Pieter Kitslaar
Research Subjects
Pieter Kitslaar has a total of 20 co-authors. Here are the top co-authors by number of shared publications:
- Alexander Broersen
Division of Image Processing, Department of Radiology, Leiden University Medical Center, Leiden, The Netherlands
1 shared publication - Amear Souded Ali Jan Mohammed
School of Engineering and Material Science, Queen Mary University of London, London, UK
1 shared publication - Anantharaman Ramasamy
Cardiology, Barts Heart Centre, Barts Health NHS Trust, London, UK
1 shared publication - Attila Tóth
Semmelweis University Heart and Vascular Center, Budapest, Hungary
1 shared publication - Christos Vasileios Bourantas
Department of Cardiology, Barts Heart Centre, Barts Health NHS Trust, United Kingdom
1 shared publication - Hessam Sokooti
Medis Medical Imaging, Leiden, The Netherlands
1 shared publication
Latest Publications
- Open Access
- 13 March 2024
- Published by Springer Nature in International Journal of Computer Assisted Radiology and Surgery
- Vol. 19 (5) , 971-981
Cross-sectional angle prediction of lipid-rich and calcified tissue on computed tomography angiography images
Purpose: The assessment of vulnerable plaque characteristics and distribution is important to stratify cardiovascular risk in a patient. Computed tomography angiography (CTA) offers a promising alternative to invasive imaging but is limited by the fact that the range of Hounsfield units (HU) in lipid-rich areas overlaps with the HU range in fibrotic tissue and that the HU range of calcified plaques overlaps with the contrast within the contrast-filled lumen. This paper is to investigate whether lipid-rich and calcified plaques can be detected more accurately on cross-sectional CTA images using deep learning methodology. Methods: Two deep learning (DL) approaches are proposed, a 2.5D Dense U-Net and 2.5D Mask-RCNN, which separately perform the cross-sectional plaque detection in the Cartesian and polar domain. The spread-out view is used to evaluate and show the prediction result of the plaque regions. The accuracy and F1-score are calculated on a lesion level for the DL and conventional plaque detection methods. Results: For the lipid-rich plaques, the median and mean values of the F1-score calculated by the two proposed DL methods on 91 lesions were approximately 6 and 3 times higher than those of the conventional method. For the calcified plaques, the F1-score of the proposed methods was comparable to those of the conventional method. The median F1-score of the Dense U-Net-based method was 3% higher than that of the conventional method. Conclusion: The two methods proposed in this paper contribute to finer cross-sectional predictions of lipid-rich and calcified plaques compared to studies focusing only on longitudinal prediction. The angular prediction performance of the proposed methods outperforms the convincing conventional method for lipid-rich plaque and is comparable for calcified plaque.
- 13 March 2024
- Published by Springer Nature in International Journal of Computer Assisted Radiology and Surgery
- Vol. 19 (5) , 971-981
Open AccessCross-sectional angle prediction of lipid-rich and calcified tissue on computed tomography angiography images
Purpose: The assessment of vulnerable plaque characteristics and distribution is important to stratify cardiovascular risk in a patient. Computed tomography angiography (CTA) offers a promising alternative to invasive imaging but is limited by the fact that the range of Hounsfield units (HU) in lipid-rich areas overlaps with the HU range in fibrotic tissue and that the HU range of calcified plaques overlaps with the contrast within the contrast-filled lumen. This paper is to investigate whether lipid-rich and calcified plaques can be detected more accurately on cross-sectional CTA images using deep learning methodology. Methods: Two deep learning (DL) approaches are proposed, a 2.5D Dense U-Net and 2.5D Mask-RCNN, which separately perform the cross-sectional plaque detection in the Cartesian and polar domain. The spread-out view is used to evaluate and show the prediction result of the plaque regions. The accuracy and F1-score are calculated on a lesion level for the DL and conventional plaque detection methods. Results: For the lipid-rich plaques, the median and mean values of the F1-score calculated by the two proposed DL methods on 91 lesions were approximately 6 and 3 times higher than those of the conventional method. For the calcified plaques, the F1-score of the proposed methods was comparable to those of the conventional method. The median F1-score of the Dense U-Net-based method was 3% higher than that of the conventional method. Conclusion: The two methods proposed in this paper contribute to finer cross-sectional predictions of lipid-rich and calcified plaques compared to studies focusing only on longitudinal prediction. The angular prediction performance of the proposed methods outperforms the convincing conventional method for lipid-rich plaque and is comparable for calcified plaque.
- Open Access
- 24 November 2023
- Published by MDPI AG in Journal of Cardiovascular Development and Disease
- Vol. 10 (12) , 474
Reference Values for Inward Displacement in the Normal Left Ventricle: A Novel Method of Regional Left Ventricular Function Assessment
Background: Regional functional left ventricular (LV) assessment using current imaging techniques remains limited. Inward displacement (InD) has been developed as a novel technique to assess regional LV function via measurement of the regional displacement of the LV endocardial border across each of the 17 LV segments. Currently, normal ranges for InD are not available for clinical use. The aim of this study was to validate the normal reference limits of InD in healthy adults across all LV segments. Methods: InD was analyzed in 120 healthy subjects with a normal LV ejection fraction, using the three standard long-axis views obtained during cardiac MRI that quantified the degree of inward endocardial wall motion towards the true LV center of contraction. For all LV segments, InD was measured in mm and expressed as a percentage of the theoretical degree of maximal segment contraction towards the true LV centerline. The arithmetic average InD was obtained for each of the 17 segments. The LV was divided into three regions, obtaining average InD at the LV base (segments 1–6), mid-cavity (segments 7–12) and apex (segments 13–17). Results: Average InD was 33.4 ± 4.3%. InD was higher in basal and mid-cavity LV segments (32.8 ± 4.1% and 38.1 ± 5.8%) compared to apical LV segments (28.6 ± 7.7%). Interobserver variability correlations for InD were strong (R = 0.80, p < 0.0001). Conclusions: We provide clinically meaningful reference ranges for InD in subjects with normal LV function, which will emerge as an important screening and assessment imaging tool for a range of HFrEF therapies.
- 24 November 2023
- Published by MDPI AG in Journal of Cardiovascular Development and Disease
- Vol. 10 (12) , 474
Open AccessReference Values for Inward Displacement in the Normal Left Ventricle: A Novel Method of Regional Left Ventricular Function Assessment
Background: Regional functional left ventricular (LV) assessment using current imaging techniques remains limited. Inward displacement (InD) has been developed as a novel technique to assess regional LV function via measurement of the regional displacement of the LV endocardial border across each of the 17 LV segments. Currently, normal ranges for InD are not available for clinical use. The aim of this study was to validate the normal reference limits of InD in healthy adults across all LV segments. Methods: InD was analyzed in 120 healthy subjects with a normal LV ejection fraction, using the three standard long-axis views obtained during cardiac MRI that quantified the degree of inward endocardial wall motion towards the true LV center of contraction. For all LV segments, InD was measured in mm and expressed as a percentage of the theoretical degree of maximal segment contraction towards the true LV centerline. The arithmetic average InD was obtained for each of the 17 segments. The LV was divided into three regions, obtaining average InD at the LV base (segments 1–6), mid-cavity (segments 7–12) and apex (segments 13–17). Results: Average InD was 33.4 ± 4.3%. InD was higher in basal and mid-cavity LV segments (32.8 ± 4.1% and 38.1 ± 5.8%) compared to apical LV segments (28.6 ± 7.7%). Interobserver variability correlations for InD were strong (R = 0.80, p < 0.0001). Conclusions: We provide clinically meaningful reference ranges for InD in subjects with normal LV function, which will emerge as an important screening and assessment imaging tool for a range of HFrEF therapies.