Charlotte L. Brouwer
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Charlotte L. Brouwer has a total of 136 co-authors. Here are the top co-authors by number of shared publications:
- Johannes Albertus Langendijk
Department of Radiation Oncology, University of Groningen, University Medical Center Groningen, Groningen, The Netherlands
8 shared publications Johannes A. Langendijk
University of Groningen, University Medical Center Groningen, Department of Radiation Oncology, Groningen, the Netherlands
6 shared publications- Nanna Maria Sijtsema
Department of Radiation Oncology, University Medical Center Groningen, University of Groningen, Groningen, The Netherlands
6 shared publications Stefan Both
University of Groningen, University Medical Center Groningen, Department of Radiation Oncology, Groningen, the Netherlands
6 shared publicationsRoel J.H.M. Steenbakkers
University of Groningen, University Medical Center Groningen, Department of Radiation Oncology, Hanzeplein 1, 9713 GZ Groningen, the Netherlands
5 shared publications- Stefan Both
University Medical Center Groningen
4 shared publications
Latest Publications
- Open Access
- 19 April 2026
- Published by Elsevier in Technical Innovations & Patient Support in Radiation Oncology
- Vol. 38, 100405
Toxicity of rectal preparation strategies in ultra-hypofractionated SBRT for prostate cancer
- 19 April 2026
- Published by Elsevier in Technical Innovations & Patient Support in Radiation Oncology
- Vol. 38, 100405
Open AccessToxicity of rectal preparation strategies in ultra-hypofractionated SBRT for prostate cancer
- Open Access
- 17 October 2025
- Published by IOP Publishing in Physics in Medicine & Biology
- Vol. 70 (20) , 205023
Reliability of uncertainty quantification methods for deep learning auto-segmentation in head and neck organs at risk
Objective. Deep learning auto-segmentation has greatly advanced contouring in radiotherapy. However, quality assurance remains necessary due to performance fluctuation among individual patients. This manual process reintroduces variability and partially reduces time-saving benefits. As a solution, uncertainty quantification (UQ) is increasingly explored for its ability to estimate output confidence. While numerous methods to quantify uncertainty exist, their comparative reliability remains underexplored. This study compares the reliability of commonly used UQ approaches for auto-segmentation in radiotherapy. Approach. We evaluated the reliability of three popular uncertainty methods (Monte Carlo dropout, deep ensemble modelling and test-time augmentation) and uncertainty metrics (predictive entropy, mutual information and variance). We trained a 3D U-Net within the nnU-Net framework to segment 19 organs at risk (OAR) for head and neck cancer patients. We evaluated the reliability of the UQ methods and metrics on a set of 10 patients using segmentation model accuracy (surface Dice similarity coefficient), confidence calibration (expected calibration error (label)), and error localisation ability (uncertainty-error (U-E) overlap). Both multi-class and class-specific uncertainty maps were assessed. Main results. Segmentation accuracy remained stable without significant deviations across all UQ methods with respect to the baseline model without UQ. The reliability of different UQ methods in terms of confidence calibration and error localisation was also comparable. In contrast, the choice of UQ metric significantly influenced reliability. Multi-class predictive entropy (ECE-label: 0.06–0.06, U-E overlap: 0.45–0.46) consistently outperformed variance (ECE-label: 0.13–0.14, U-E overlap: 0.32–0.40, p < 0.001) and mutual information (ECE-label: 0.13–0.14, U-E overlap: 0.35–0.40, p < 0.001). Predictive entropy also demonstrated superior reliability as a class-specific UQ metric, though variability was observed between OARs. Significance. This study demonstrates that the choice of UQ approach substantially impacts the reliability of uncertainty maps. While different UQ methods performed comparably, the specific UQ metric chosen significantly affected reliability. These findings underscore the importance of careful metric selection and evaluation prior to application.
- 17 October 2025
- Published by IOP Publishing in Physics in Medicine & Biology
- Vol. 70 (20) , 205023
Open AccessReliability of uncertainty quantification methods for deep learning auto-segmentation in head and neck organs at risk
Objective. Deep learning auto-segmentation has greatly advanced contouring in radiotherapy. However, quality assurance remains necessary due to performance fluctuation among individual patients. This manual process reintroduces variability and partially reduces time-saving benefits. As a solution, uncertainty quantification (UQ) is increasingly explored for its ability to estimate output confidence. While numerous methods to quantify uncertainty exist, their comparative reliability remains underexplored. This study compares the reliability of commonly used UQ approaches for auto-segmentation in radiotherapy. Approach. We evaluated the reliability of three popular uncertainty methods (Monte Carlo dropout, deep ensemble modelling and test-time augmentation) and uncertainty metrics (predictive entropy, mutual information and variance). We trained a 3D U-Net within the nnU-Net framework to segment 19 organs at risk (OAR) for head and neck cancer patients. We evaluated the reliability of the UQ methods and metrics on a set of 10 patients using segmentation model accuracy (surface Dice similarity coefficient), confidence calibration (expected calibration error (label)), and error localisation ability (uncertainty-error (U-E) overlap). Both multi-class and class-specific uncertainty maps were assessed. Main results. Segmentation accuracy remained stable without significant deviations across all UQ methods with respect to the baseline model without UQ. The reliability of different UQ methods in terms of confidence calibration and error localisation was also comparable. In contrast, the choice of UQ metric significantly influenced reliability. Multi-class predictive entropy (ECE-label: 0.06–0.06, U-E overlap: 0.45–0.46) consistently outperformed variance (ECE-label: 0.13–0.14, U-E overlap: 0.32–0.40, p < 0.001) and mutual information (ECE-label: 0.13–0.14, U-E overlap: 0.35–0.40, p < 0.001). Predictive entropy also demonstrated superior reliability as a class-specific UQ metric, though variability was observed between OARs. Significance. This study demonstrates that the choice of UQ approach substantially impacts the reliability of uncertainty maps. While different UQ methods performed comparably, the specific UQ metric chosen significantly affected reliability. These findings underscore the importance of careful metric selection and evaluation prior to application.
- Open Access
- 15 July 2025
- Published by Elsevier in Physica Medica
- Vol. 136, 105041
Dir-based dose accumulation for parotid glands in head and neck cancer: Accuracy and implications for adaptive radiotherapy
- 15 July 2025
- Published by Elsevier in Physica Medica
- Vol. 136, 105041
Open AccessDir-based dose accumulation for parotid glands in head and neck cancer: Accuracy and implications for adaptive radiotherapy
- Open Access
- 8 May 2025
- Published by Elsevier in Physics and Imaging in Radiation Oncology
- Vol. 34, 100771
Leveraging network uncertainty to identify regions in rectal cancer clinical target volume auto-segmentations likely requiring manual edits
- 8 May 2025
- Published by Elsevier in Physics and Imaging in Radiation Oncology
- Vol. 34, 100771
Open AccessLeveraging network uncertainty to identify regions in rectal cancer clinical target volume auto-segmentations likely requiring manual edits
- Open Access
Deep Learning for Automated Ventricle and Periventricular Space Segmentation on CT and T1CE MRI in Neuro-Oncology Patients
Purpose: This study aims to create a deep learning (DL) model capable of accurately delineating the ventricles, and by extension, the periventricular space (PVS), following the 2021 EPTN Neuro-Oncology Atlas guidelines on T1-weighted contrast-enhanced MRI scans (T1CE). The performance of this DL model was quantitatively and qualitatively compared with an off-the-shelf model. Materials and Methods: An nnU-Net was trained for ventricle segmentation using both CT and T1CE MRI images from 78 patients. Its performance was compared to that of a publicly available pretrained segmentation model, SynthSeg. The evaluation was conducted on both internal (N = 18) and external (n = 18) test sets, with each consisting of paired CT and T1CE MRI images and expert-delineated ground truths (GTs). Segmentation accuracy was assessed using the volumetric Dice Similarity Coefficient (DSC), 95th percentile Hausdorff distance (HD95), surface DSC, and added path length (APL). Additionally, a local evaluation of ventricle segmentations quantified differences between manual and automatic segmentations across both test sets. All segmentations were scored by radiotherapy technicians for clinical acceptability using a 4-point Likert scale. Results: The nnU-Net significantly outperformed the SynthSeg model on the internal test dataset in terms of median [range] DSC, 0.93 [0.86–0.95] vs. 0.85 [0.67–0.91], HD95, 0.9 [0.7–2.5] mm vs. 2.2 [1.7–4.8] mm, surface DSC, 0.97 [0.90–0.98] vs. 0.84 [0.70–0.89], and APL, 876 [407–1298] mm vs. 2809 [2311–3622] mm, all with p < 0.001. No significant differences in these metrics were found in the external test set. However clinical ratings favored nnU-Net segmentations on the internal and external test sets. In addition, the nnU-Net had higher clinical ratings than the GT delineation on the internal and external test set. Conclusions: The nnU-Net model outperformed the SynthSeg model on the internal dataset in both segmentation metrics and clinician ratings. While segmentation metrics showed no significant differences between the models on the external set, clinician ratings favored nnU-Net, suggesting enhanced clinical acceptability. This suggests that nnU-Net could contribute to more time-efficient and streamlined radiotherapy planning workflows.
Open AccessDeep Learning for Automated Ventricle and Periventricular Space Segmentation on CT and T1CE MRI in Neuro-Oncology Patients
Purpose: This study aims to create a deep learning (DL) model capable of accurately delineating the ventricles, and by extension, the periventricular space (PVS), following the 2021 EPTN Neuro-Oncology Atlas guidelines on T1-weighted contrast-enhanced MRI scans (T1CE). The performance of this DL model was quantitatively and qualitatively compared with an off-the-shelf model. Materials and Methods: An nnU-Net was trained for ventricle segmentation using both CT and T1CE MRI images from 78 patients. Its performance was compared to that of a publicly available pretrained segmentation model, SynthSeg. The evaluation was conducted on both internal (N = 18) and external (n = 18) test sets, with each consisting of paired CT and T1CE MRI images and expert-delineated ground truths (GTs). Segmentation accuracy was assessed using the volumetric Dice Similarity Coefficient (DSC), 95th percentile Hausdorff distance (HD95), surface DSC, and added path length (APL). Additionally, a local evaluation of ventricle segmentations quantified differences between manual and automatic segmentations across both test sets. All segmentations were scored by radiotherapy technicians for clinical acceptability using a 4-point Likert scale. Results: The nnU-Net significantly outperformed the SynthSeg model on the internal test dataset in terms of median [range] DSC, 0.93 [0.86–0.95] vs. 0.85 [0.67–0.91], HD95, 0.9 [0.7–2.5] mm vs. 2.2 [1.7–4.8] mm, surface DSC, 0.97 [0.90–0.98] vs. 0.84 [0.70–0.89], and APL, 876 [407–1298] mm vs. 2809 [2311–3622] mm, all with p < 0.001. No significant differences in these metrics were found in the external test set. However clinical ratings favored nnU-Net segmentations on the internal and external test sets. In addition, the nnU-Net had higher clinical ratings than the GT delineation on the internal and external test set. Conclusions: The nnU-Net model outperformed the SynthSeg model on the internal dataset in both segmentation metrics and clinician ratings. While segmentation metrics showed no significant differences between the models on the external set, clinician ratings favored nnU-Net, suggesting enhanced clinical acceptability. This suggests that nnU-Net could contribute to more time-efficient and streamlined radiotherapy planning workflows.
- Open Access
- 16 January 2025
- Published by MDPI AG in Journal of Clinical Medicine
- Vol. 14 (2) , 551
Assessing the Validity of Diffusion Weighted Imaging Models: A Study in Patients with Post-Surgical Lower-Grade Glioma
Background: Diffusion weighted imaging (DWI) is used for monitoring purposes for lower-grade glioma (LGG). While the apparent diffusion coefficient (ADC) is clinically used, various DWI models have been developed to better understand the micro-environment. However, the validity of these models and how they relate to each other is currently unknown. Therefore, this study assesses the validity and agreement of these models. Methods: Fourteen post-treatment LGG patients and six healthy controls (HC) underwent DWI MRI on a 3T MRI scanner. DWI processing included diffusion tensor imaging (DTI), diffusion kurtosis imaging (DKI), white matter tract integrity (WMTI), neurite orientation dispersion and density imaging (NODDI), and fixel-based analysis (FBA). Validity was assessed by delineating surgical cavity, peri-surgical cavity, and normal-appearing white matter (NAWM) in LGG patients, and white matter (WM) in HC. Spearman correlation assessed the agreement between DWI parameters. Results: All obtained parameters differed significantly across tissue types. Remarkably, WMTI showed that intra-axonal diffusivity was high in the surgical cavity and low in NAWM and WM. Most DWI parameters correlated well with each other, except for WMTI-derived intra-axonal diffusivity. Conclusion: This study shows that all parameters relevant for tumour monitoring and DWI-derived parameters for axonal fibre-bundle integrity (except WMTI-IAS-Da) could be used interchangeably, enhancing inter-DWI model interpretability.
- 16 January 2025
- Published by MDPI AG in Journal of Clinical Medicine
- Vol. 14 (2) , 551
Open AccessAssessing the Validity of Diffusion Weighted Imaging Models: A Study in Patients with Post-Surgical Lower-Grade Glioma
Background: Diffusion weighted imaging (DWI) is used for monitoring purposes for lower-grade glioma (LGG). While the apparent diffusion coefficient (ADC) is clinically used, various DWI models have been developed to better understand the micro-environment. However, the validity of these models and how they relate to each other is currently unknown. Therefore, this study assesses the validity and agreement of these models. Methods: Fourteen post-treatment LGG patients and six healthy controls (HC) underwent DWI MRI on a 3T MRI scanner. DWI processing included diffusion tensor imaging (DTI), diffusion kurtosis imaging (DKI), white matter tract integrity (WMTI), neurite orientation dispersion and density imaging (NODDI), and fixel-based analysis (FBA). Validity was assessed by delineating surgical cavity, peri-surgical cavity, and normal-appearing white matter (NAWM) in LGG patients, and white matter (WM) in HC. Spearman correlation assessed the agreement between DWI parameters. Results: All obtained parameters differed significantly across tissue types. Remarkably, WMTI showed that intra-axonal diffusivity was high in the surgical cavity and low in NAWM and WM. Most DWI parameters correlated well with each other, except for WMTI-derived intra-axonal diffusivity. Conclusion: This study shows that all parameters relevant for tumour monitoring and DWI-derived parameters for axonal fibre-bundle integrity (except WMTI-IAS-Da) could be used interchangeably, enhancing inter-DWI model interpretability.
- Open Access
- 19 June 2024
- Published by Elsevier in Physics and Imaging in Radiation Oncology
- Vol. 31, 100600
Target coverage and organs at risk dose in hypofractionated salvage radiotherapy after prostatectomy
- 19 June 2024
- Published by Elsevier in Physics and Imaging in Radiation Oncology
- Vol. 31, 100600
Open AccessTarget coverage and organs at risk dose in hypofractionated salvage radiotherapy after prostatectomy
- Open Access
- 11 May 2024
- Published by Elsevier in Clinical and Translational Radiation Oncology
- Vol. 47, 100794
Pelvic lymph node motion during cone-beam computed tomography guided stereotactic radiotherapy
- 11 May 2024
- Published by Elsevier in Clinical and Translational Radiation Oncology
- Vol. 47, 100794
Open AccessPelvic lymph node motion during cone-beam computed tomography guided stereotactic radiotherapy
- Open Access
Proton PBS Planning Techniques, Robustness Evaluation, and OAR Sparing for the Whole-Brain Part of Craniospinal Axis Irradiation
Proton therapy is a promising modality for craniospinal irradiation (CSI), offering dosimetric advantages over conventional treatments. While significant attention has been paid to spine fields, for the brain fields, only dose reduction to the lens of the eye has been reported. Hence, the objective of this study is to assess the potential gains and feasibility of adopting different treatment planning techniques for the entire brain within the CSI target. To this end, eight previously treated CSI patients underwent retrospective replanning using various techniques: (1) intensity modulated proton therapy (IMPT) optimization, (2) the modification/addition of field directions, and (3) the pre-optimization removal of superficially placed spots. The target coverage robustness was evaluated and dose comparisons for lenses, cochleae, and scalp were conducted, considering potential biological dose increases. The target coverage robustness was maintained across all plans, with minor reductions when superficial spot removal was utilized. Single- and multifield optimization showed comparable target coverage robustness and organ-at-risk sparing. A significant scalp sparing was achieved in adults but only limited in pediatric cases. Superficial spot removal contributed to scalp V30 Gy reduction at the expense of lower coverage robustness in specific cases. Lens sparing benefits from multiple field directions, while cochlear sparing remains impractical. Based on the results, all investigated plan types are deemed clinically adoptable.
Open AccessProton PBS Planning Techniques, Robustness Evaluation, and OAR Sparing for the Whole-Brain Part of Craniospinal Axis Irradiation
Proton therapy is a promising modality for craniospinal irradiation (CSI), offering dosimetric advantages over conventional treatments. While significant attention has been paid to spine fields, for the brain fields, only dose reduction to the lens of the eye has been reported. Hence, the objective of this study is to assess the potential gains and feasibility of adopting different treatment planning techniques for the entire brain within the CSI target. To this end, eight previously treated CSI patients underwent retrospective replanning using various techniques: (1) intensity modulated proton therapy (IMPT) optimization, (2) the modification/addition of field directions, and (3) the pre-optimization removal of superficially placed spots. The target coverage robustness was evaluated and dose comparisons for lenses, cochleae, and scalp were conducted, considering potential biological dose increases. The target coverage robustness was maintained across all plans, with minor reductions when superficial spot removal was utilized. Single- and multifield optimization showed comparable target coverage robustness and organ-at-risk sparing. A significant scalp sparing was achieved in adults but only limited in pediatric cases. Superficial spot removal contributed to scalp V30 Gy reduction at the expense of lower coverage robustness in specific cases. Lens sparing benefits from multiple field directions, while cochlear sparing remains impractical. Based on the results, all investigated plan types are deemed clinically adoptable.
- Open Access
- 1 January 2024
- Published by Oxford University Press (OUP) in BJR|Artificial Intelligence
- Vol. 1 (1)
Clinical adoption of deep learning target auto-segmentation for radiation therapy: challenges, clinical risks, and mitigation strategies
Radiation therapy is a localized cancer treatment that relies on precise delineation of the target to be treated and healthy tissues to guarantee optimal treatment effect. This step, known as contouring or segmentation, involves identifying both target volumes and organs at risk on imaging modalities like CT, PET, and MRI to guide radiation delivery. Manual segmentation, however, is time-consuming and highly subjective, despite the presence of contouring guidelines. In recent years, automated segmentation methods, particularly deep learning models, have shown promise in addressing this task. However, challenges persist in their clinical use, including the need for robust quality assurance (QA) processes and addressing clinical risks associated with the use of the models. This review examines the challenges and considerations of the clinical adoption of deep learning target auto-segmentation in radiotherapy, focused on the target volume. We discuss potential clinical risks (eg, over- and under-segmentation, automation bias, and appropriate trust), mitigation strategies (eg, human oversight, uncertainty quantification, and education of clinical professionals), and we highlight the importance of expanding QA to include geometric, dose-volume, and outcome-based performance monitoring. While deep learning target auto-segmentation offers significant potential benefits, careful attention to clinical risks and rigorous QA measures are essential for its successful integration in clinical practice.
- 1 January 2024
- Published by Oxford University Press (OUP) in BJR|Artificial Intelligence
- Vol. 1 (1)
Open AccessClinical adoption of deep learning target auto-segmentation for radiation therapy: challenges, clinical risks, and mitigation strategies
Radiation therapy is a localized cancer treatment that relies on precise delineation of the target to be treated and healthy tissues to guarantee optimal treatment effect. This step, known as contouring or segmentation, involves identifying both target volumes and organs at risk on imaging modalities like CT, PET, and MRI to guide radiation delivery. Manual segmentation, however, is time-consuming and highly subjective, despite the presence of contouring guidelines. In recent years, automated segmentation methods, particularly deep learning models, have shown promise in addressing this task. However, challenges persist in their clinical use, including the need for robust quality assurance (QA) processes and addressing clinical risks associated with the use of the models. This review examines the challenges and considerations of the clinical adoption of deep learning target auto-segmentation in radiotherapy, focused on the target volume. We discuss potential clinical risks (eg, over- and under-segmentation, automation bias, and appropriate trust), mitigation strategies (eg, human oversight, uncertainty quantification, and education of clinical professionals), and we highlight the importance of expanding QA to include geometric, dose-volume, and outcome-based performance monitoring. While deep learning target auto-segmentation offers significant potential benefits, careful attention to clinical risks and rigorous QA measures are essential for its successful integration in clinical practice.