+publisher:"Delft University of Technology" +contributor:("Vos, Frans")

Delft University of Technology

1. van Wijnen, Kimberlin (author). Detecting Perivascular Spaces: a Geodesic Deep Learning Approach.

Degree: 2018, Delft University of Technology

URL: http://resolver.tudelft.nl/uuid:0696f548-97b8-4b32-b21c-cb5b95ed02eb

► Perivascular spaces (PVS) visible on MRI are currently emerging as an important potential neuroimaging marker for several pathologies in the brain like Alzheimer’s disease and… (more)

▼ Perivascular spaces (PVS) visible on MRI are currently emerging as an important potential neuroimaging marker for several pathologies in the brain like Alzheimer’s disease and cerebral small vessel disease. PVS are fluid-filled spaces surrounding vessels as they enter the brain. Although PVS are normally not noticeable on MRI scans acquired at clinical field strengths, when these spaces increase in size they become increasingly visible and quantifiable. To study these spaces it is important to have a robust method for quantifying PVS. Manual quantification of PVS is challenging, time-consuming and subject to observer bias due to the difficulty of distinguishing PVS from mimics and the large number of PVS that can occur in MRI scans. Many promising (semi-)automated methods have been proposed recently to decrease annotation time and intra- and inter-observer variability while providing more information about EPVS. However there are still various limitations in the current methods that need to be overcome. An important limitation is that most of the methods are based on elaborate preprocessing steps, feature extraction and heuristic fine-tuning of parameters, making the use of these methods on new datasets cumbersome. Furthermore the majority of the currently proposed methods have been evaluated on small sets of barely 30 images, as most of these methods aim to segment PVS and require voxel-wise annotations for evaluation. In this thesis we propose a method for automated detection of perivascular spaces that combines a convolutional neural network and geodesic distance transform (GDT). We propose to use dot annotations instead of voxel-wise segmentations as this is less time-consuming than fully segmenting PVS while still providing the location of PVS. This enables us to use a considerably larger dataset with ground truth locations than is used in all previously proposed (semi-)automatic methods that provide the location of PVS. We investigated two approaches of using geodesic distance transform to optimize the CNN to detect PVS. The first approach focuses on optimizing the CNN for voxel-wise regression of the geodesic distance map (GDM) computed from the dots and the intensity image. The second approach aims to predict segmentations of the PVS using a CNN that is trained on approximated segmentations obtained by thresholding GDMs. We use 1202 proton density-weighted (PDw) MRI scans to develop our methods and 1000 other scans are used to evaluate the performance of the methods. We show that our methods match human intra-rater performance on detecting PVS without the need for any user interaction. Additionally we show that GDMs are extremely useful for capturing complex morphologies when computed from dot annotations. Our experiments indicate that GDMs can be used to provide valuable additional information to CNNs during training. Advisors/Committee Members: Dubost, Florian (mentor), de Bruijne, Marleen (mentor), Niessen, Wiro (graduation committee), Vos, Frans (graduation committee), Vilanova Bartroli, Anna (graduation committee), Staring, Marius (graduation committee), Delft University of Technology (degree granting institution).

Subjects/Keywords: Deep learning; perivascular spaces; detection; geodesic distance transform; dot annotations; weighted loss

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

van Wijnen, K. (. (2018). Detecting Perivascular Spaces: a Geodesic Deep Learning Approach. (Masters Thesis). Delft University of Technology. Retrieved from http://resolver.tudelft.nl/uuid:0696f548-97b8-4b32-b21c-cb5b95ed02eb

Chicago Manual of Style (16^th Edition):

van Wijnen, Kimberlin (author). “Detecting Perivascular Spaces: a Geodesic Deep Learning Approach.” 2018. Masters Thesis, Delft University of Technology. Accessed February 26, 2021. http://resolver.tudelft.nl/uuid:0696f548-97b8-4b32-b21c-cb5b95ed02eb.

MLA Handbook (7^th Edition):

van Wijnen, Kimberlin (author). “Detecting Perivascular Spaces: a Geodesic Deep Learning Approach.” 2018. Web. 26 Feb 2021.

Vancouver:

van Wijnen K(. Detecting Perivascular Spaces: a Geodesic Deep Learning Approach. [Internet] [Masters thesis]. Delft University of Technology; 2018. [cited 2021 Feb 26]. Available from: http://resolver.tudelft.nl/uuid:0696f548-97b8-4b32-b21c-cb5b95ed02eb.

Council of Science Editors:

van Wijnen K(. Detecting Perivascular Spaces: a Geodesic Deep Learning Approach. [Masters Thesis]. Delft University of Technology; 2018. Available from: http://resolver.tudelft.nl/uuid:0696f548-97b8-4b32-b21c-cb5b95ed02eb

Delft University of Technology

2. Driever, Theo (author). Improving the reproducibility of BOLD rs-fMRI signal by selective data elimination.

Degree: 2018, Delft University of Technology

URL: http://resolver.tudelft.nl/uuid:ce07f35d-12b5-48d8-98e7-794f045bcfd2

► Connectivity mapping with resting state functional magnetic resonance imaging (rs-fMRI) is rapidly developing and has shown great promise for clinical applications. Before successful implementation in… (more)

▼ Connectivity mapping with resting state functional magnetic resonance imaging (rs-fMRI) is rapidly developing and has shown great promise for clinical applications. Before successful implementation in clinical setting, it is key to evaluate the long-term reproducibility of the functional connectivity profiles. To this end, the reproducibility of rs-fMRI data is studied in this work. The main research question revolves around the improvement of the overall reproducibility by selectively omitting single components (either nodes or elements) from BOLD rs-fMRI connectivity matrices (CM’s). The scans of the subjects are parcellated using four different schemes, which are all analysed throughout this work. A reproducibility study is carried out on a dataset of 37 subjects that are scanned twice within 2 weeks on average. The inter-subject intraclass correlation coefficient (ICC) is used to quantify component reproducibility within the dataset. An algorithm is designed to quantify which component has the lowest inter-subject ICC, which is then eliminated from all CM’s in the dataset. After every single component elimination, the intra-subject ICC is computed for every subject to quantify the reproducibility, and a matching accuracy (MA) test is performed on the set to quantify the distinctive power of the CM’s. The order in which components are eliminated and its effect on the overall reproducibility is tested by applying this to a larger test set of longitudinal data. To this end, a dataset of 521 subjects is used to quantify the reproducibility of the CM’s after iteratively removing components in the order that is found in the reproducibility study. This larger dataset of 521 subjects is analysed, along with 4 subsets, namely: sex based, age based, interscan time based and based on the grounds for exclusion. The latter is a subset where the quality of the rs-fMRI scans could not be assured due to pathologies or excessive motion during image acquisition. No significant difference is found within the sex-based subsets, and no relation between the reproducibility and the interscan time (within the range that is assessed in this work, namely 5 years) is found. Significantly lower intra-subject ICC’s are found for the subjects whose scan quality was subpar, due to excessive motion or pathology. For the age-based subset analysis, it is reported that reproducibility decreases with age. The node removal algorithm clearly outperforms the element removal algorithm when looking at the intra-subject ICC. As the element removal algorithm can increase the intra-subject ICC by roughly 0.1, whereas the node removal algorithm manages to increase the intra-subject ICC of roughly 0.3. The MA, which is used as to quantify the distinguishing power between various CM’s, is seen to increase from 82.4% to the maximum of 98.7% correctly matched subjects for the RSS100 parcellation scheme within the reproducibility study. Aside from the element removal within the reproducibility study, the matching accuracy is not improved for… Advisors/Committee Members: Vos, Frans (mentor), van Valenberg, Willem (mentor), Delft University of Technology (degree granting institution).

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Driever, T. (. (2018). Improving the reproducibility of BOLD rs-fMRI signal by selective data elimination. (Masters Thesis). Delft University of Technology. Retrieved from http://resolver.tudelft.nl/uuid:ce07f35d-12b5-48d8-98e7-794f045bcfd2

Chicago Manual of Style (16^th Edition):

Driever, Theo (author). “Improving the reproducibility of BOLD rs-fMRI signal by selective data elimination.” 2018. Masters Thesis, Delft University of Technology. Accessed February 26, 2021. http://resolver.tudelft.nl/uuid:ce07f35d-12b5-48d8-98e7-794f045bcfd2.

MLA Handbook (7^th Edition):

Driever, Theo (author). “Improving the reproducibility of BOLD rs-fMRI signal by selective data elimination.” 2018. Web. 26 Feb 2021.

Vancouver:

Driever T(. Improving the reproducibility of BOLD rs-fMRI signal by selective data elimination. [Internet] [Masters thesis]. Delft University of Technology; 2018. [cited 2021 Feb 26]. Available from: http://resolver.tudelft.nl/uuid:ce07f35d-12b5-48d8-98e7-794f045bcfd2.

Council of Science Editors:

Driever T(. Improving the reproducibility of BOLD rs-fMRI signal by selective data elimination. [Masters Thesis]. Delft University of Technology; 2018. Available from: http://resolver.tudelft.nl/uuid:ce07f35d-12b5-48d8-98e7-794f045bcfd2

Delft University of Technology

3. van Hoek, Bob (author). MR reconstruction of FLAIR weighted images with simulated lesions.: A comparison between Compressed Sensing and a Recurrent Inference Machine.

Degree: 2019, Delft University of Technology

URL: http://resolver.tudelft.nl/uuid:3aa8c68e-3135-4b86-b256-8c853a409960

► Background: For both hospitals and patients it would be beneficial if the scan time of MR images could be reduced. At the moment, Compressed Sensing… (more)

▼ Background: For both hospitals and patients it would be beneficial if the scan time of MR images could be reduced. At the moment, Compressed Sensing (CS) is introduced to reduce the scan time, however, new methods are developed such as a deep learning method, called the Recurrent Inference Machine (RIM). In this study the effect of reconstructing undersampled MRI images with lesions, using the RIM and CS, was evaluated. In data of a healthy control, lesions were simulated. Evaluation is done by checking if the lesion has the correct intensity and shape after reconstruction of undersampled data. Methods: In raw data of a healthy control lesions were simulated. To test the RIM and CS, the images with lesions where first undersampled 4x, 6x, 8x and 10x. After undersampling, the images were reconstructed with both RIM and CS. First, the peak intensity difference was measured between the reference image (with simulated lesions) and reconstructed images for both RIM and CS. Second, one lesion was undersampled ten times with different undersampling masks creating different noise, for 3 different acceleration factors (4x, 6x, 8x). These lesions were reconstructed with both RIM and CS. The maximum intensity difference between reference and reconstructed image was measured and averaged over the ten different undersampled images. Results: In total seven different lesions were simulated in a healthy control with different intensities varying between 10% and 100% of the GM-lesion intensity in a FLAIR weighted scan. The intensities of all lesions were more accurately reconstructed with the RIM compared to CS at higher acceleration factors: the average intensity per lesions after 10 times reconstruction with RIM was more equal to the correct intensity compared to the reconstruction with CS. Conclusion: The RIM shows robust and accurate results on data with simulated lesions. Moreover, the RIM outperformed CS on data that was more undersampled. Therefore, the RIM may be used for reconstruction of MRI data that is acquired with shorter acquisition time. And since the reconstruction time is better, it could replace CS in the future. However, before the RIM could be used, further evaluations on actual patient data are needed. Advisors/Committee Members: Vos, Frans (mentor), Caan, Matthan WA (graduation committee), Delft University of Technology (degree granting institution).

Subjects/Keywords: MRI; Image Reconstruction; Deep Learning; Lesion Simulation

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

van Hoek, B. (. (2019). MR reconstruction of FLAIR weighted images with simulated lesions.: A comparison between Compressed Sensing and a Recurrent Inference Machine. (Masters Thesis). Delft University of Technology. Retrieved from http://resolver.tudelft.nl/uuid:3aa8c68e-3135-4b86-b256-8c853a409960

Chicago Manual of Style (16^th Edition):

van Hoek, Bob (author). “MR reconstruction of FLAIR weighted images with simulated lesions.: A comparison between Compressed Sensing and a Recurrent Inference Machine.” 2019. Masters Thesis, Delft University of Technology. Accessed February 26, 2021. http://resolver.tudelft.nl/uuid:3aa8c68e-3135-4b86-b256-8c853a409960.

MLA Handbook (7^th Edition):

van Hoek, Bob (author). “MR reconstruction of FLAIR weighted images with simulated lesions.: A comparison between Compressed Sensing and a Recurrent Inference Machine.” 2019. Web. 26 Feb 2021.

Vancouver:

van Hoek B(. MR reconstruction of FLAIR weighted images with simulated lesions.: A comparison between Compressed Sensing and a Recurrent Inference Machine. [Internet] [Masters thesis]. Delft University of Technology; 2019. [cited 2021 Feb 26]. Available from: http://resolver.tudelft.nl/uuid:3aa8c68e-3135-4b86-b256-8c853a409960.

Council of Science Editors:

van Hoek B(. MR reconstruction of FLAIR weighted images with simulated lesions.: A comparison between Compressed Sensing and a Recurrent Inference Machine. [Masters Thesis]. Delft University of Technology; 2019. Available from: http://resolver.tudelft.nl/uuid:3aa8c68e-3135-4b86-b256-8c853a409960

Delft University of Technology

4. Lelekas, Ioannis (author). Top-Down Networks: A coarse-to-fine reimagination of CNNs.

Degree: 2020, Delft University of Technology

URL: http://resolver.tudelft.nl/uuid:11888a7b-1e54-424d-9daa-8ff48de58345

► Biological vision adopts a coarse-to-fine information processing pathway, from initial visual detection and binding of salient features of a visual scene, to the enhanced and… (more)

Subjects/Keywords: Computer Vision; Deep Learning; Convolutional Neural Networks; Top-Down; Fine-to-Coarse; Coarse-to-Fine; Adversarial attacks; Adversarial robustness; Gradcam; Object localization

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Lelekas, I. (. (2020). Top-Down Networks: A coarse-to-fine reimagination of CNNs. (Masters Thesis). Delft University of Technology. Retrieved from http://resolver.tudelft.nl/uuid:11888a7b-1e54-424d-9daa-8ff48de58345

Chicago Manual of Style (16^th Edition):

Lelekas, Ioannis (author). “Top-Down Networks: A coarse-to-fine reimagination of CNNs.” 2020. Masters Thesis, Delft University of Technology. Accessed February 26, 2021. http://resolver.tudelft.nl/uuid:11888a7b-1e54-424d-9daa-8ff48de58345.

MLA Handbook (7^th Edition):

Lelekas, Ioannis (author). “Top-Down Networks: A coarse-to-fine reimagination of CNNs.” 2020. Web. 26 Feb 2021.

Vancouver:

Lelekas I(. Top-Down Networks: A coarse-to-fine reimagination of CNNs. [Internet] [Masters thesis]. Delft University of Technology; 2020. [cited 2021 Feb 26]. Available from: http://resolver.tudelft.nl/uuid:11888a7b-1e54-424d-9daa-8ff48de58345.

Council of Science Editors:

Lelekas I(. Top-Down Networks: A coarse-to-fine reimagination of CNNs. [Masters Thesis]. Delft University of Technology; 2020. Available from: http://resolver.tudelft.nl/uuid:11888a7b-1e54-424d-9daa-8ff48de58345

Delft University of Technology

5. Ragunathan, Srinidhi (author). Segmentation of Carpal Bones: Based on Statistical Shape Models using Spherical Harmonics.

Degree: 2019, Delft University of Technology

URL: http://resolver.tudelft.nl/uuid:d31b9623-9db8-4224-a8c3-0e74d8848bf4

►

A study has been conducted on the application of Spherical Harmonics based Statistical Shape Modelling for Image Segmentation. This study is focused on the segmentation… (more)

Subjects/Keywords: Image Segmentation; Statistical Shape Model; Spherical harmonics

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Ragunathan, S. (. (2019). Segmentation of Carpal Bones: Based on Statistical Shape Models using Spherical Harmonics. (Masters Thesis). Delft University of Technology. Retrieved from http://resolver.tudelft.nl/uuid:d31b9623-9db8-4224-a8c3-0e74d8848bf4

Chicago Manual of Style (16^th Edition):

Ragunathan, Srinidhi (author). “Segmentation of Carpal Bones: Based on Statistical Shape Models using Spherical Harmonics.” 2019. Masters Thesis, Delft University of Technology. Accessed February 26, 2021. http://resolver.tudelft.nl/uuid:d31b9623-9db8-4224-a8c3-0e74d8848bf4.

MLA Handbook (7^th Edition):

Ragunathan, Srinidhi (author). “Segmentation of Carpal Bones: Based on Statistical Shape Models using Spherical Harmonics.” 2019. Web. 26 Feb 2021.

Vancouver:

Ragunathan S(. Segmentation of Carpal Bones: Based on Statistical Shape Models using Spherical Harmonics. [Internet] [Masters thesis]. Delft University of Technology; 2019. [cited 2021 Feb 26]. Available from: http://resolver.tudelft.nl/uuid:d31b9623-9db8-4224-a8c3-0e74d8848bf4.

Council of Science Editors:

Ragunathan S(. Segmentation of Carpal Bones: Based on Statistical Shape Models using Spherical Harmonics. [Masters Thesis]. Delft University of Technology; 2019. Available from: http://resolver.tudelft.nl/uuid:d31b9623-9db8-4224-a8c3-0e74d8848bf4

Delft University of Technology

6. Wu, Yulun (author). Long-term Effect of MPH on White Matter Tracts of Adults with ADHD: An Application of Consistent Model Selection followed by TBSS.

Degree: 2018, Delft University of Technology

URL: http://resolver.tudelft.nl/uuid:e06f218d-b22b-410c-8041-3199ff0acdaa

►

We focused on analysis of long-term medication influenced white matter tracts based on diffusion-weighted MRI brain images of patients with ADHD disorder. We applied a… (more)

Subjects/Keywords: diffusion MRI; DTI; model selection; ADHD disorder; white matter

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Wu, Y. (. (2018). Long-term Effect of MPH on White Matter Tracts of Adults with ADHD: An Application of Consistent Model Selection followed by TBSS. (Masters Thesis). Delft University of Technology. Retrieved from http://resolver.tudelft.nl/uuid:e06f218d-b22b-410c-8041-3199ff0acdaa

Chicago Manual of Style (16^th Edition):

Wu, Yulun (author). “Long-term Effect of MPH on White Matter Tracts of Adults with ADHD: An Application of Consistent Model Selection followed by TBSS.” 2018. Masters Thesis, Delft University of Technology. Accessed February 26, 2021. http://resolver.tudelft.nl/uuid:e06f218d-b22b-410c-8041-3199ff0acdaa.

MLA Handbook (7^th Edition):

Wu, Yulun (author). “Long-term Effect of MPH on White Matter Tracts of Adults with ADHD: An Application of Consistent Model Selection followed by TBSS.” 2018. Web. 26 Feb 2021.

Vancouver:

Wu Y(. Long-term Effect of MPH on White Matter Tracts of Adults with ADHD: An Application of Consistent Model Selection followed by TBSS. [Internet] [Masters thesis]. Delft University of Technology; 2018. [cited 2021 Feb 26]. Available from: http://resolver.tudelft.nl/uuid:e06f218d-b22b-410c-8041-3199ff0acdaa.

Council of Science Editors:

Wu Y(. Long-term Effect of MPH on White Matter Tracts of Adults with ADHD: An Application of Consistent Model Selection followed by TBSS. [Masters Thesis]. Delft University of Technology; 2018. Available from: http://resolver.tudelft.nl/uuid:e06f218d-b22b-410c-8041-3199ff0acdaa

Delft University of Technology

7. Undetermined, U. (author). Correlating scored daily anatomical changes to in-vivo EPID dosimetry and cone beam CT based dose calculations: A retrospective study.

Degree: 2017, Delft University of Technology

URL: http://resolver.tudelft.nl/uuid:b69226f9-c00b-4137-819c-7e6a6ea4aea4

► At the Antoni van Leeuwenhoek Hospital/Dutch Cancer Institute (NKI-AvL) in Amsterdam, inter-fractional anatomical changes during the course of radiotherapy are monitored using cone beam CT… (more)

▼ At the Antoni van Leeuwenhoek Hospital/Dutch Cancer Institute (NKI-AvL) in Amsterdam, inter-fractional anatomical changes during the course of radiotherapy are monitored using cone beam CT scans, taken prior to irradiation. These scans are assessed visually, and the fractions are scored according to a 'traffic light protocol'. Based on the magnitude of change, a green, yellow, orange or red colour, in increasing order of severity, is assigned to the fraction. The goal of this work was to ascertain if the colour of the traffic lights, which were assumed to be indicators of anatomical change, correlate to changes in dosimetry for H\&N VMAT treatments, as well as lung IMRT treatments. The in-vivo EPID dose was reconstructed in the patient for each fraction, using a back-projection algorithm that is used clinically at the NKI. Calibrated CBCTs of each fraction were obtained using DIR or anti-scatter grid methods researched at the NKI, which were then imported to a TPS to obtain the fraction dose. These two modes of dosimetry were compared against each other, as well as against the traffic light colours for H\&N treatments. For lung treatments, due to unavailability of CBCT based dose data, only EPID dosimetry was used; two different models of the back-projection algorithm were compared in this case. γ index and DVH metrics were used to express deviation in the dose distributions. Deviations over successive fractions for 18 H\&N treatments were studied. The traffic light protocol correlated poorly with CBCT based dose and EPID reconstructed dose (ρ = 0.33 and 0.35 respectively). The CBCT and EPID dose correlated with each other quite strongly (ρ = 0.72), however the EPID dose was more sensitive in its fluctuations. Deviations for 98 IMRT lung fractions were studied. The traffic light protocol correlated even more poorly with the EPID reconstructed dose than in the H\&N study (ρ = 0.18). The calculated transmission model of the EPID was found to exaggerate the deviations in comparison to the measured transmission model. Since VMAT innately uses the calculated transmission model, this explains the sensitivity of the EPID results seen in the H\&N study. We have shown that the traffic light protocol does not correlate with dosimetric changes, due to differences in assessment criteria. 15 out of 18 H\&N treatments showed moderate (ρ ≥ 0.4), if not strong, correlations between deviations of EPID reconstructed dose and CBCT based dose, strengthening the EPID's applicability for in-vivo dosimetry. Advisors/Committee Members: Schaart, Dennis (mentor), Mans, Anton (mentor), Olaciregui-Ruiz, Igor (mentor), Vos, Frans (graduation committee), Perko, Zoltan (graduation committee), Delft University of Technology (degree granting institution).

Subjects/Keywords: Radiotherapy; epid dosimetry; cone beam CT

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Undetermined, U. (. (2017). Correlating scored daily anatomical changes to in-vivo EPID dosimetry and cone beam CT based dose calculations: A retrospective study. (Masters Thesis). Delft University of Technology. Retrieved from http://resolver.tudelft.nl/uuid:b69226f9-c00b-4137-819c-7e6a6ea4aea4

Chicago Manual of Style (16^th Edition):

Undetermined, U (author). “Correlating scored daily anatomical changes to in-vivo EPID dosimetry and cone beam CT based dose calculations: A retrospective study.” 2017. Masters Thesis, Delft University of Technology. Accessed February 26, 2021. http://resolver.tudelft.nl/uuid:b69226f9-c00b-4137-819c-7e6a6ea4aea4.

MLA Handbook (7^th Edition):

Undetermined, U (author). “Correlating scored daily anatomical changes to in-vivo EPID dosimetry and cone beam CT based dose calculations: A retrospective study.” 2017. Web. 26 Feb 2021.

Vancouver:

Undetermined U(. Correlating scored daily anatomical changes to in-vivo EPID dosimetry and cone beam CT based dose calculations: A retrospective study. [Internet] [Masters thesis]. Delft University of Technology; 2017. [cited 2021 Feb 26]. Available from: http://resolver.tudelft.nl/uuid:b69226f9-c00b-4137-819c-7e6a6ea4aea4.

Council of Science Editors:

Undetermined U(. Correlating scored daily anatomical changes to in-vivo EPID dosimetry and cone beam CT based dose calculations: A retrospective study. [Masters Thesis]. Delft University of Technology; 2017. Available from: http://resolver.tudelft.nl/uuid:b69226f9-c00b-4137-819c-7e6a6ea4aea4

Delft University of Technology

8. Versteeg, Edwin (author). Probabilistic tractography for complex fiber orientations with automatic model selection: A tool to study structural connectivity in stroke patients.

Degree: 2017, Delft University of Technology

URL: http://resolver.tudelft.nl/uuid:1d7390d0-005f-4ee1-bb95-cb4c6715d29a

► Stroke is one of the leading causes of both death and disability in the world. Consequently, the processes underlying motor recovery are a hot research… (more)

▼ Stroke is one of the leading causes of both death and disability in the world. Consequently, the processes underlying motor recovery are a hot research topic. Electroencephalography (EEG) and diffusion weighted magnetic resonance imaging (dMRI) are two modalities that can be used to find functional and structural predictors for this motor recovery, respectively. Specifically, EEG measures the sources of activity (dipoles) in the brain while dMRI provides estimates of the properties of white matter (WM) tracts such as the fiber orientation. The estimated fiber orientations can be used to reconstruct WM connections in the brain by performing fiber tractography. In this thesis, we aim to introduce a framework for model selection and probabilistic tractography with parsimonious model selection. Practically, we use a range of multi-tensor models to cope with regions with multiple fiber populations. Furthermore, our probabilistic tractography uses the Cram\'er-Rao lower bound to capture the uncertainty in the fiber orientations. We mitigate the effect of overfitting by using a model selection method that incorporates the ICOMP-TKLD criterion to determine the most appropriate tensor model in each voxel. Ultimately, this framework can be applied to data from stroke patients and combined with functional regions obtained from EEG. We assessed the performance of the model selection method by investigating the influence of b-value and noise on the ability to detect crossing fibers in the fibercup phantom and human data. In the phantom, our model selection reconstructed all the crossings for the b-value combination of 1500 and \SI{2000}{\s\per\mm\squared} and at a signal-to-noise-ratio (SNR) comparable to clinical acquisitions. Moreover, our model selection method was able to identify the crossing of the corpus callosum and corticospinal tract in the human data. A range of step sizes and curvature thresholds was used to investigate the sensitivity of our tractography to its input parameters. In general, a smaller step size and lower curvature thresholds resulted in more deterministic behavior, while a larger step sizes and higher curvature thresholds led to more probabilistic behavior and deeper propagation into the gray matter in human data. We compared the performance of our framework and the open source diffusion MRI toolkit Camino on the fibercup phantom and healthy control data. In this comparison, our framework performed better in curved bundles and reconstructed more lateral projections of the corpus callosum. Lastly, we explored the subdivision of the brain into modules for stroke patients and healthy controls, by combining our framework with sources obtained from EEG. Fewer modules were found in the patient group, which might be attributed to a change in structural connections after stroke. Altogether, we have shown that our framework was able to select the appropriate diffusion models in crossing fiber regions and track across these crossings both in a phantom and… Advisors/Committee Members: Vos, Frans (mentor), Filatova, Lena (mentor), Delft University of Technology (degree granting institution).

Subjects/Keywords: Magnetic Resonance Imaging; Diffusion tensor; Tractography

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Versteeg, E. (. (2017). Probabilistic tractography for complex fiber orientations with automatic model selection: A tool to study structural connectivity in stroke patients. (Masters Thesis). Delft University of Technology. Retrieved from http://resolver.tudelft.nl/uuid:1d7390d0-005f-4ee1-bb95-cb4c6715d29a

Chicago Manual of Style (16^th Edition):

Versteeg, Edwin (author). “Probabilistic tractography for complex fiber orientations with automatic model selection: A tool to study structural connectivity in stroke patients.” 2017. Masters Thesis, Delft University of Technology. Accessed February 26, 2021. http://resolver.tudelft.nl/uuid:1d7390d0-005f-4ee1-bb95-cb4c6715d29a.

MLA Handbook (7^th Edition):

Versteeg, Edwin (author). “Probabilistic tractography for complex fiber orientations with automatic model selection: A tool to study structural connectivity in stroke patients.” 2017. Web. 26 Feb 2021.

Vancouver:

Versteeg E(. Probabilistic tractography for complex fiber orientations with automatic model selection: A tool to study structural connectivity in stroke patients. [Internet] [Masters thesis]. Delft University of Technology; 2017. [cited 2021 Feb 26]. Available from: http://resolver.tudelft.nl/uuid:1d7390d0-005f-4ee1-bb95-cb4c6715d29a.

Council of Science Editors:

Versteeg E(. Probabilistic tractography for complex fiber orientations with automatic model selection: A tool to study structural connectivity in stroke patients. [Masters Thesis]. Delft University of Technology; 2017. Available from: http://resolver.tudelft.nl/uuid:1d7390d0-005f-4ee1-bb95-cb4c6715d29a

Delft University of Technology

9. Konduri, Praneeta (author). A Planning Tool for Left Ventricular Reconstruction in Patients with Severe Ischemic Cardiomyopathy.

Degree: 2017, Delft University of Technology

URL: http://resolver.tudelft.nl/uuid:3483d327-dbab-40ad-80ba-1fe1c46f9003

►

Surgical ventricular reconstruction aims to restore the ideal left ventricular geometry and function and is used as a treatment modality for patients with severe ischemic… (more)

▼

Surgical ventricular reconstruction aims to restore the ideal left ventricular geometry and function and is used as a treatment modality for patients with severe ischemic cardiomyopathy. This study addresses the clinical need for in-silico modelling to estimate the effect of left ventricular reconstruction through Revivent Myocardial Anchoring System on the function and geometry of the residual left ventricle. The planning tool developed in this study corrects for slice misalignment produced due to breathing motion and patient movement during Cardiac MR image acquisition. The extent and the location of the scar are identified on the contrast enhanced Cardiac MR images and subsequently used to classify the left ventricular short axis contour points into scarred and healthy segments. The reconstruction surgery is simulated by estimating each short axis contour of the residual LV as a circle obtained from the healthy segment. Functional analysis consisted of comparing the simulated residual left ventricular volumes at end-diastolic and end-systolic phase, stroke volume and ejection fraction with the baseline characteristics. Geometrical analysis consisted of quantifying the occlusion of the Right Ventricular Outflow Tract by the plicated scar and comparing the curvedness values of the residual LV with two geometrical models - Modified Simpson’s Model and Biplane Ellipsoid model. The required functional end-points are met for all four patients. A more localized approach is required for the geometrical analysis. The presented approach shows promising results but needs to be clinically validated by comparing with a larger database of post surgical scans to obtain higher accuracy and a more comprehensive understanding of the surgery.

Biomedical Engineering

Advisors/Committee Members: Marquering, Henk A. (mentor), Vos, Frans (mentor), Dankelman, Jenny (graduation committee), Sarkalkan, Nazli (graduation committee), Delft University of Technology (degree granting institution).

Subjects/Keywords: Surgical ventricular reconstruction; Planning tool; Ischemic Cardiomyopathy

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Konduri, P. (. (2017). A Planning Tool for Left Ventricular Reconstruction in Patients with Severe Ischemic Cardiomyopathy. (Masters Thesis). Delft University of Technology. Retrieved from http://resolver.tudelft.nl/uuid:3483d327-dbab-40ad-80ba-1fe1c46f9003

Chicago Manual of Style (16^th Edition):

Konduri, Praneeta (author). “A Planning Tool for Left Ventricular Reconstruction in Patients with Severe Ischemic Cardiomyopathy.” 2017. Masters Thesis, Delft University of Technology. Accessed February 26, 2021. http://resolver.tudelft.nl/uuid:3483d327-dbab-40ad-80ba-1fe1c46f9003.

MLA Handbook (7^th Edition):

Konduri, Praneeta (author). “A Planning Tool for Left Ventricular Reconstruction in Patients with Severe Ischemic Cardiomyopathy.” 2017. Web. 26 Feb 2021.

Vancouver:

Konduri P(. A Planning Tool for Left Ventricular Reconstruction in Patients with Severe Ischemic Cardiomyopathy. [Internet] [Masters thesis]. Delft University of Technology; 2017. [cited 2021 Feb 26]. Available from: http://resolver.tudelft.nl/uuid:3483d327-dbab-40ad-80ba-1fe1c46f9003.

Council of Science Editors:

Konduri P(. A Planning Tool for Left Ventricular Reconstruction in Patients with Severe Ischemic Cardiomyopathy. [Masters Thesis]. Delft University of Technology; 2017. Available from: http://resolver.tudelft.nl/uuid:3483d327-dbab-40ad-80ba-1fe1c46f9003

Delft University of Technology

10. Wang, Johnny (author). Grey Matter Age Prediction as a Biomarker for Risk of Dementia: A Population-based Study.

Degree: 2019, Delft University of Technology

URL: http://resolver.tudelft.nl/uuid:1fda41dd-745e-4d4d-8098-d9212148153a

►

The gap between predicted brain age and chronological age could serve as biomarker for early-stage neurodegeneration and as potentially as a risk indicator for dementia.… (more)

▼

The gap between predicted brain age and chronological age could serve as biomarker for early-stage neurodegeneration and as potentially as a risk indicator for dementia. We assess the utility of this age gap as a risk biomarker for incident dementia in a general elderly population. The brain age is estimated from longitudinal brain magnetic resonance imaging (MRI) data using deep learning models. From the population-based Rotterdam Study, 5656 dementia-free and stroke-free participants (mean age 64.67±9.82, 54.73% women) underwent brain MRI at 1.5T, including three-dimensional (3D) T1-weighted sequence, between 2006 and 2015. All participants were followed for incident dementia until 2016. During 6.66±2.46 years of follow-up, 159 subjects developed dementia. The entire dataset was split into control (N=5497) and incident dementia (N=159) groups. We then built a convolutional neural network (CNN) model trained on the control group to predict brain age based on brain MRI. Model prediction performance was measured in mean absolute error MAE=4.45±3.59 years of brain age prediction. Reproducibility of prediction was tested using the intra-class correlation coefficient ICC=0.97 (95% confidence interval CI=0.96-0.98), computed on a subset of 80 subjects. Hereafter, we investigated the gap between model predicted age and chronological age of the incident dementia group data, compared to control group. Logistic regressions and Cox proportional hazards models were used to assess the association of the age gap with incident dementia, adjusted for years of education, ApoE4 allele carriership, GM and intracranial volume. These models showed that the age gap was significantly related to incident dementia (odds ratio OR=1.11 and 95% confidence intervals CI=1.05-1.16; hazard ratio HR=1.11 and 95% CI=1.06-1.15, respectively). Additionally, we computed the attention maps of CNN, which shows the importance of brain regions for age prediction. These were particularly focused on the amygdalae and hippocampi. We show that the gap between predicted and chronological brain age is a biomarker, associated with a risk of dementia development. This suggests that it can potentially be used as a complimentary biomarker for early-stage dementia risk screening.

Mechanical Engineering

Advisors/Committee Members: Niessen, Wiro (mentor), Kooij, Julian (graduation committee), Vos, Frans (graduation committee), Roshchupkin, Gennady V. (graduation committee), Delft University of Technology (degree granting institution).

Subjects/Keywords: Deep Learning; Age prediction; Dementia; Biomarker; Brain; Magnetic Resonance Imaging; Voxel-based morphometry; Survival analysis

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Wang, J. (. (2019). Grey Matter Age Prediction as a Biomarker for Risk of Dementia: A Population-based Study. (Masters Thesis). Delft University of Technology. Retrieved from http://resolver.tudelft.nl/uuid:1fda41dd-745e-4d4d-8098-d9212148153a

Chicago Manual of Style (16^th Edition):

Wang, Johnny (author). “Grey Matter Age Prediction as a Biomarker for Risk of Dementia: A Population-based Study.” 2019. Masters Thesis, Delft University of Technology. Accessed February 26, 2021. http://resolver.tudelft.nl/uuid:1fda41dd-745e-4d4d-8098-d9212148153a.

MLA Handbook (7^th Edition):

Wang, Johnny (author). “Grey Matter Age Prediction as a Biomarker for Risk of Dementia: A Population-based Study.” 2019. Web. 26 Feb 2021.

Vancouver:

Wang J(. Grey Matter Age Prediction as a Biomarker for Risk of Dementia: A Population-based Study. [Internet] [Masters thesis]. Delft University of Technology; 2019. [cited 2021 Feb 26]. Available from: http://resolver.tudelft.nl/uuid:1fda41dd-745e-4d4d-8098-d9212148153a.

Council of Science Editors:

Wang J(. Grey Matter Age Prediction as a Biomarker for Risk of Dementia: A Population-based Study. [Masters Thesis]. Delft University of Technology; 2019. Available from: http://resolver.tudelft.nl/uuid:1fda41dd-745e-4d4d-8098-d9212148153a

Delft University of Technology

11. Wu, Zhiyi (author). Functional Liver Partition of DCE-MRI.

Degree: 2017, Delft University of Technology

URL: http://resolver.tudelft.nl/uuid:83965250-3834-4643-a54d-842e87e1602e

The proposed functional liver segments partition method based on DCE-MRI is introduced in this thesis.

Biomedical Engineering

Advisors/Committee Members: Vos, Frans (mentor), Zhang, Tian (mentor), Delft University of Technology (degree granting institution).

Subjects/Keywords: functional liver partition; DCE-MRI

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Wu, Z. (. (2017). Functional Liver Partition of DCE-MRI. (Masters Thesis). Delft University of Technology. Retrieved from http://resolver.tudelft.nl/uuid:83965250-3834-4643-a54d-842e87e1602e

Chicago Manual of Style (16^th Edition):

Wu, Zhiyi (author). “Functional Liver Partition of DCE-MRI.” 2017. Masters Thesis, Delft University of Technology. Accessed February 26, 2021. http://resolver.tudelft.nl/uuid:83965250-3834-4643-a54d-842e87e1602e.

MLA Handbook (7^th Edition):

Wu, Zhiyi (author). “Functional Liver Partition of DCE-MRI.” 2017. Web. 26 Feb 2021.

Vancouver:

Wu Z(. Functional Liver Partition of DCE-MRI. [Internet] [Masters thesis]. Delft University of Technology; 2017. [cited 2021 Feb 26]. Available from: http://resolver.tudelft.nl/uuid:83965250-3834-4643-a54d-842e87e1602e.

Council of Science Editors:

Wu Z(. Functional Liver Partition of DCE-MRI. [Masters Thesis]. Delft University of Technology; 2017. Available from: http://resolver.tudelft.nl/uuid:83965250-3834-4643-a54d-842e87e1602e

Delft University of Technology

12. Meij, Senna (author). The applicability of deep learning to detect the progress of laparoscopic surgery using video recordings.

Degree: 2019, Delft University of Technology

URL: http://resolver.tudelft.nl/uuid:28f96ac7-f5ae-43af-9ba0-14832af5c103

►

The operating room is one of the most complex and expensive environments in the hospital. Research has been focusing on improving the efficient use of… (more)

▼

The operating room is one of the most complex and expensive environments in the hospital. Research has been focusing on improving the efficient use of the OR time, for instance by using intraoperative data to update the planning of the OR during the day. This thesis used a deep learning network to automatically recognize surgical tools and pre-defined surgical phases present in the recordings, to ultimately track the progress of the procedure. The aim of this thesis is to assess the performance and applicability of this deep learning method for the use of image recognition in a medical environment. To ultimately predict the remaining surgery duration and improve the efficiency of the OR planning. Two datasets of laparoscopic recordings were used, one containing laparoscopic cholecystectomies and one containing total laparoscopic hysterectomies. The surgical tools and the pre-defined phases of the procedure were annotated in every recording, after which the deep learning network was trained with this data. The performance of the network was tested in multiple experiments. The results showed that the performance of the deep learning network was promising and in line with published literature, but that the results varied between recordings. An experiment using three different sized datasets showed that a larger dataset corresponded with the best results and results that varied the least between recordings. Testing the generalizability of the network showed that a network trained on one type of surgery can also be used to recognize similar tools in a different type of surgery. Important is that the tools have the same design. It was found that the most important resources for a project like this are a dedicated hardware with image recognition software and time. This thesis showed the applicability of a deep learning network to automatically recognize the progress of a surgery and provided insight into the steps that need to be taken to use it on a larger scale.

BioMedical Engineering

Advisors/Committee Members: van den Dobbelsteen, John (mentor), Vos, Frans (graduation committee), Vijfvinkel, Teddy (graduation committee), Guédon, A.C.P. (graduation committee), Delft University of Technology (degree granting institution).

Subjects/Keywords: Deep learning; Image recognition; surgery progress

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Meij, S. (. (2019). The applicability of deep learning to detect the progress of laparoscopic surgery using video recordings. (Masters Thesis). Delft University of Technology. Retrieved from http://resolver.tudelft.nl/uuid:28f96ac7-f5ae-43af-9ba0-14832af5c103

Chicago Manual of Style (16^th Edition):

Meij, Senna (author). “The applicability of deep learning to detect the progress of laparoscopic surgery using video recordings.” 2019. Masters Thesis, Delft University of Technology. Accessed February 26, 2021. http://resolver.tudelft.nl/uuid:28f96ac7-f5ae-43af-9ba0-14832af5c103.

MLA Handbook (7^th Edition):

Meij, Senna (author). “The applicability of deep learning to detect the progress of laparoscopic surgery using video recordings.” 2019. Web. 26 Feb 2021.

Vancouver:

Meij S(. The applicability of deep learning to detect the progress of laparoscopic surgery using video recordings. [Internet] [Masters thesis]. Delft University of Technology; 2019. [cited 2021 Feb 26]. Available from: http://resolver.tudelft.nl/uuid:28f96ac7-f5ae-43af-9ba0-14832af5c103.

Council of Science Editors:

Meij S(. The applicability of deep learning to detect the progress of laparoscopic surgery using video recordings. [Masters Thesis]. Delft University of Technology; 2019. Available from: http://resolver.tudelft.nl/uuid:28f96ac7-f5ae-43af-9ba0-14832af5c103

Open Access Theses and Dissertations