Privacy risks of whole-slide image sharing in digital pathology

J 2023

Privacy risks of whole-slide image sharing in digital pathology

HOLUB, Petr, Heimo MÜLLER, Tomáš BÍL, Luca PIREDDU, Markus PLASS et. al.

Basic information

Original name

Privacy risks of whole-slide image sharing in digital pathology

Authors

HOLUB, Petr (203 Czech Republic, guarantor, belonging to the institution), Heimo MÜLLER, Tomáš BÍL (203 Czech Republic, belonging to the institution), Luca PIREDDU, Markus PLASS, Fabian PRASSER, Irene SCHLÜNDER, Kurt ZATLOUKAL, Rudolf NENUTIL (203 Czech Republic) and Tomáš BRÁZDIL (203 Czech Republic, belonging to the institution)

Edition

Nature Communications, 2023, 2041-1723

Other information

Language

English

Type of outcome

Článek v odborném periodiku

Field of Study

10201 Computer sciences, information science, bioinformatics

Country of publisher

Germany

Confidentiality degree

není předmětem státního či obchodního tajemství

References:

URL

Impact factor

Impact factor: 16.600 in 2022

RIV identification code

RIV/00216224:14610/23:00130727

Organization unit

Institute of Computer Science

DOI

http://dx.doi.org/10.1038/s41467-023-37991-y

UT WoS

001001562200003

Keywords in English

digital pathology; whole slide images; anonymity; privacy risks; data sharing

Změněno: 5/4/2024 11:00, Mgr. Alena Mokrá

Abstract

V originále

Access to large volumes of so-called whole-slide images—high-resolution scans of complete pathological slides—has become a cornerstone of the development of novel artificial intelligence methods in pathology for diagnostic use, education/training of pathologists, and research. Nevertheless, a methodology based on risk analysis for evaluating the privacy risks associated with sharing such imaging data and applying the principle “as open as possible and as closed as necessary” is still lacking. In this article, we develop a model for privacy risk analysis for whole-slide images which focuses primarily on identity disclosure attacks, as these are the most important from a regulatory perspective. We introduce a taxonomy of whole-slide images with respect to privacy risks and mathematical model for risk assessment and design . Based on this risk assessment model and the taxonomy, we conduct a series of experiments to demonstrate the risks using real-world imaging data. Finally, we develop guidelines for risk assessment and recommendations for low-risk sharing of whole-slide image data.

Links

90125, large research infrastructures

Name: BBMRI-CZ III

Citovat

HOLUB, Petr, Heimo MÜLLER, Tomáš BÍL, Luca PIREDDU, Markus PLASS, Fabian PRASSER, Irene SCHLÜNDER, Kurt ZATLOUKAL, Rudolf NENUTIL and Tomáš BRÁZDIL. Privacy risks of whole-slide image sharing in digital pathology. Nature Communications. 2023, vol. 14, No 2577, p. 1-15. ISSN 2041-1723. Available from: https://dx.doi.org/10.1038/s41467-023-37991-y.

@article{2280138,
   author = {Holub, Petr and Müller, Heimo and Bíl, Tomáš and Pireddu, Luca and Plass, Markus and Prasser, Fabian and Schlünder, Irene and Zatloukal, Kurt and Nenutil, Rudolf and Brázdil, Tomáš},
   article_number = {2577},
   doi = {http://dx.doi.org/10.1038/s41467-023-37991-y},
   keywords = {digital pathology; whole slide images; anonymity; privacy risks; data sharing},
   language = {eng},
   issn = {2041-1723},
   journal = {Nature Communications},
   title = {Privacy risks of whole-slide image sharing in digital pathology},
   url = {https://www.nature.com/articles/s41467-023-37991-y},
   volume = {14},
   year = {2023}
}

TY  - JOUR
ID  - 2280138
AU  - Holub, Petr - Müller, Heimo - Bíl, Tomáš - Pireddu, Luca - Plass, Markus - Prasser, Fabian - Schlünder, Irene - Zatloukal, Kurt - Nenutil, Rudolf - Brázdil, Tomáš
PY  - 2023
TI  - Privacy risks of whole-slide image sharing in digital pathology
JF  - Nature Communications
VL  - 14
IS  - 2577
SP  - 1-15
EP  - 1-15
SN  - 20411723
KW  - digital pathology
KW  - whole slide images
KW  - anonymity
KW  - privacy risks
KW  - data sharing
UR  - https://www.nature.com/articles/s41467-023-37991-y
N2  - Access to large volumes of so-called whole-slide images—high-resolution scans of complete pathological slides—has become a cornerstone of the development of novel artificial intelligence methods in pathology for diagnostic use, education/training of pathologists, and research. Nevertheless, a methodology based on risk analysis for evaluating the privacy risks associated with sharing such imaging data and applying the principle “as open as possible and as closed as necessary” is still lacking. In this article, we develop a model for privacy risk analysis for whole-slide images which focuses primarily on identity disclosure attacks, as these are the most important from a regulatory perspective. We introduce a taxonomy of whole-slide images with respect to privacy risks and mathematical model for risk assessment and design . Based on this risk assessment model and the taxonomy, we conduct a series of experiments to demonstrate the risks using real-world imaging data. Finally, we develop guidelines for risk assessment and recommendations for low-risk sharing of whole-slide image data.
ER  -

HOLUB, Petr, Heimo MÜLLER, Tomáš BÍL, Luca PIREDDU, Markus PLASS, Fabian PRASSER, Irene SCHLÜNDER, Kurt ZATLOUKAL, Rudolf NENUTIL and Tomáš BRÁZDIL. Privacy risks of whole-slide image sharing in digital pathology. \textit{Nature Communications}. 2023, vol.~14, No~2577, p.~1-15. ISSN~2041-1723. Available from: https://dx.doi.org/10.1038/s41467-023-37991-y.

Detailed Information on Publication Record