4 results on '"Enzinger C"'
Search Results
2. 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
3. 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
4. Automated MRI perfusion-diffusion mismatch estimation may be significantly different in individual patients when using different software packages.
- Author
-
Deutschmann H, Hinteregger N, Wießpeiner U, Kneihsl M, Fandler-Höfler S, Michenthaler M, Enzinger C, Hassler E, Leber S, and Reishofer G
- Subjects
- Cerebrovascular Circulation, Diffusion Magnetic Resonance Imaging, Humans, Magnetic Resonance Imaging, Perfusion, Software, Brain Ischemia diagnostic imaging, Stroke diagnostic imaging
- Abstract
Objective: To compare two established software applications in terms of apparent diffusion coefficient (ADC) lesion volumes, volume of critically hypoperfused brain tissue, and calculated volumes of perfusion-diffusion mismatch in brain MRI of patients with acute ischemic stroke., Methods: Brain MRI examinations of 81 patients with acute stroke due to large vessel occlusion of the anterior circulation were analyzed. The volume of hypoperfused brain tissue, ADC volume, and the volume of perfusion-diffusion mismatch were calculated automatically with two different software packages. The calculated parameters were compared quantitatively using formal statistics., Results: Significant difference was found for the volume of hypoperfused tissue (median 91.0 ml vs. 102.2 ml; p < 0.05) and the ADC volume (median 30.0 ml vs. 23.9 ml; p < 0.05) between different software packages. The volume of the perfusion-diffusion mismatch differed significantly (median 47.0 ml vs. 67.2 ml; p < 0.05). Evaluation of the results on a single-subject basis revealed a mean absolute difference of 20.5 ml for hypoperfused tissue, 10.8 ml for ADC volumes, and 27.6 ml for mismatch volumes, respectively. Application of the DEFUSE 3 threshold of 70 ml infarction core would have resulted in dissenting treatment decisions in 6/81 (7.4%) patients., Conclusion: Volume segmentation in different software products may lead to significantly different results in the individual patient and may thus seriously influence the decision for or against mechanical thrombectomy., Key Points: • Automated calculation of MRI perfusion-diffusion mismatch helps clinicians to apply inclusion and exclusion criteria derived from randomized trials. • Infarct volume segmentation plays a crucial role and lead to significantly different result for different computer programs. • Perfusion-diffusion mismatch estimation from different computer programs may influence the decision for or against mechanical thrombectomy.
- Published
- 2021
- Full Text
- View/download PDF
Catalog
Discovery Service for Jio Institute Digital Library
For full access to our library's resources, please sign in.