25 consensus OARs for neuro-oncology are shown on CT (WW/WL 120/40, 3000/600), 3T MR images, (T1Gd, T2FLAIR 1mm) and 7T MR (MP2RAGE 0.7 mm). All are presented in transversal, sagittal and coronal view.

Please cite this Atlas as follows:

Eekers D, Di Perri D, Roelofs E, Postma A, Troost EG.
EPTN International Neurological Contouring Atlas - 2021 Update
CancerData, 2021. doi:10.17195/candat.2021.02.1

 

Optimization of Brain and Head & Neck Radiotherapy

Daniëlle BP Eekers

The aim of this thesis is to further optimise radiation therapy of Brain and Head & Neck cancer by reducing the dose to the healthy surrounding tissue, so called organs at risk (OARs), leading to a reduction in side effects.

Different treatment techniques for photon and particle (e.g. proton) therapy are compared for multiple tumour sites. Furthermore, tools for consistent contouring and dose prescription are presented in close collaboration with the European Particle Therapy Network (EPTN).

 

EPTN consensus-based guideline for the tolerance dose per fraction of organs at risk in the brain

Daniëlle BP Eekers, Maarten Lambrecht, Petra De Witt Nyström, Ans Swinnen, Frederik WR Wesseling, Erik Roelofs, Esther GC Troost

 

EPTN consensus-based guideline for the tolerance dose per fraction of organs at risk in the brain

In collaboration with the European Particle Therapy Network, a consensus table of tolerance doses for Organs at Risk in the brain was created. These values were all defined as a near maximum EQD2 values. Using the linear quadratic formula the doses are recalculated depending on the number of fractions.

 

Please site this table as follows:

Eekers D, Lambrecht M, Nyström PDW, Swinnen A, Wesseling FWR, Roelofs E, Troost EG
EPTN consensus-based guideline for the tolerance dose per fraction of organs at risk in the brain
CancerData, 2018; doi:10.17195/candat.2018.01.1

EPTN International Neurological Contouring Atlas

Daniëlle Eekers, Lieke In T Ven, Erik Roelofs, Alida Postma, Esther G Troost


Eekers et al. have published an international neurological atlas for contouring of organs at risk in consensus with the European Particle Therapy Network (EPTN). The purpose of this consensus atlas is to decrease inter- and intra-observer variability in delineating OARs relevant for neuro-oncology. We propose this atlas is used in photon and particle therapy in order to derive consistent dosimetric data. When required this atlas will be updated according to new insights.

Included are all OARs known to be relevant for radiation-induced toxicity in neuro-oncology: brain, brainstem, cochlea, vestibulum & semicircular canals, cornea, lens, retina, lacrimal gland, optic nerve, chiasm, pituitary, hippocampus and skin. A new OAR relevant for neuro-cognition, the posterior cerebellum is also included.

Three-dimensional delineation of the fifteen consensus OARs for neuro-oncology are shown on CT and 3 Tesla (3T) MR images (slice thickness 1 mm with intravenous contrast agent). All are presented in transversal, sagittal and coronal view.


Please cite this Atlas as follows:

Eekers D, In ’t Ven L, Roelofs E, Postma A, Troost EG. 
EPTN International Neurological Contouring Atlas 
CancerData, 2017. doi:10.17195/candat.2017.08.1