Benjamin Roberfroid
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Benjamin Roberfroid has a total of 23 co-authors. Here are the top co-authors by number of shared publications:
- Ana Maria Barragan Montero
Molecular Imaging, Radiotherapy and Oncology, Institut de Recherche Expérimentale et Clinique, UCLouvain, Belgium
4 shared publications John A. Lee
Université catholique de Louvain - Center of Molecular Imaging, Radiotherapy and Oncology (MIRO) Brussels Belgium
3 shared publicationsEdmond Sterpin
Université catholique de Louvain - Center of Molecular Imaging, Radiotherapy and Oncology (MIRO) Brussels Belgium
2 shared publications- Edmond Sterpin
KU Leuven
2 shared publications - John Aldo Lee
Université catholique de Louvain
2 shared publications Margerie Huet-Dastarac
2 shared publications
Latest Publications
- Open Access
- 12 March 2026
- Published by Elsevier in SSRN Electronic Journal
Expert trained AI-models as a paradigm shift for disseminating radiotherapy contouring guidelines: The EPTN consensus atlas for CT- and MR-based neuro-oncology contouring
We present an expert-trained deep learning model for automated delineation of 25 organs-at-risk defined in the EPTN atlas for neuro-oncological radiotherapy. Multiple input configurations were evaluated. The dual-input channel model combining contrast-enhanced T1-weighted MRI and CT achieved the best overall results (median surface Dice Similarity Coefficient = 0.84). It demonstrated robust performance across a wide range of organs-at-risk, supporting its use as a segmentation-support tool under human supervision and for fully automated retrospective dose–response analyses. We release the model publicly to the international community, while explicitly acknowledging that clinical use remains the responsibility of each institution within its regulatory context.
- 12 March 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessExpert trained AI-models as a paradigm shift for disseminating radiotherapy contouring guidelines: The EPTN consensus atlas for CT- and MR-based neuro-oncology contouring
We present an expert-trained deep learning model for automated delineation of 25 organs-at-risk defined in the EPTN atlas for neuro-oncological radiotherapy. Multiple input configurations were evaluated. The dual-input channel model combining contrast-enhanced T1-weighted MRI and CT achieved the best overall results (median surface Dice Similarity Coefficient = 0.84). It demonstrated robust performance across a wide range of organs-at-risk, supporting its use as a segmentation-support tool under human supervision and for fully automated retrospective dose–response analyses. We release the model publicly to the international community, while explicitly acknowledging that clinical use remains the responsibility of each institution within its regulatory context.
- 5 March 2025
- Published by IOP Publishing in Physics in Medicine & Biology
- Vol. 70 (6) , 065005
Anticipating potential bottlenecks in adaptive proton FLASH therapy: a ridge filter reuse strategy
Objective. Achieving FLASH dose rate with pencil beam scanning intensity modulated proton therapy is challenging. However, utilizing a single energy layer with a ridge filter (RF) can maintain dose rate and conformality. Yet, changes in patient anatomy over the treatment course can render the RF obsolete. Unfortunately, creating a new RF is time-consuming, thus, incompatible with online adaptation. To address this, we propose to re-optimize the spot weights while keeping the same initial RF. Approach. Data from six head and neck cancer patients with a repeated computed tomography (CT2) were used. FLASH treatment plans were generated with three methods on CT2: ‘full-adaptation’ (FA), optimized from scratch with a new RF; ‘spot-adaptation only’ (SAO), re-using initial RF but adjusting plan spot weights; and ‘no adaptation’ (NoA) where the dose from initial plans on initial CT (CT1) was recomputed on CT2. The prescribed dose per fraction was 9 Gy. Different beam angles were tested for each CT2 (1 beam per fraction). The FA, SAO and NoA plans were then compared on CT2. Main results. Fractions with SAO showed a median decrease of 0.05 Gy for D98% and a median increase of 0.03 Gy for D2% of CTV when compared to their homologous FA plans on nominal case. Median conformity number decreased by 0.03. Median max dose to spinal cord increased by 0.09 Gy. The largest median increase in mean dose to organs was 0.03 Gy to the mandible. The largest observed median difference in organs receiving a minimal dose rate of 40 Gy s−1 was 0.5% for the mandible. Up to 16 of the 20 evaluated SAO fractions were thus deemed clinically acceptable, with up to 8 NoA plans already acceptable before adaptation. Significance. Proposed SAO workflow showed that for most of our evaluated plans, daily reprinting of RF was not necessary.
- 5 March 2025
- Published by IOP Publishing in Physics in Medicine & Biology
- Vol. 70 (6) , 065005
Anticipating potential bottlenecks in adaptive proton FLASH therapy: a ridge filter reuse strategy
Objective. Achieving FLASH dose rate with pencil beam scanning intensity modulated proton therapy is challenging. However, utilizing a single energy layer with a ridge filter (RF) can maintain dose rate and conformality. Yet, changes in patient anatomy over the treatment course can render the RF obsolete. Unfortunately, creating a new RF is time-consuming, thus, incompatible with online adaptation. To address this, we propose to re-optimize the spot weights while keeping the same initial RF. Approach. Data from six head and neck cancer patients with a repeated computed tomography (CT2) were used. FLASH treatment plans were generated with three methods on CT2: ‘full-adaptation’ (FA), optimized from scratch with a new RF; ‘spot-adaptation only’ (SAO), re-using initial RF but adjusting plan spot weights; and ‘no adaptation’ (NoA) where the dose from initial plans on initial CT (CT1) was recomputed on CT2. The prescribed dose per fraction was 9 Gy. Different beam angles were tested for each CT2 (1 beam per fraction). The FA, SAO and NoA plans were then compared on CT2. Main results. Fractions with SAO showed a median decrease of 0.05 Gy for D98% and a median increase of 0.03 Gy for D2% of CTV when compared to their homologous FA plans on nominal case. Median conformity number decreased by 0.03. Median max dose to spinal cord increased by 0.09 Gy. The largest median increase in mean dose to organs was 0.03 Gy to the mandible. The largest observed median difference in organs receiving a minimal dose rate of 40 Gy s−1 was 0.5% for the mandible. Up to 16 of the 20 evaluated SAO fractions were thus deemed clinically acceptable, with up to 8 NoA plans already acceptable before adaptation. Significance. Proposed SAO workflow showed that for most of our evaluated plans, daily reprinting of RF was not necessary.
- Open Access
- 30 January 2025
- Published by Elsevier in Physics and Imaging in Radiation Oncology
- Vol. 33, 100705
Towards faster plan adaptation for proton arc therapy using initial treatment plan information
- 30 January 2025
- Published by Elsevier in Physics and Imaging in Radiation Oncology
- Vol. 33, 100705
Open AccessTowards faster plan adaptation for proton arc therapy using initial treatment plan information
- 23 January 2024
- Published by Elsevier in Radiotherapy and Oncology
- Vol. 192, 110108
DIVE-ART: A tool to guide clinicians towards dosimetrically informed volume editions of automatically segmented volumes in adaptive radiation therapy
- 23 January 2024
- Published by Elsevier in Radiotherapy and Oncology
- Vol. 192, 110108
DIVE-ART: A tool to guide clinicians towards dosimetrically informed volume editions of automatically segmented volumes in adaptive radiation therapy
- 23 November 2023
- Published by Elsevier in Physica Medica
- Vol. 116, 103178
Comparison of Ethos template-based planning and AI-based dose prediction: General performance, patient optimality, and limitations
- 23 November 2023
- Published by Elsevier in Physica Medica
- Vol. 116, 103178
Comparison of Ethos template-based planning and AI-based dose prediction: General performance, patient optimality, and limitations