Floor N H Wilting
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Floor N H Wilting has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
- Catharina J. M. Klijn
Department of Neurology, Donders Institute for Brain, Cognition and Behaviour, Radboud University Medical Center, Nijmegen, The Netherlands
2 shared publications - Floris H. B. M. Schreuder
Department of Neurology, Donders Institute for Brain, Cognition and Behaviour, Radboud University Medical Center, Nijmegen, The Netherlands
2 shared publications - Gerjon Hannink
Department of Medical Imaging, Radboudumc, Nijmegen, The Netherlands
2 shared publications - Marieke J. H. Wermer
Department of Neurology, Leiden University Medical Center, Leiden, the Netherlands
2 shared publications - Ruben Dammers
Department of Neurosurgery, Erasmus University Medical Center, Rotterdam, The Netherlands
2 shared publications Wilmar M T Jolink
Department of Neurology, Isala Hospital , Zwolle
2 shared publications
Latest Publications
- Open Access
- 1 March 2026
- Published by Oxford University Press (OUP) in European Stroke Journal
- Vol. 11 (3)
Deep learning-based automated segmentation of intracerebral haemorrhage, intraventricular haemorrhage and perihaematomal oedema on non-contrast CT
Introduction: Precise volumetric evaluation of intracerebral haemorrhage (ICH), intraventricular haemorrhage (IVH) and perihaematomal oedema (PHO) is essential but manual segmentation is time-consuming and susceptible to variability. We aimed to develop and externally validate a deep learning model for simultaneous segmentation of ICH, IVH and PHO on non-contrast CT (NCCT) in patients with spontaneous ICH. Patients and methods: A 3D U-net model was trained with 5-fold cross-validation on baseline NCCTs from 301 patients included in 2 prospective multicentre studies. External validation was performed on 141 baseline NCCTs from another multicentre study. Model performance was evaluated against manual ground truth segmentations using the Dice similarity coefficient (DSC), intraclass correlation coefficients (ICC) and Bland–Altman analyses. Results: The model achieved a median DSC of 0.93 (IQR 0.91–0.94) for ICH, 0.75 (IQR 0.57–0.82) for IVH and 0.53 (IQR 0.34–0.65) for PHO. Volume correlations were excellent for ICH (mean absolute and consistency ICC both 0.98 [95% CI 0.98–0.99]) and IVH (absolute ICC 0.97 [95% CI 0.92–0.98]; consistency ICC 0.98 [95% CI 0.96–0.99]), and moderate for PHO (absolute ICC 0.60 [95% CI -0.08–0.85]; consistency ICC 0.82 [95% CI 0.76–0.87]). Bland–Altman analyses demonstrated a bias for ICH of −0.48 mL (LoA −8.21 to 7.26), for IVH of −1.68 mL (LoA −7.35 to 3.99) and for PHO of 13.91 mL (LoA −4.85 to 32.68). Discussion and conclusion: The model enables accurate automated segmentation of ICH, while IVH and PHO segmentation remain more challenging. Automated segmentations may already serve as reliable pre-segmentations in research, but require visual assessment and correction, in particular for IVH and PHO.
- 1 March 2026
- Published by Oxford University Press (OUP) in European Stroke Journal
- Vol. 11 (3)
Open AccessDeep learning-based automated segmentation of intracerebral haemorrhage, intraventricular haemorrhage and perihaematomal oedema on non-contrast CT
Introduction: Precise volumetric evaluation of intracerebral haemorrhage (ICH), intraventricular haemorrhage (IVH) and perihaematomal oedema (PHO) is essential but manual segmentation is time-consuming and susceptible to variability. We aimed to develop and externally validate a deep learning model for simultaneous segmentation of ICH, IVH and PHO on non-contrast CT (NCCT) in patients with spontaneous ICH. Patients and methods: A 3D U-net model was trained with 5-fold cross-validation on baseline NCCTs from 301 patients included in 2 prospective multicentre studies. External validation was performed on 141 baseline NCCTs from another multicentre study. Model performance was evaluated against manual ground truth segmentations using the Dice similarity coefficient (DSC), intraclass correlation coefficients (ICC) and Bland–Altman analyses. Results: The model achieved a median DSC of 0.93 (IQR 0.91–0.94) for ICH, 0.75 (IQR 0.57–0.82) for IVH and 0.53 (IQR 0.34–0.65) for PHO. Volume correlations were excellent for ICH (mean absolute and consistency ICC both 0.98 [95% CI 0.98–0.99]) and IVH (absolute ICC 0.97 [95% CI 0.92–0.98]; consistency ICC 0.98 [95% CI 0.96–0.99]), and moderate for PHO (absolute ICC 0.60 [95% CI -0.08–0.85]; consistency ICC 0.82 [95% CI 0.76–0.87]). Bland–Altman analyses demonstrated a bias for ICH of −0.48 mL (LoA −8.21 to 7.26), for IVH of −1.68 mL (LoA −7.35 to 3.99) and for PHO of 13.91 mL (LoA −4.85 to 32.68). Discussion and conclusion: The model enables accurate automated segmentation of ICH, while IVH and PHO segmentation remain more challenging. Automated segmentations may already serve as reliable pre-segmentations in research, but require visual assessment and correction, in particular for IVH and PHO.
- Open Access
- 29 December 2025
- Published by Oxford University Press (OUP) in European Stroke Journal
- Vol. 11 (1)
The Dutch Intracerebral Haemorrhage Surgery Trial: study protocol for a randomised clinical trial of minimally invasive endoscopy-guided surgery in patients with spontaneous, supratentorial intracerebral haemorrhage
Background: Growing evidence suggests that surgical treatment of ICH may be beneficial, particularly when performed early, with minimally invasive procedures, and in patients with lobar ICH. However, the available evidence is limited by risk of bias, heterogeneity and imprecision, and data supporting a beneficial effect in deep ICH is limited. Aim: To determine whether early minimally invasive endoscopy-guided surgery in addition to standard medical management improves functional outcome in patients with spontaneous supratentorial ICH, compared with standard medical management alone. Study design: The Dutch ICH Surgery Trial (DIST) is a multicentre, prospective, randomised trial with open-label treatment and blinded end-point assessment conducted in 11 neurosurgical centres in the Netherlands. Six hundred adult patients with spontaneous supratentorial ICH with a haematoma volume ≥ 10 mL and an NIHSS score ≥2 will be enrolled. Patients will be randomised (1:1) to minimally invasive endoscopy-guided surgery within 8 hours of symptom onset in addition to standard medical management, or to standard medical management alone. Study endpoints: The primary outcome is the mRS score at 180 days. Secondary outcomes include the mRS at 90 and 365 days, safety and technical efficacy outcomes, quality-of-life measures and health economic evaluations up to 365 days. In addition, DIST will investigate blood and imaging biomarkers of secondary brain injury. Summary: Dutch ICH Surgery Trial assesses the efficacy of early endoscopy-guided surgery for patients with supratentorial ICH. Recruitment started in November 2022; as of October 2025, 235 participants have been enrolled. Completion of recruitment is expected in 2027. Trial registration: ClinicalTrials.gov NCT05460793.
- 29 December 2025
- Published by Oxford University Press (OUP) in European Stroke Journal
- Vol. 11 (1)
Open AccessThe Dutch Intracerebral Haemorrhage Surgery Trial: study protocol for a randomised clinical trial of minimally invasive endoscopy-guided surgery in patients with spontaneous, supratentorial intracerebral haemorrhage
Background: Growing evidence suggests that surgical treatment of ICH may be beneficial, particularly when performed early, with minimally invasive procedures, and in patients with lobar ICH. However, the available evidence is limited by risk of bias, heterogeneity and imprecision, and data supporting a beneficial effect in deep ICH is limited. Aim: To determine whether early minimally invasive endoscopy-guided surgery in addition to standard medical management improves functional outcome in patients with spontaneous supratentorial ICH, compared with standard medical management alone. Study design: The Dutch ICH Surgery Trial (DIST) is a multicentre, prospective, randomised trial with open-label treatment and blinded end-point assessment conducted in 11 neurosurgical centres in the Netherlands. Six hundred adult patients with spontaneous supratentorial ICH with a haematoma volume ≥ 10 mL and an NIHSS score ≥2 will be enrolled. Patients will be randomised (1:1) to minimally invasive endoscopy-guided surgery within 8 hours of symptom onset in addition to standard medical management, or to standard medical management alone. Study endpoints: The primary outcome is the mRS score at 180 days. Secondary outcomes include the mRS at 90 and 365 days, safety and technical efficacy outcomes, quality-of-life measures and health economic evaluations up to 365 days. In addition, DIST will investigate blood and imaging biomarkers of secondary brain injury. Summary: Dutch ICH Surgery Trial assesses the efficacy of early endoscopy-guided surgery for patients with supratentorial ICH. Recruitment started in November 2022; as of October 2025, 235 participants have been enrolled. Completion of recruitment is expected in 2027. Trial registration: ClinicalTrials.gov NCT05460793.