Robert Poel

Robert Poel

Auto-generated profile, based on publicly available information

Robert Poel


Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
23 August 2023 in Cancers
Verified
Journal Article
Open access
PDF file
RPRobert Poel
Robert Poel
AKAmith Kamath
Amith Kamath
JWJonas Willmann
Jonas Willmann
NANicolaus Andratschke
Nicolaus Andratschke
EEEkin Ermis
Ekin Ermis
MRMauricio Reyes
Mauricio Reyes
External beam radiation therapy requires a sophisticated and laborious planning procedure. To improve the efficiency and quality of this procedure, machine-learning models that predict these dose distributions were introduced. The most recent dose prediction models are based on deep-learning architectures called 3D U-Nets that give good approximations of the dose in 3D almost instantly. Our purpose was to train such a 3D dose prediction model for glioblastoma VMAT treatment and test its robustness and sensitivity for the purpose of quality assurance of automatic contouring. From a cohort of 125 glioblastoma (GBM) patients, VMAT plans were created according to a clinical protocol. The initial model was trained on a cascaded 3D U-Net. A total of 60 cases were used for training, 15 for validation and 20 for testing. The prediction model was tested for sensitivity to dose changes when subject to realistic contour variations. Additionally, the model was tested for robustness by exposing it to a worst-case test set containing out-of-distribution cases. The initially trained prediction model had a dose score of 0.94 Gy and a mean DVH (dose volume histograms) score for all structures of 1.95 Gy. In terms of sensitivity, the model was able to predict the dose changes that occurred due to the contour variations with a mean error of 1.38 Gy. We obtained a 3D VMAT dose prediction model for GBM with limited data, providing good sensitivity to realistic contour variations. We tested and improved the model’s robustness by targeted updates to the training set, making it a useful technique for introducing dose awareness in the contouring evaluation and quality assurance process.

22 October 2022 in Radiation Oncology
Verified
Journal Article
Open access
PDF file
RPRobert Poel
Robert Poel
ERElias Rüfenacht
Elias Rüfenacht
EEEkin Ermis
Ekin Ermis
MMMichael Müller
Michael Müller
MFMichael K. Fix
Michael K. Fix
MRMauricio Reyes
Mauricio Reyes
To save time and have more consistent contours, fully automatic segmentation of targets and organs at risk (OAR) is a valuable asset in radiotherapy. Though current deep learning (DL) based models are on par with manual contouring, they are not perfect and typical errors, as false positives, occur frequently and unpredictably. While it is possible to solve this for OARs, it is far from straightforward for target structures. In order to tackle this problem, in this study, we analyzed the occurrence and the possible dose effects of automated delineation outliers. First, a set of controlled experiments on synthetically generated outliers on the CT of a glioblastoma (GBM) patient was performed. We analyzed the dosimetric impact on outliers with different location, shape, absolute size and relative size to the main target, resulting in 61 simulated scenarios. Second, multiple segmentation models where trained on a U-Net network based on 80 training sets consisting of GBM cases with annotated gross tumor volume (GTV) and edema structures. On 20 test cases, 5 different trained models and a majority voting method were used to predict the GTV and edema. The amount of outliers on the predictions were determined, as well as their size and distance from the actual target. We found that plans containing outliers result in an increased dose to healthy brain tissue. The extent of the dose effect is dependent on the relative size, location and the distance to the main targets and involved OARs. Generally, the larger the absolute outlier volume and the distance to the target the higher the potential dose effect. For 120 predicted GTV and edema structures, we found 1887 outliers. After construction of the planning treatment volume (PTV), 137 outliers remained with a mean distance to the target of 38.5 ± 5.0 mm and a mean size of 1010.8 ± 95.6 mm3. We also found that majority voting of DL results is capable to reduce outliers. This study shows that there is a severe risk of false positive outliers in current DL predictions of target structures. Additionally, these errors will have an evident detrimental impact on the dose and therefore could affect treatment outcome.

6 December 2025 in Physics and Imaging in Radiation Oncology
Verified
Journal Article
Open access
RPRobert Poel
Robert Poel
AKAmith Kamath
Amith Kamath
EEEkin Ermiş
Ekin Ermiş
JWJonas Willmann
Jonas Willmann
ERElias Rüfenacht
Elias Rüfenacht
MRMauricio Reyes
Mauricio Reyes
Despite widespread adaptation of automatic segmentation (AS), manual review and adjustment of generated contours are still essential. This process is time-consuming and identifying clinically relevant corrections remains challenging. Inter-observer variability and the risk of overlooking significant errors further complicate the workflow. A dedicated quality assurance tool is highly relevant to assure quality and speed up the manual review task. The primary aim of this work is to identify critical segmentation errors while reducing unnecessary manual review, enabling efficient integration of AS into routine radiotherapy. We developed an evaluation assistant that assesses contour quality through the geometric measures Dice similarity coefficient and the Hausdorff distance. This was combined with a dose prediction model to determine the clinical relevance. The system was validated on 30 glioblastoma cases with ground truth and manually modified organ at risk (OAR) contours. A traffic light decision matrix classified contours based on geometric and dose parameters, flagging structures for human review. Out of 507 analyzed OARs, 180 were classified as critical. Our approach identified 173 of these critical structures (sensitivity: 0.96, specificity: 0.55). The system flagged 317 organs (61%) as critical, effectively ruling out 39% as non-critical with only 7 false negatives comprising structures. Our dual-layer QA approach effectively identifies critical OAR segmentations with high sensitivity and acceptable specificity, potentially reducing manual review requirements significantly. By focusing on clinically relevant dose/volume metric endpoints, this method assures the quality of brain AS results in clinical radiotherapy practice.

11 August 2023 in Preprints.org
Verified
Preprint
Open access
PDF file
RPRobert Poel
Robert Poel
AKAmith Kamath
Amith Kamath
JWJonas Willmann
Jonas Willmann
NANicolaus Andratschke
Nicolaus Andratschke
EEEkin Ermis
Ekin Ermis
MRMauricio Reyes
Mauricio Reyes
Background: External beam radiation therapy requires a sophisticated and laborious planning procedure. To improve the efficiency and quality of the planning procedure, machine learning predictions of the dose distributions have been introduced to speed up the planning procedure and to serve as quality assurance. The most recent dose prediction models are based on deep learning U-Nets that give good approximations of the dose in 3D almost instantly. It is our purpose to train a 3D dose prediction for glioblastoma VMAT treatment and test its robustness and sensitivity for the purpose of quality assurance of automatic contouring. Methods: From a cohort of 125 glioblastoma (GBM) patients, VMAT plans were created according to a clinical protocol. The initial model was trained on a concatenated 3D U-Net. A total of 60 cases were used for training, 15 for validation and 20 for testing. The prediction model was tested for sensitivity to dose changes according to realistic contour variations. Additionally, the model was tested for robustness by exposing it to a worst-case test set containing out-of-distribution cases.Results: The initially trained prediction model had a dose score of 0.94 Gy and a mean DVH score for all structures of 1.95 Gy. In terms of sensitivity, the model was able to predict the dose changes that occurred due to the contour variations with a mean error of 1.38 Gy.Conclusions: We obtained a 3D VMAT dose prediction model for GBM with limited data, providing good sensitivity to realistic contour variations. We tested and improved the model's robustness, by targeted updating the training set, making it a useful technique for dose awareness in the contouring evaluation and quality assurance.