1
|
Clunie DA, Flanders A, Taylor A, Erickson B, Bialecki B, Brundage D, Gutman D, Prior F, Seibert JA, Perry J, Gichoya JW, Kirby J, Andriole K, Geneslaw L, Moore S, Fitzgerald TJ, Tellis W, Xiao Y, Farahani K. Report of the Medical Image De-Identification (MIDI) Task Group -- Best Practices and Recommendations. ARXIV 2025:arXiv:2303.10473v3. [PMID: 37033463 PMCID: PMC10081345] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Subscribe] [Scholar Register] [Indexed: 04/11/2023]
Abstract
This report addresses the technical aspects of de-identification of medical images of human subjects and biospecimens, such that re-identification risk of ethical, moral, and legal concern is sufficiently reduced to allow unrestricted public sharing for any purpose, regardless of the jurisdiction of the source and distribution sites. All medical images, regardless of the mode of acquisition, are considered, though the primary emphasis is on those with accompanying data elements, especially those encoded in formats in which the data elements are embedded, particularly Digital Imaging and Communications in Medicine (DICOM). These images include image-like objects such as Segmentations, Parametric Maps, and Radiotherapy (RT) Dose objects. The scope also includes related non-image objects, such as RT Structure Sets, Plans and Dose Volume Histograms, Structured Reports, and Presentation States. Only de-identification of publicly released data is considered, and alternative approaches to privacy preservation, such as federated learning for artificial intelligence (AI) model development, are out of scope, as are issues of privacy leakage from AI model sharing. Only technical issues of public sharing are addressed.
Collapse
|
2
|
Clunie D, Taylor A, Bisson T, Gutman D, Xiao Y, Schwarz CG, Greve D, Gichoya J, Shih G, Kline A, Kopchick B, Farahani K. Summary of the National Cancer Institute 2023 Virtual Workshop on Medical Image De-identification-Part 2: Pathology Whole Slide Image De-identification, De-facing, the Role of AI in Image De-identification, and the NCI MIDI Datasets and Pipeline. JOURNAL OF IMAGING INFORMATICS IN MEDICINE 2025; 38:16-30. [PMID: 38980626 PMCID: PMC11811347 DOI: 10.1007/s10278-024-01183-x] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 04/13/2024] [Revised: 06/16/2024] [Accepted: 06/18/2024] [Indexed: 07/10/2024]
Abstract
De-identification of medical images intended for research is a core requirement for data sharing initiatives, particularly as the demand for data for artificial intelligence (AI) applications grows. The Center for Biomedical Informatics and Information Technology (CBIIT) of the United States National Cancer Institute (NCI) convened a two half-day virtual workshop with the intent of summarizing the state of the art in de-identification technology and processes and exploring interesting aspects of the subject. This paper summarizes the highlights of the second day of the workshop, the recordings and presentations of which are publicly available for review. The topics covered included pathology whole slide image de-identification, de-facing, the role of AI in image de-identification, and the NCI Medical Image De-Identification Initiative (MIDI) datasets and pipeline.
Collapse
Affiliation(s)
| | | | - Tom Bisson
- Charité - Universitätsmedizin Berlin, Berlin, Germany
| | | | - Ying Xiao
- Hospital of the University of Pennsylvania, Philadelphia, PA, USA
| | | | | | | | - George Shih
- Weill Cornell Medical College, New York, NY, USA
| | | | | | - Keyvan Farahani
- National Heart, Lung, and Blood Institute, National Institutes of Health, Bethesda, MD, USA
| |
Collapse
|
3
|
Landau SM, Harrison TM, Baker SL, Boswell MS, Lee J, Taggett J, Ward TJ, Chadwick T, Murphy A, DeCarli C, Schwarz CG, Vemuri P, Jack CR, Koeppe RA, Jagust WJ, for the U.S. POINTER Study Group and for the Alzheimer's Disease Neuroimaging Initiative. Positron emission tomography harmonization in the Alzheimer's Disease Neuroimaging Initiative: A scalable and rigorous approach to multisite amyloid and tau quantification. Alzheimers Dement 2025; 21:e14378. [PMID: 39559932 PMCID: PMC11772732 DOI: 10.1002/alz.14378] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/04/2024] [Revised: 10/07/2024] [Accepted: 10/10/2024] [Indexed: 11/20/2024]
Abstract
INTRODUCTION A key goal of the Alzheimer's Disease NeuroImaging Initiative (ADNI) positron emission tomography (PET) Core is to harmonize quantification of β-amyloid (Aβ) and tau PET image data across multiple scanners and tracers. METHODS We developed an analysis pipeline (Berkeley PET Imaging Pipeline, B-PIP) for ADNI Aβ and tau PET images and applied it to PET data from other multisite studies. Steps include image pre-processing, refacing, magnetic resonance imaging (MRI)/PET co-registration, visual quality control (QC), quantification of tracer uptake, and standardization of Aβ and tau standardized uptake value ratios (SUVrs) across tracers. RESULTS Measurements from 10,105 cross-sectional and longitudinal Aβ and tau PET scans acquired in several studies between 2010 and 2024 can be processed, harmonized, and directly merged across tracers and cohorts. DISCUSSION The B-PIP developed in ADNI is a scalable image harmonization approach used in several observational studies and clinical trials that facilitates rigorous Aβ and tau PET quantification and data sharing. HIGHLIGHTS Quantitative results from ADNI Aβ and tau PET data are generated using a rigorous, scalable image processing pipeline This pipeline has been applied to PET data from several other large, multisite studies and trials Quantitative outcomes are harmonizable across studies and are shared with the scientific community.
Collapse
Affiliation(s)
- Susan M. Landau
- Neuroscience DepartmentUniversity of CaliforniaBerkeleyCaliforniaUSA
| | | | - Suzanne L. Baker
- Molecular Biophysics and Integrated BioimagingLawrence Berkeley National LaboratoryBerkeleyCaliforniaUSA
| | - Martin S. Boswell
- Molecular Biophysics and Integrated BioimagingLawrence Berkeley National LaboratoryBerkeleyCaliforniaUSA
| | - JiaQie Lee
- Neuroscience DepartmentUniversity of CaliforniaBerkeleyCaliforniaUSA
| | - Jacinda Taggett
- Neuroscience DepartmentUniversity of CaliforniaBerkeleyCaliforniaUSA
| | - Tyler J. Ward
- Neuroscience DepartmentUniversity of CaliforniaBerkeleyCaliforniaUSA
| | - Trevor Chadwick
- Neuroscience DepartmentUniversity of CaliforniaBerkeleyCaliforniaUSA
| | - Alice Murphy
- Neuroscience DepartmentUniversity of CaliforniaBerkeleyCaliforniaUSA
| | | | | | | | | | - Robert A. Koeppe
- Department of RadiologyUniversity of MichiganAnn ArborMichiganUSA
| | - William J. Jagust
- Neuroscience DepartmentUniversity of CaliforniaBerkeleyCaliforniaUSA
- Molecular Biophysics and Integrated BioimagingLawrence Berkeley National LaboratoryBerkeleyCaliforniaUSA
| | | |
Collapse
|
4
|
Steeg K, Bohrer E, Schäfer SB, Vu VD, Scherberich J, Windfelder AG, Krombach GA. Re-identification of anonymised MRI head images with publicly available software: investigation of the current risk to patient privacy. EClinicalMedicine 2024; 78:102930. [PMID: 39640939 PMCID: PMC11617779 DOI: 10.1016/j.eclinm.2024.102930] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 07/01/2024] [Revised: 10/25/2024] [Accepted: 10/25/2024] [Indexed: 12/07/2024] Open
Abstract
Background Facial recognition software (FRS) has historically been perceived as lacking the capability to identify individuals from cross-sectional medical images. Utilising such data for identification purposes was considered infeasible due to the substantial computational power and specialised technical expertise it would require. However, recent advancements in accessible artificial intelligence-based (AI-based) software and open-source tools have made these applications widely available and easy to use, raising new privacy concerns. Methods This proof-of-concept was designed as a cross-sectional study and included participants with a verified online presence. Standard magnetic resonance imaging (MRI) head scans were performed on these participants, from which three-dimensional rendering (3DR) images were created using free and publicly available software. These images were used for face searches by free and publicly available FRS. Different head orientations and hairstyles were applied to the 3DR images to assess whether non-facial features influenced the FRS results. All results were obtained between the 10th of February 2024 and the 1st of March 2024. Findings Face searches of 3DR images in a database containing over 800 million images from the World Wide Web (WWW) yielded correct matches for 50% of the participants in less than 10 min. The user-friendly software required minimal computational knowledge or resources, making this process broadly accessible. Modifying elements such as hairstyles or the orientation of the 3DR to better resemble actual photographs of the participants improved FRS matches. Interpretation Current existing FRS can swiftly and accurately identify individuals from MRI head scans. This poses a significant privacy risk for participants in enrolled clinical trials and highlights the urgent need for improved data protection measures and increased sensitivity to ensure participant confidentiality. Funding There was no funding source for this study.
Collapse
Affiliation(s)
- Katharina Steeg
- Department of Diagnostic and Interventional Radiology, University Hospital Giessen, Justus-Liebig-University Giessen, Klinikstraße 33, 35392, Giessen, Germany
| | - Evelyn Bohrer
- Department of Diagnostic and Interventional Radiology, University Hospital Giessen, Justus-Liebig-University Giessen, Klinikstraße 33, 35392, Giessen, Germany
| | - Stefan Benjamin Schäfer
- Department of Diagnostic and Interventional Radiology, University Hospital Giessen, Justus-Liebig-University Giessen, Klinikstraße 33, 35392, Giessen, Germany
| | - Viet Duc Vu
- Department of Diagnostic and Interventional Radiology, University Hospital Giessen, Justus-Liebig-University Giessen, Klinikstraße 33, 35392, Giessen, Germany
| | - Jan Scherberich
- Department of Diagnostic and Interventional Radiology, University Hospital Giessen, Justus-Liebig-University Giessen, Klinikstraße 33, 35392, Giessen, Germany
| | - Anton George Windfelder
- Department of Diagnostic and Interventional Radiology, University Hospital Giessen, Justus-Liebig-University Giessen, Klinikstraße 33, 35392, Giessen, Germany
- Department of Bioresources, Fraunhofer Institute for Molecular Biology and Applied Ecology IME, Giessen, Germany
| | - Gabriele Anja Krombach
- Department of Diagnostic and Interventional Radiology, University Hospital Giessen, Justus-Liebig-University Giessen, Klinikstraße 33, 35392, Giessen, Germany
| |
Collapse
|
5
|
Schwarz CG, Choe M, Rossi S, Das SR, Ittyerah R, Fletcher E, Maillard P, Singh B, Harvey DJ, Malone IB, Prosser L, Senjem ML, Matoush LC, Ward CP, Prakaashana CM, Landau SM, Koeppe RA, Lee J, DeCarli C, Weiner MW, Jack CR, Jagust WJ, Yushkevich PA, Tosun D, for the Alzheimer's Disease Neuroimaging Initiative. Implementation and validation of face de-identification (de-facing) in ADNI4. Alzheimers Dement 2024; 20:8048-8061. [PMID: 39392215 PMCID: PMC11567833 DOI: 10.1002/alz.14303] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/03/2024] [Revised: 09/03/2024] [Accepted: 09/10/2024] [Indexed: 10/12/2024]
Abstract
INTRODUCTION Recent technological advances have increased the risk that de-identified brain images could be re-identified from face imagery. The Alzheimer's Disease Neuroimaging Initiative (ADNI) is a leading source of publicly available de-identified brain imaging, who quickly acted to protect participants' privacy. METHODS An independent expert committee evaluated 11 face-deidentification ("de-facing") methods and selected four for formal testing. RESULTS Effects of de-facing on brain measurements were comparable across methods and sufficiently small to recommend de-facing in ADNI. The committee ultimately recommended mri_reface for advantages in reliability, and for some practical considerations. ADNI leadership approved the committee's recommendation, beginning in ADNI4. DISCUSSION ADNI4 de-faces all applicable brain images before subsequent pre-processing, analyses, and public release. Trained analysts inspect de-faced images to confirm complete face removal and complete non-modification of brain. This paper details the history of the algorithm selection process and extensive validation, then describes the production workflows for de-facing in ADNI. HIGHLIGHTS ADNI is implementing "de-facing" of MRI and PET beginning in ADNI4. "De-facing" alters face imagery in brain images to help protect privacy. Four algorithms were extensively compared for ADNI and mri_reface was chosen. Validation confirms mri_reface is robust and effective for ADNI sequences. Validation confirms mri_reface negligibly affects ADNI brain measurements.
Collapse
Affiliation(s)
| | - Mark Choe
- Northern California Institute for Research and EducationSan Francisco Veterans Affairs Medical CenterSan FranciscoCaliforniaUSA
| | - Stephanie Rossi
- Department of RadiologyUniversity of California, San FranciscoSan FranciscoCaliforniaUSA
| | - Sandhitsu R. Das
- Department of NeurologyUniversity of PennsylvaniaPhiladelphiaPennsylvaniaUSA
| | - Ranjit Ittyerah
- Department of RadiologyUniversity of PennsylvaniaPhiladelphiaPennsylvaniaUSA
| | - Evan Fletcher
- Department of NeurologyUniversity of California, DavisDavisCaliforniaUSA
| | - Pauline Maillard
- Department of NeurologyUniversity of California, DavisDavisCaliforniaUSA
| | - Baljeet Singh
- Department of NeurologyUniversity of California, DavisDavisCaliforniaUSA
| | - Danielle J. Harvey
- Division of Biostatistics Department of Public Health Sciences, University of California, DavisDavisCaliforniaUSA
| | - Ian B. Malone
- Dementia Research Centre, Dementia Research CentreUCL Institute of NeurologyQueen SquareLondonUK
| | - Lloyd Prosser
- Dementia Research Centre, Dementia Research CentreUCL Institute of NeurologyQueen SquareLondonUK
| | - Matthew L. Senjem
- Department of Information TechnologyMayo ClinicRochesterMinnesotaUSA
| | | | | | | | - Susan M. Landau
- Helen Wills Neuroscience InstituteUniversity of California, BerkeleyBerkeleyCaliforniaUSA
| | - Robert A. Koeppe
- Department of RadiologyUniversity of MichiganAnn ArborMichiganUSA
| | - JiaQie Lee
- Helen Wills Neuroscience InstituteUniversity of California, BerkeleyBerkeleyCaliforniaUSA
| | - Charles DeCarli
- Department of NeurologyUniversity of California, DavisDavisCaliforniaUSA
| | - Michael W. Weiner
- Department of RadiologyUniversity of California, San FranciscoSan FranciscoCaliforniaUSA
| | | | - William J. Jagust
- Helen Wills Neuroscience InstituteUniversity of California, BerkeleyBerkeleyCaliforniaUSA
| | - Paul A. Yushkevich
- Department of RadiologyUniversity of PennsylvaniaPhiladelphiaPennsylvaniaUSA
| | - Duygu Tosun
- Northern California Institute for Research and EducationSan Francisco Veterans Affairs Medical CenterSan FranciscoCaliforniaUSA
- Department of RadiologyUniversity of California, San FranciscoSan FranciscoCaliforniaUSA
| | | |
Collapse
|
6
|
Mahmutoglu MA, Rastogi A, Schell M, Foltyn-Dumitru M, Baumgartner M, Maier-Hein KH, Deike-Hofmann K, Radbruch A, Bendszus M, Brugnara G, Vollmuth P. Deep learning-based defacing tool for CT angiography: CTA-DEFACE. Eur Radiol Exp 2024; 8:111. [PMID: 39382818 PMCID: PMC11465008 DOI: 10.1186/s41747-024-00510-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/23/2024] [Accepted: 09/05/2024] [Indexed: 10/10/2024] Open
Abstract
The growing use of artificial neural network (ANN) tools for computed tomography angiography (CTA) data analysis underscores the necessity for elevated data protection measures. We aimed to establish an automated defacing pipeline for CTA data. In this retrospective study, CTA data from multi-institutional cohorts were utilized to annotate facemasks (n = 100) and train an ANN model, subsequently tested on an external institution's dataset (n = 50) and compared to a publicly available defacing algorithm. Face detection (MTCNN) and verification (FaceNet) networks were applied to measure the similarity between the original and defaced CTA images. Dice similarity coefficient (DSC), face detection probability, and face similarity measures were calculated to evaluate model performance. The CTA-DEFACE model effectively segmented soft face tissue in CTA data achieving a DSC of 0.94 ± 0.02 (mean ± standard deviation) on the test set. Our model was benchmarked against a publicly available defacing algorithm. After applying face detection and verification networks, our model showed substantially reduced face detection probability (p < 0.001) and similarity to the original CTA image (p < 0.001). The CTA-DEFACE model enabled robust and precise defacing of CTA data. The trained network is publicly accessible at www.github.com/neuroAI-HD/CTA-DEFACE . RELEVANCE STATEMENT: The ANN model CTA-DEFACE, developed for automatic defacing of CT angiography images, achieves significantly lower face detection probabilities and greater dissimilarity from the original images compared to a publicly available model. The algorithm has been externally validated and is publicly accessible. KEY POINTS: The developed ANN model (CTA-DEFACE) automatically generates facemasks for CT angiography images. CTA-DEFACE offers superior deidentification capabilities compared to a publicly available model. By means of graphics processing unit optimization, our model ensures rapid processing of medical images. Our model underwent external validation, underscoring its reliability for real-world application.
Collapse
Affiliation(s)
- Mustafa Ahmed Mahmutoglu
- Department of Neuroradiology, Heidelberg University Hospital, Heidelberg, Germany.
- Division for Computational Neuroimaging, Heidelberg University Hospital, Heidelberg, Germany.
| | - Aditya Rastogi
- Department of Neuroradiology, Heidelberg University Hospital, Heidelberg, Germany
- Division for Computational Neuroimaging, Heidelberg University Hospital, Heidelberg, Germany
| | - Marianne Schell
- Department of Neuroradiology, Heidelberg University Hospital, Heidelberg, Germany
- Division for Computational Neuroimaging, Heidelberg University Hospital, Heidelberg, Germany
| | - Martha Foltyn-Dumitru
- Department of Neuroradiology, Heidelberg University Hospital, Heidelberg, Germany
- Division for Computational Neuroimaging, Heidelberg University Hospital, Heidelberg, Germany
| | - Michael Baumgartner
- Division for Medical Image Computing, German Cancer Research Center, Heidelberg, Germany
- Helmholtz Imaging, Heidelberg, Germany
- Faculty of Mathematics and Computer Science, Heidelberg University, Heidelberg, Germany
| | | | - Katerina Deike-Hofmann
- Department of Neuroradiology, Bonn University Hospital, Bonn, Germany
- Clinical Neuroimaging Group, German Center for Neurodegenerative Diseases, DZNE, Bonn, Germany
| | - Alexander Radbruch
- Department of Neuroradiology, Bonn University Hospital, Bonn, Germany
- Clinical Neuroimaging Group, German Center for Neurodegenerative Diseases, DZNE, Bonn, Germany
| | - Martin Bendszus
- Department of Neuroradiology, Heidelberg University Hospital, Heidelberg, Germany
| | - Gianluca Brugnara
- Department of Neuroradiology, Heidelberg University Hospital, Heidelberg, Germany
- Division for Computational Neuroimaging, Heidelberg University Hospital, Heidelberg, Germany
| | - Philipp Vollmuth
- Department of Neuroradiology, Heidelberg University Hospital, Heidelberg, Germany
- Division for Computational Neuroimaging, Heidelberg University Hospital, Heidelberg, Germany
| |
Collapse
|
7
|
Bou Hanna E, Partarrieu S, Berenbaum A, Allassonnière S, Besson FL. Exploring de-anonymization risks in PET imaging: Insights from a comprehensive analysis of 853 patient scans. Sci Data 2024; 11:932. [PMID: 39198445 PMCID: PMC11358492 DOI: 10.1038/s41597-024-03800-4] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/21/2024] [Accepted: 08/20/2024] [Indexed: 09/01/2024] Open
Abstract
Due to their high resolution, anonymized CT scans can be reidentified using face recognition tools. However, little is known regarding PET deanonymization because of its lower resolution. In this study, we analysed PET/CT scans of 853 patients from a TCIA-restricted dataset (AutoPET). First, we built denoised 2D morphological reconstructions of both PET and CT scans, and then we determined how frequently a PET reconstruction could be matched to the correct CT reconstruction with no other metadata. Using the CT morphological reconstructions as ground truth allows us to frame the problem as a face recognition problem and to quantify our performance using traditional metrics (top k accuracies) without any use of patient pictures. Using our denoised PET 2D reconstructions, we achieved 72% top 10 accuracy after the realignment of all CTs in the same reference frame, and 71% top 10 accuracy after realignment and mixing within a larger face dataset of 10, 168 pictures. This highlights the need to consider face identification issues when dealing with PET imaging data.
Collapse
Affiliation(s)
| | | | - Arnaud Berenbaum
- Université Paris-Saclay, Commissariat à l'énergie atomique et aux énergies alternatives (CEA), Centre National de la Recherche Scientifique (CNRS), Inserm, BioMaps, Orsay, France
| | - Stéphanie Allassonnière
- CRC, HeKA, Parisanté Campus, Université Paris Cité, Inria, Inserm, Sorbonne Université, Paris, France
| | - Florent L Besson
- Université Paris-Saclay, Commissariat à l'énergie atomique et aux énergies alternatives (CEA), Centre National de la Recherche Scientifique (CNRS), Inserm, BioMaps, Orsay, France.
- Department of Nuclear Medicine-Molecular Imaging, Hôpitaux Universitaires Paris-Saclay, Assistance Publique-Hôpitaux de Paris, DMU SMART IMAGING, CHU Bicêtre, Le Kremlin-Bicêtre, France.
- Université Paris-Saclay, School of Medicine, Le Kremlin-Bicêtre, France.
| |
Collapse
|
8
|
Ryu DW, Lee C, Lee HJ, Shim YS, Hong YJ, Cho JH, Kim S, Lee JM, Yang DW. Assessing the Impact of Defacing Algorithms on Brain Volumetry Accuracy in MRI Analyses. Dement Neurocogn Disord 2024; 23:127-135. [PMID: 39113754 PMCID: PMC11300685 DOI: 10.12779/dnd.2024.23.3.127] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/15/2024] [Revised: 04/26/2024] [Accepted: 04/26/2024] [Indexed: 08/10/2024] Open
Abstract
Background and Purpose To ensure data privacy, the development of defacing processes, which anonymize brain images by obscuring facial features, is crucial. However, the impact of these defacing methods on brain imaging analysis poses significant concern. This study aimed to evaluate the reliability of three different defacing methods in automated brain volumetry. Methods Magnetic resonance imaging with three-dimensional T1 sequences was performed on ten patients diagnosed with subjective cognitive decline. Defacing was executed using mri_deface, BioImage Suite Web-based defacing, and Defacer. Brain volumes were measured employing the QBraVo program and FreeSurfer, assessing intraclass correlation coefficient (ICC) and the mean differences in brain volume measurements between the original and defaced images. Results The mean age of the patients was 71.10±6.17 years, with 4 (40.0%) being male. The total intracranial volume, total brain volume, and ventricle volume exhibited high ICCs across the three defacing methods and 2 volumetry analyses. All regional brain volumes showed high ICCs with all three defacing methods. Despite variations among some brain regions, no significant mean differences in regional brain volume were observed between the original and defaced images across all regions. Conclusions The three defacing algorithms evaluated did not significantly affect the results of image analysis for the entire brain or specific cerebral regions. These findings suggest that these algorithms can serve as robust methods for defacing in neuroimaging analysis, thereby supporting data anonymization without compromising the integrity of brain volume measurements.
Collapse
Affiliation(s)
- Dong-Woo Ryu
- Department of Neurology, College of Medicine, The Catholic University of Korea, Seoul, Korea
| | - ChungHwee Lee
- Department of Neurology, College of Medicine, The Catholic University of Korea, Seoul, Korea
| | - Hyuk-je Lee
- Department of Neurology, College of Medicine, The Catholic University of Korea, Seoul, Korea
| | - Yong S Shim
- Department of Neurology, College of Medicine, The Catholic University of Korea, Seoul, Korea
| | - Yun Jeong Hong
- Department of Neurology, College of Medicine, The Catholic University of Korea, Seoul, Korea
| | - Jung Hee Cho
- Department of Neurology, College of Medicine, The Catholic University of Korea, Seoul, Korea
| | - Seonggyu Kim
- Department of Electronic Engineering, Hanyang University, Seoul, Korea
| | - Jong-Min Lee
- Department of Biomedical Engineering, Hanyang University, Seoul, Korea
| | - Dong Won Yang
- Department of Neurology, College of Medicine, The Catholic University of Korea, Seoul, Korea
| |
Collapse
|
9
|
Molchanova N, Maréchal B, Thiran J, Kober T, Huelnhagen T, Richiardi J, the Alzheimer's Disease Neuroimaging Initiative. Fast refacing of MR images with a generative neural network lowers re-identification risk and preserves volumetric consistency. Hum Brain Mapp 2024; 45:e26721. [PMID: 38899549 PMCID: PMC11187735 DOI: 10.1002/hbm.26721] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/26/2023] [Revised: 04/09/2024] [Accepted: 05/06/2024] [Indexed: 06/21/2024] Open
Abstract
With the rise of open data, identifiability of individuals based on 3D renderings obtained from routine structural magnetic resonance imaging (MRI) scans of the head has become a growing privacy concern. To protect subject privacy, several algorithms have been developed to de-identify imaging data using blurring, defacing or refacing. Completely removing facial structures provides the best re-identification protection but can significantly impact post-processing steps, like brain morphometry. As an alternative, refacing methods that replace individual facial structures with generic templates have a lower effect on the geometry and intensity distribution of original scans, and are able to provide more consistent post-processing results by the price of higher re-identification risk and computational complexity. In the current study, we propose a novel method for anonymized face generation for defaced 3D T1-weighted scans based on a 3D conditional generative adversarial network. To evaluate the performance of the proposed de-identification tool, a comparative study was conducted between several existing defacing and refacing tools, with two different segmentation algorithms (FAST and Morphobox). The aim was to evaluate (i) impact on brain morphometry reproducibility, (ii) re-identification risk, (iii) balance between (i) and (ii), and (iv) the processing time. The proposed method takes 9 s for face generation and is suitable for recovering consistent post-processing results after defacing.
Collapse
Affiliation(s)
- Nataliia Molchanova
- Department of RadiologyLausanne University Hospital (CHUV)LausanneSwitzerland
- Institute of InformaticsUniversity of Applied Sciences and Arts of Western Switzerland (HES‐SO)SierreSwitzerland
- Faculty of Biology and MedicineUniversity of Lausanne (UNIL)LausanneSwitzerland
- Advanced Clinical Imaging TechnologySiemens Healthineers International AGLausanneSwitzerland
- Laboratory of Signal Processing 5Ecole Polytechnique Fédérale de Lausanne, (EPFL)LausanneSwitzerland
| | - Bénédicte Maréchal
- Department of RadiologyLausanne University Hospital (CHUV)LausanneSwitzerland
- Advanced Clinical Imaging TechnologySiemens Healthineers International AGLausanneSwitzerland
- Laboratory of Signal Processing 5Ecole Polytechnique Fédérale de Lausanne, (EPFL)LausanneSwitzerland
| | - Jean‐Philippe Thiran
- Department of RadiologyLausanne University Hospital (CHUV)LausanneSwitzerland
- Laboratory of Signal Processing 5Ecole Polytechnique Fédérale de Lausanne, (EPFL)LausanneSwitzerland
| | - Tobias Kober
- Department of RadiologyLausanne University Hospital (CHUV)LausanneSwitzerland
- Advanced Clinical Imaging TechnologySiemens Healthineers International AGLausanneSwitzerland
- Laboratory of Signal Processing 5Ecole Polytechnique Fédérale de Lausanne, (EPFL)LausanneSwitzerland
| | - Till Huelnhagen
- Department of RadiologyLausanne University Hospital (CHUV)LausanneSwitzerland
- Advanced Clinical Imaging TechnologySiemens Healthineers International AGLausanneSwitzerland
- Laboratory of Signal Processing 5Ecole Polytechnique Fédérale de Lausanne, (EPFL)LausanneSwitzerland
| | - Jonas Richiardi
- Department of RadiologyLausanne University Hospital (CHUV)LausanneSwitzerland
- Faculty of Biology and MedicineUniversity of Lausanne (UNIL)LausanneSwitzerland
| | | |
Collapse
|
10
|
Satoh R, Ali F, Botha H, Lowe VJ, Josephs KA, Whitwell JL. Direct comparison between 18F-Flortaucipir tau PET and quantitative susceptibility mapping in progressive supranuclear palsy. Neuroimage 2024; 286:120509. [PMID: 38184157 PMCID: PMC10868646 DOI: 10.1016/j.neuroimage.2024.120509] [Citation(s) in RCA: 3] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/11/2023] [Revised: 12/22/2023] [Accepted: 01/03/2024] [Indexed: 01/08/2024] Open
Abstract
PURPOSE The pattern of flortaucipir tau PET uptake is topographically similar to the pattern of magnetic susceptibility in progressive supranuclear palsy (PSP); both with increased signal in subcortical structures such as the basal ganglia and midbrain, suggesting that they may be closely related. However, their relationship remains unknown since no studies have directly compared these two modalities in the same PSP cohort. We hypothesized that some flortaucipir uptake in PSP is associated with magnetic susceptibility, and hence iron deposition. The aim of this study was to evaluate the regional relationship between flortaucipir uptake and magnetic susceptibility and to examine the effects of susceptibility on flortaucipir uptake in PSP. METHODS Fifty PSP patients and 67 cognitively normal controls were prospectively recruited and underwent three Tesla MRI and flortaucipir tau PET scans. Quantitative susceptibility maps were reconstructed from multi-echo gradient-echo MRI images. Region of interest (ROI) analysis was performed to obtain flortaucipir and susceptibility values in the subcortical regions. Relationships between flortaucipir and susceptibility signals were evaluated using partial correlation analysis in the subcortical ROIs and voxel-based analysis in the whole brain. The effects of susceptibility on flortaucipir uptake were examined by using the framework of mediation analysis. RESULTS Both flortaucipir and susceptibility were greater in PSP compared to controls in the putamen, pallidum, subthalamic nucleus, red nucleus, and cerebellar dentate (p<0.05). The ROI-based and voxel-based analyses showed that these two signals were positively correlated in these five regions (r = 0.36-0.59, p<0.05). Mediation analysis showed that greater flortaucipir uptake was partially explained by susceptibility in the putamen, pallidum, subthalamic nucleus, and red nucleus, and fully explained in the cerebellar dentate. CONCLUSIONS These results suggest that some of the flortaucipir uptake in subcortical regions in PSP is related to iron deposition. These findings will contribute to our understanding of the mechanisms underlying flortaucipir tau PET findings in PSP and other neurodegenerative diseases.
Collapse
Affiliation(s)
- Ryota Satoh
- Department of Neurology, Mayo Clinic, Rochester, MN, USA
| | - Farwa Ali
- Department of Neurology, Mayo Clinic, Rochester, MN, USA
| | - Hugo Botha
- Department of Neurology, Mayo Clinic, Rochester, MN, USA
| | - Val J Lowe
- Department of Radiology, Mayo Clinic, 200 1st St SW, 55905, Rochester, MN, USA
| | | | - Jennifer L Whitwell
- Department of Radiology, Mayo Clinic, 200 1st St SW, 55905, Rochester, MN, USA.
| |
Collapse
|
11
|
Filippi CG, Stein JM, Wang Z, Bakas S, Liu Y, Chang PD, Lui Y, Hess C, Barboriak DP, Flanders AE, Wintermark M, Zaharchuk G, Wu O. Ethical Considerations and Fairness in the Use of Artificial Intelligence for Neuroradiology. AJNR Am J Neuroradiol 2023; 44:1242-1248. [PMID: 37652578 PMCID: PMC10631523 DOI: 10.3174/ajnr.a7963] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/30/2023] [Accepted: 07/07/2023] [Indexed: 09/02/2023]
Abstract
In this review, concepts of algorithmic bias and fairness are defined qualitatively and mathematically. Illustrative examples are given of what can go wrong when unintended bias or unfairness in algorithmic development occurs. The importance of explainability, accountability, and transparency with respect to artificial intelligence algorithm development and clinical deployment is discussed. These are grounded in the concept of "primum no nocere" (first, do no harm). Steps to mitigate unfairness and bias in task definition, data collection, model definition, training, testing, deployment, and feedback are provided. Discussions on the implementation of fairness criteria that maximize benefit and minimize unfairness and harm to neuroradiology patients will be provided, including suggestions for neuroradiologists to consider as artificial intelligence algorithms gain acceptance into neuroradiology practice and become incorporated into routine clinical workflow.
Collapse
Affiliation(s)
- C G Filippi
- From the Department of Radiology (C.G.F.), Tufts University School of Medicine, Boston, Massachusetts
| | - J M Stein
- Department of Radiology (J.M.S., S.B.), University of Pennsylvania, Philadelphia, Pennsylvania
| | - Z Wang
- Athinoula A. Martinos Center for Biomedical Imaging (Z.W., Y. Liu, O.W.), Department of Radiology, Massachusetts General Hospital, Boston, Massachusetts
| | - S Bakas
- Department of Radiology (J.M.S., S.B.), University of Pennsylvania, Philadelphia, Pennsylvania
| | - Y Liu
- Athinoula A. Martinos Center for Biomedical Imaging (Z.W., Y. Liu, O.W.), Department of Radiology, Massachusetts General Hospital, Boston, Massachusetts
| | - P D Chang
- Department of Radiological Sciences (P.D.C.), University of California, Irvine, California
| | - Y Lui
- Department of Neuroradiology (Y. Lui), NYU Langone Health, New York, New York
| | - C Hess
- Department of Radiology and Biomedical Imaging (C.H.), University of California, San Francisco, San Francisco, California
| | - D P Barboriak
- Department of Radiology (D.P.B.), Duke University School of Medicine, Durham, North Carolina
| | - A E Flanders
- Department of Neuroradiology/Otolaryngology (ENT) Radiology (A.E.F.), Thomas Jefferson University, Philadelphia, Pennsylvania
| | - M Wintermark
- Department of Neuroradiology (M.W.), Division of Diagnostic Imaging, MD Anderson Cancer Center, Houston, Texas
| | - G Zaharchuk
- Department of Radiology (G.Z.), Stanford University, Stanford, California
| | - O Wu
- Athinoula A. Martinos Center for Biomedical Imaging (Z.W., Y. Liu, O.W.), Department of Radiology, Massachusetts General Hospital, Boston, Massachusetts
| |
Collapse
|
12
|
Schwarz CG, Kremers WK, Weigand SD, Prakaashana CM, Senjem ML, Przybelski SA, Lowe VJ, Gunter JL, Kantarci K, Vemuri P, Graff-Radford J, Petersen RC, Knopman DS, Jack CR. Effects of de-facing software mri_reface on utility of imaging biomarkers used in Alzheimer's disease research. Neuroimage Clin 2023; 40:103507. [PMID: 37703605 PMCID: PMC10502400 DOI: 10.1016/j.nicl.2023.103507] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/02/2023] [Revised: 08/07/2023] [Accepted: 09/05/2023] [Indexed: 09/15/2023]
Abstract
Brain imaging research studies increasingly use "de-facing" software to remove or replace facial imagery before public data sharing. Several works have studied the effects of de-facing software on brain imaging biomarkers by directly comparing automated measurements from unmodified vs de-faced images, but most research brain images are used in analyses of correlations with cognitive measurements or clinical statuses, and the effects of de-facing on these types of imaging-to-cognition correlations has not been measured. In this work, we focused on brain imaging measures of amyloid (A), tau (T), neurodegeneration (N), and vascular (V) measures used in Alzheimer's Disease (AD) research. We created a retrospective sample of participants from three age- and sex-matched clinical groups (cognitively unimpaired, mild cognitive impairment, and AD dementia, and we performed region- and voxel-wise analyses of: hippocampal volume (N), white matter hyperintensity volume (V), amyloid PET (A), and tau PET (T) measures, each from multiple software pipelines, on their ability to separate cognitively defined groups and their degrees of correlation with age and Clinical Dementia Rating (CDR)-Sum of Boxes (CDR-SB). We performed each of these analyses twice: once with unmodified images and once with images de-faced with leading de-facing software mri_reface, and we directly compared the findings and their statistical strengths between the original vs. the de-faced images. Analyses with original and with de-faced images had very high agreement. There were no significant differences between any voxel-wise comparisons. Among region-wise comparisons, only three out of 55 correlations were significantly different between original and de-faced images, and these were not significant after correction for multiple comparisons. Overall, the statistical power of the imaging data for AD biomarkers was almost identical between unmodified and de-faced images, and their analyses results were extremely consistent.
Collapse
Affiliation(s)
| | - Walter K Kremers
- Department of Quantitative Health Sciences, Division of Clinical Trials & Biostatistics, Mayo Clinic, Rochester, MN, USA
| | - Stephen D Weigand
- Department of Quantitative Health Sciences, Division of Clinical Trials & Biostatistics, Mayo Clinic, Rochester, MN, USA
| | | | - Matthew L Senjem
- Department of Radiology, Mayo Clinic, Rochester, MN, USA; Department of Information Technology, Mayo Clinic, Rochester, MN, USA
| | - Scott A Przybelski
- Department of Quantitative Health Sciences, Division of Clinical Trials & Biostatistics, Mayo Clinic, Rochester, MN, USA
| | - Val J Lowe
- Department of Radiology, Mayo Clinic, Rochester, MN, USA
| | | | - Kejal Kantarci
- Department of Radiology, Mayo Clinic, Rochester, MN, USA
| | | | | | | | | | | |
Collapse
|
13
|
Selfridge AR, Spencer BA, Abdelhafez YG, Nakagawa K, Tupin JD, Badawi RD. Facial Anonymization and Privacy Concerns in Total-Body PET/CT. J Nucl Med 2023; 64:1304-1309. [PMID: 37268426 PMCID: PMC10394314 DOI: 10.2967/jnumed.122.265280] [Citation(s) in RCA: 7] [Impact Index Per Article: 3.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/01/2022] [Revised: 03/30/2023] [Indexed: 06/04/2023] Open
Abstract
Total-body PET/CT images can be rendered to produce images of a subject's face and body. In response to privacy and identifiability concerns when sharing data, we have developed and validated a workflow that obscures (defaces) a subject's face in 3-dimensional volumetric data. Methods: To validate our method, we measured facial identifiability before and after defacing images from 30 healthy subjects who were imaged with both [18F]FDG PET and CT at either 3 or 6 time points. Briefly, facial embeddings were calculated using Google's FaceNet, and an analysis of clustering was used to estimate identifiability. Results: Faces rendered from CT images were correctly matched to CT scans at other time points at a rate of 93%, which decreased to 6% after defacing. Faces rendered from PET images were correctly matched to PET images at other time points at a maximum rate of 64% and to CT images at a maximum rate of 50%, both of which decreased to 7% after defacing. We further demonstrated that defaced CT images can be used for attenuation correction during PET reconstruction, introducing a maximum bias of -3.3% in regions of the cerebral cortex nearest the face. Conclusion: We believe that the proposed method provides a baseline of anonymity and discretion when sharing image data online or between institutions and will help to facilitate collaboration and future regulatory compliance.
Collapse
Affiliation(s)
- Aaron R Selfridge
- Department of Biomedical Engineering, University of California-Davis, Davis, California;
| | - Benjamin A Spencer
- Department of Biomedical Engineering, University of California-Davis, Davis, California
- Department of Radiology, University of California-Davis, Davis, California
| | - Yasser G Abdelhafez
- Department of Radiology, University of California-Davis, Davis, California
- Radiotherapy and Nuclear Medicine Department, South Egypt Cancer Institute, Assiut University, Assiut, Egypt
| | - Keisuke Nakagawa
- Cloud Innovation Center, University of California-Davis, Davis, California; and
| | - John D Tupin
- IRB Administration, University of California-Davis, Davis, California
| | - Ramsey D Badawi
- Department of Biomedical Engineering, University of California-Davis, Davis, California
- Department of Radiology, University of California-Davis, Davis, California
| |
Collapse
|
14
|
Schwarz CG, Kremers WK, Arani A, Savvides M, Reid RI, Gunter JL, Senjem ML, Cogswell PM, Vemuri P, Kantarci K, Knopman DS, Petersen RC, Jack CR. A face-off of MRI research sequences by their need for de-facing. Neuroimage 2023; 276:120199. [PMID: 37269958 PMCID: PMC10389782 DOI: 10.1016/j.neuroimage.2023.120199] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/08/2023] [Revised: 04/19/2023] [Accepted: 05/25/2023] [Indexed: 06/05/2023] Open
Abstract
It is now widely known that research brain MRI, CT, and PET images may potentially be re-identified using face recognition, and this potential can be reduced by applying face-deidentification ("de-facing") software. However, for research MRI sequences beyond T1-weighted (T1-w) and T2-FLAIR structural images, the potential for re-identification and quantitative effects of de-facing are both unknown, and the effects of de-facing T2-FLAIR are also unknown. In this work we examine these questions (where applicable) for T1-w, T2-w, T2*-w, T2-FLAIR, diffusion MRI (dMRI), functional MRI (fMRI), and arterial spin labelling (ASL) sequences. Among current-generation, vendor-product research-grade sequences, we found that 3D T1-w, T2-w, and T2-FLAIR were highly re-identifiable (96-98%). 2D T2-FLAIR and 3D multi-echo GRE (ME-GRE) were also moderately re-identifiable (44-45%), and our derived T2* from ME-GRE (comparable to a typical 2D T2*) matched at only 10%. Finally, diffusion, functional and ASL images were each minimally re-identifiable (0-8%). Applying de-facing with mri_reface version 0.3 reduced successful re-identification to ≤8%, while differential effects on popular quantitative pipelines for cortical volumes and thickness, white matter hyperintensities (WMH), and quantitative susceptibility mapping (QSM) measurements were all either comparable with or smaller than scan-rescan estimates. Consequently, high-quality de-facing software can greatly reduce the risk of re-identification for identifiable MRI sequences with only negligible effects on automated intracranial measurements. The current-generation echo-planar and spiral sequences (dMRI, fMRI, and ASL) each had minimal match rates, suggesting that they have a low risk of re-identification and can be shared without de-facing, but this conclusion should be re-evaluated if they are acquired without fat suppression, with a full-face scan coverage, or if newer developments reduce the current levels of artifacts and distortion around the face.
Collapse
Affiliation(s)
- Christopher G Schwarz
- Department of Radiology, Mayo Clinic, 200 First Street SW, Rochester, MN 55905, USA.
| | - Walter K Kremers
- Department of Health Sciences Research, Division of Biomedical Statistics and Informatics, Mayo Clinic, Rochester, MN, USA
| | - Arvin Arani
- Department of Radiology, Mayo Clinic, 200 First Street SW, Rochester, MN 55905, USA
| | - Marios Savvides
- CyLab Biometrics Center and Department of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA, USA
| | - Robert I Reid
- Department of Radiology, Mayo Clinic, 200 First Street SW, Rochester, MN 55905, USA
| | - Jeffrey L Gunter
- Department of Radiology, Mayo Clinic, 200 First Street SW, Rochester, MN 55905, USA
| | - Matthew L Senjem
- Department of Information Technology, Mayo Clinic, Rochester, MN, USA
| | - Petrice M Cogswell
- Department of Radiology, Mayo Clinic, 200 First Street SW, Rochester, MN 55905, USA
| | - Prashanthi Vemuri
- Department of Radiology, Mayo Clinic, 200 First Street SW, Rochester, MN 55905, USA
| | - Kejal Kantarci
- Department of Radiology, Mayo Clinic, 200 First Street SW, Rochester, MN 55905, USA
| | | | | | - Clifford R Jack
- Department of Radiology, Mayo Clinic, 200 First Street SW, Rochester, MN 55905, USA
| |
Collapse
|
15
|
Lathe R. Restricted access data in the neurosciences: Are the restrictions always justified? Front Neurosci 2023; 16:975795. [PMID: 36760799 PMCID: PMC9904205 DOI: 10.3389/fnins.2022.975795] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/22/2022] [Accepted: 11/25/2022] [Indexed: 01/26/2023] Open
|