Search

Your search keyword '"Müller, D M J"' showing total 7 results
Start Over Author "Müller, D M J"
7 results on '"Müller, D M J"'

1. Preoperative brain tumor imaging: models and software for segmentation and standardized reporting

Author

Bouget, D., Pedersen, A., Jakola, A. S., Kavouridis, V., Emblem, K. E., Eijgelaar, R. S., Kommers, I., Ardon, H., Barkhof, F., Bello, L., Berger, M. S., Nibali, M. C., Furtner, J., Hervey-Jumper, S., Idema, A. J. S., Kiesel, B., Kloet, A., Mandonnet, E., Müller, D. M. J., Robe, P. A., Rossi, M., Sciortino, T., Brink, W. Van den, Wagemakers, M., Widhalm, G., Witte, M. G., Zwinderman, A. H., Hamer, P. C. De Witt, Solheim, O., and Reinertsen, I.

Subjects
Electrical Engineering and Systems Science - Image and Video Processing, Computer Science - Computer Vision and Pattern Recognition, Computer Science - Machine Learning, I.4.6, J.3
Abstract

For patients suffering from brain tumor, prognosis estimation and treatment decisions are made by a multidisciplinary team based on a set of preoperative MR scans. Currently, the lack of standardized and automatic methods for tumor detection and generation of clinical reports represents a major hurdle. In this study, we investigate glioblastomas, lower grade gliomas, meningiomas, and metastases, through four cohorts of up to 4000 patients. Tumor segmentation models were trained using the AGU-Net architecture with different preprocessing steps and protocols. Segmentation performances were assessed in-depth using a wide-range of voxel and patient-wise metrics covering volume, distance, and probabilistic aspects. Finally, two software solutions have been developed, enabling an easy use of the trained models and standardized generation of clinical reports: Raidionics and Raidionics-Slicer. Segmentation performances were quite homogeneous across the four different brain tumor types, with an average true positive Dice ranging between 80% and 90%, patient-wise recall between 88% and 98%, and patient-wise precision around 95%. With our Raidionics software, running on a desktop computer with CPU support, tumor segmentation can be performed in 16 to 54 seconds depending on the dimensions of the MRI volume. For the generation of a standardized clinical report, including the tumor segmentation and features computation, 5 to 15 minutes are necessary. All trained models have been made open-access together with the source code for both software solutions and validation metrics computation. In the future, an automatic classification of the brain tumor type would be necessary to replace manual user input. Finally, the inclusion of post-operative segmentation in both software solutions will be key for generating complete post-operative standardized clinical reports., Comment: 20 pages, 5 figures, 10 tables

Published
2022
Full Text
View/download PDF

3. Facing privacy in neuroimaging:removing facial features degrades performance of image analysis methods

Author

de Sitter, A, Visser, M, Brouwer, I, Cover, K S, van Schijndel, R A, Eijgelaar, R S, Müller, D M J, Ropele, S, Kappos, L, Rovira, Á, Filippi, M, Enzinger, C, Frederiksen, J, Ciccarelli, O, Guttmann, C R G, Wattjes, M P, Witte, M G, de Witt Hamer, P C, Barkhof, F, Vrenken, H, de Sitter, A, Visser, M, Brouwer, I, Cover, K S, van Schijndel, R A, Eijgelaar, R S, Müller, D M J, Ropele, S, Kappos, L, Rovira, Á, Filippi, M, Enzinger, C, Frederiksen, J, Ciccarelli, O, Guttmann, C R G, Wattjes, M P, Witte, M G, de Witt Hamer, P C, Barkhof, F, and Vrenken, H

Abstract

BACKGROUND: Recent studies have created awareness that facial features can be reconstructed from high-resolution MRI. Therefore, data sharing in neuroimaging requires special attention to protect participants' privacy. Facial features removal (FFR) could alleviate these concerns. We assessed the impact of three FFR methods on subsequent automated image analysis to obtain clinically relevant outcome measurements in three clinical groups.METHODS: FFR was performed using QuickShear, FaceMasking, and Defacing. In 110 subjects of Alzheimer's Disease Neuroimaging Initiative, normalized brain volumes (NBV) were measured by SIENAX. In 70 multiple sclerosis patients of the MAGNIMS Study Group, lesion volumes (WMLV) were measured by lesion prediction algorithm in lesion segmentation toolbox. In 84 glioblastoma patients of the PICTURE Study Group, tumor volumes (GBV) were measured by BraTumIA. Failed analyses on FFR-processed images were recorded. Only cases in which all image analyses completed successfully were analyzed. Differences between outcomes obtained from FFR-processed and full images were assessed, by quantifying the intra-class correlation coefficient (ICC) for absolute agreement and by testing for systematic differences using paired t tests.RESULTS: Automated analysis methods failed in 0-19% of cases in FFR-processed images versus 0-2% of cases in full images. ICC for absolute agreement ranged from 0.312 (GBV after FaceMasking) to 0.998 (WMLV after Defacing). FaceMasking yielded higher NBV (p = 0.003) and WMLV (p ≤ 0.001). GBV was lower after QuickShear and Defacing (both p < 0.001).CONCLUSIONS: All three outcome measures were affected differently by FFR, including failure of analysis methods and both "random" variation and systematic differences. Further study is warranted to ensure high-quality neuroimaging research while protecting participants' privacy.KEY POINTS: • Protecting participants' privacy when sharing MRI data is imp

Published
2020

4. Facing privacy in neuroimaging: removing facial features degrades performance of image analysis methods.

Author

de Sitter, A., Visser, M., Brouwer, I., Cover, K. S., van Schijndel, R. A., Eijgelaar, R. S., Müller, D. M. J., Ropele, S., Kappos, L., Rovira, Á., Filippi, M., Enzinger, C., Frederiksen, J., Ciccarelli, O., Guttmann, C. R. G., Wattjes, M. P., Witte, M. G., de Witt Hamer, P. C., Barkhof, F., and Vrenken, H.

Subjects
FACE, IMAGE analysis, PRIVACY, FAILURE analysis, ALZHEIMER'S disease, COMPUTERS in medicine, BRAIN, MULTIPLE sclerosis, FERRANS & Powers Quality of Life Index, RESEARCH evaluation, ANTHROPOMETRY, MAGNETIC resonance imaging, GLIOMAS, DIAGNOSTIC imaging, MEDICAL ethics, COMMUNICATION, IMPACT of Event Scale, RESEARCH funding, NEURORADIOLOGY, ALGORITHMS
Abstract

Background: Recent studies have created awareness that facial features can be reconstructed from high-resolution MRI. Therefore, data sharing in neuroimaging requires special attention to protect participants' privacy. Facial features removal (FFR) could alleviate these concerns. We assessed the impact of three FFR methods on subsequent automated image analysis to obtain clinically relevant outcome measurements in three clinical groups.Methods: FFR was performed using QuickShear, FaceMasking, and Defacing. In 110 subjects of Alzheimer's Disease Neuroimaging Initiative, normalized brain volumes (NBV) were measured by SIENAX. In 70 multiple sclerosis patients of the MAGNIMS Study Group, lesion volumes (WMLV) were measured by lesion prediction algorithm in lesion segmentation toolbox. In 84 glioblastoma patients of the PICTURE Study Group, tumor volumes (GBV) were measured by BraTumIA. Failed analyses on FFR-processed images were recorded. Only cases in which all image analyses completed successfully were analyzed. Differences between outcomes obtained from FFR-processed and full images were assessed, by quantifying the intra-class correlation coefficient (ICC) for absolute agreement and by testing for systematic differences using paired t tests.Results: Automated analysis methods failed in 0-19% of cases in FFR-processed images versus 0-2% of cases in full images. ICC for absolute agreement ranged from 0.312 (GBV after FaceMasking) to 0.998 (WMLV after Defacing). FaceMasking yielded higher NBV (p = 0.003) and WMLV (p ≤ 0.001). GBV was lower after QuickShear and Defacing (both p < 0.001).Conclusions: All three outcome measures were affected differently by FFR, including failure of analysis methods and both "random" variation and systematic differences. Further study is warranted to ensure high-quality neuroimaging research while protecting participants' privacy.Key Points: • Protecting participants' privacy when sharing MRI data is important. • Impact of three facial features removal methods on subsequent analysis was assessed in three clinical groups. • Removing facial features degrades performance of image analysis methods. [ABSTRACT FROM AUTHOR]

Published
2020
Full Text
View/download PDF

6. Facing privacy in neuroimaging: removing facial features degrades performance of image analysis methods

Author

Jette L. Frederiksen, Mike P. Wattjes, Ana Rovira, Charles R.G. Guttmann, P. C. de Witt Hamer, I. Brouwer, R.A. van Schijndel, Hugo Vrenken, Marjolein Visser, Massimo Filippi, L Kappos, Marnix G. Witte, Olga Ciccarelli, Stefan Ropele, Frederik Barkhof, A. de Sitter, Keith S. Cover, Roelant S Eijgelaar, Alzheimer’s Disease Neuroimaging Initiative, Christian Enzinger, D. M. J. Müller, de Sitter, A, Visser, M, Brouwer, I, Cover, K S, van Schijndel, R A, Eijgelaar, R S, Müller, D M J, Ropele, S, Kappos, L, Rovira, Á, Filippi, M, Enzinger, C, Frederiksen, J, Ciccarelli, O, Guttmann, C R G, Wattjes, M P, Witte, M G, de Witt Hamer, P C, Barkhof, F, Vrenken, H, MAGNIMS Study Group and Alzheimer’s Disease Neuroimaging, Initiative, Rocca, M. A., Biophotonics and Medical Imaging, LaserLaB - Biophotonics and Microscopy, Radiology and nuclear medicine, Amsterdam Neuroscience - Brain Imaging, AGEM - Endocrinology, metabolism and nutrition, APH - Aging & Later Life, APH - Health Behaviors & Chronic Diseases, Neurosurgery, and Other Research

Subjects
Male, medicine.medical_specialty, Multiple Sclerosis, Outcome measurements, Neuroimaging, 030218 nuclear medicine & medical imaging, Database, 03 medical and health sciences, Magnetic resonance imaging, 0302 clinical medicine, Alzheimer Disease, Image Interpretation, Computer-Assisted, medicine, Humans, Radiology, Nuclear Medicine and imaging, Magnetic Resonance, Ethic, Analysis method, Aged, Neuroradiology, Aged, 80 and over, Ethics, Lesion segmentation, medicine.diagnostic_test, Information Dissemination, business.industry, Outcome measures, Brain, Reproducibility of Results, General Medicine, Middle Aged, medicine.disease, Tumor Burden, Privacy, Face, Female, Radiology, Glioblastoma, business, Algorithms, Confidentiality, 030217 neurology & neurosurgery
Abstract

Background Recent studies have created awareness that facial features can be reconstructed from high-resolution MRI. Therefore, data sharing in neuroimaging requires special attention to protect participants’ privacy. Facial features removal (FFR) could alleviate these concerns. We assessed the impact of three FFR methods on subsequent automated image analysis to obtain clinically relevant outcome measurements in three clinical groups. Methods FFR was performed using QuickShear, FaceMasking, and Defacing. In 110 subjects of Alzheimer’s Disease Neuroimaging Initiative, normalized brain volumes (NBV) were measured by SIENAX. In 70 multiple sclerosis patients of the MAGNIMS Study Group, lesion volumes (WMLV) were measured by lesion prediction algorithm in lesion segmentation toolbox. In 84 glioblastoma patients of the PICTURE Study Group, tumor volumes (GBV) were measured by BraTumIA. Failed analyses on FFR-processed images were recorded. Only cases in which all image analyses completed successfully were analyzed. Differences between outcomes obtained from FFR-processed and full images were assessed, by quantifying the intra-class correlation coefficient (ICC) for absolute agreement and by testing for systematic differences using paired t tests. Results Automated analysis methods failed in 0–19% of cases in FFR-processed images versus 0–2% of cases in full images. ICC for absolute agreement ranged from 0.312 (GBV after FaceMasking) to 0.998 (WMLV after Defacing). FaceMasking yielded higher NBV (p = 0.003) and WMLV (p ≤ 0.001). GBV was lower after QuickShear and Defacing (both p Conclusions All three outcome measures were affected differently by FFR, including failure of analysis methods and both “random” variation and systematic differences. Further study is warranted to ensure high-quality neuroimaging research while protecting participants’ privacy. Key Points • Protecting participants’ privacy when sharing MRI data is important. • Impact of three facial features removal methods on subsequent analysis was assessed in three clinical groups. • Removing facial features degrades performance of image analysis methods.

Published
2019
Full Text
View/download PDF

7. Inter-rater agreement in glioma segmentations on longitudinal MRI.

Author

Visser M, Müller DMJ, van Duijn RJM, Smits M, Verburg N, Hendriks EJ, Nabuurs RJA, Bot JCJ, Eijgelaar RS, Witte M, van Herk MB, Barkhof F, de Witt Hamer PC, and de Munck JC

Subjects
Adult, Aged, Brain Neoplasms epidemiology, Cohort Studies, Female, Glioma epidemiology, Humans, Magnetic Resonance Imaging methods, Male, Middle Aged, Netherlands epidemiology, Observer Variation, Random Allocation, Brain Neoplasms diagnostic imaging, Glioma diagnostic imaging, Magnetic Resonance Imaging standards
Abstract

Background: Tumor segmentation of glioma on MRI is a technique to monitor, quantify and report disease progression. Manual MRI segmentation is the gold standard but very labor intensive. At present the quality of this gold standard is not known for different stages of the disease, and prior work has mainly focused on treatment-naive glioblastoma. In this paper we studied the inter-rater agreement of manual MRI segmentation of glioblastoma and WHO grade II-III glioma for novices and experts at three stages of disease. We also studied the impact of inter-observer variation on extent of resection and growth rate., Methods: In 20 patients with WHO grade IV glioblastoma and 20 patients with WHO grade II-III glioma (defined as non-glioblastoma) both the enhancing and non-enhancing tumor elements were segmented on MRI, using specialized software, by four novices and four experts before surgery, after surgery and at time of tumor progression. We used the generalized conformity index (GCI) and the intra-class correlation coefficient (ICC) of tumor volume as main outcome measures for inter-rater agreement., Results: For glioblastoma, segmentations by experts and novices were comparable. The inter-rater agreement of enhancing tumor elements was excellent before surgery (GCI 0.79, ICC 0.99) poor after surgery (GCI 0.32, ICC 0.92), and good at progression (GCI 0.65, ICC 0.91). For non-glioblastoma, the inter-rater agreement was generally higher between experts than between novices. The inter-rater agreement was excellent between experts before surgery (GCI 0.77, ICC 0.92), was reasonable after surgery (GCI 0.48, ICC 0.84), and good at progression (GCI 0.60, ICC 0.80). The inter-rater agreement was good between novices before surgery (GCI 0.66, ICC 0.73), was poor after surgery (GCI 0.33, ICC 0.55), and poor at progression (GCI 0.36, ICC 0.73). Further analysis showed that the lower inter-rater agreement of segmentation on postoperative MRI could only partly be explained by the smaller volumes and fragmentation of residual tumor. The median interquartile range of extent of resection between raters was 8.3% and of growth rate was 0.22 mm/year., Conclusion: Manual tumor segmentations on MRI have reasonable agreement for use in spatial and volumetric analysis. Agreement in spatial overlap is of concern with segmentation after surgery for glioblastoma and with segmentation of non-glioblastoma by non-experts., (Copyright © 2019 The Authors. Published by Elsevier Inc. All rights reserved.)

Published
2019
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results