Documenting the de-identification process of clinical and imaging data for AI for health imaging projects.

Autor: Kondylakis H; FORTH-ICS, Heraklion, Crete, Greece. kondylak@ics.forth.gr., Catalan R; La Fe University and Polytechnic Hospital, La Fe Health Research Institute, Valencia, Spain., Alabart SM; TIC Salut Social Foundation, Barcelona, Spain., Barelle C; European Dynamics, Luxembourg, Luxembourg., Bizopoulos P; Centre for Research & Technology Hellas, Information Technologies Institute (CERTH-ITI), Central Directorate, Thermi, Thessaloniki, Greece., Bobowicz M; Medical University of Gdańsk, Gdańsk, Poland., Bona J; University of Arkansas for Medical Sciences, Little Rock, AR, USA., Fotiadis DI; Unit of Medical Technology and Intelligent Information Systems, Department of Materials Science and Engineering, University of Ioannina, Ioannina, Greece., Garcia T; Centre for Genomic Regulation (CRG), The Barcelona Institute of Science and Technology, Barcelona, Spain., Gomez I; La Fe University and Polytechnic Hospital, La Fe Health Research Institute, Valencia, Spain., Jimenez-Pastor A; Quantitative Imaging Biomarkers in Medicine, Quibim, Valencia, Spain., Karatzanis G; FORTH-ICS, Heraklion, Crete, Greece., Lekadir K; Artificial Intelligence in Medicine Labm Universitat de Barcelona, Barcelona, Spain., Kogut-Czarkowska M; Timelex BV/SRL, Brussels, Belgium., Lalas A; Centre for Research & Technology Hellas, Information Technologies Institute (CERTH-ITI), Central Directorate, Thermi, Thessaloniki, Greece., Marias K; FORTH-ICS, Heraklion, Crete, Greece., Marti-Bonmati L; Hospital Universitario y Politécnico La Fe, Grupo de Investigación Biomédica en Imagen IIS La Fe, Valencia, España., Munuera J; Quantitative Imaging Biomarkers in Medicine, Quibim, Valencia, Spain., Nikiforaki K; FORTH-ICS, Heraklion, Crete, Greece., Pelissier M; MEDEXPRIM, Labège, France., Prior F; University of Arkansas for Medical Sciences, Little Rock, AR, USA., Rutherford M; University of Arkansas for Medical Sciences, Little Rock, AR, USA., Saint-Aubert L; MEDEXPRIM, Labège, France., Sakellariou Z; Centre for Research & Technology Hellas, Information Technologies Institute (CERTH-ITI), Central Directorate, Thermi, Thessaloniki, Greece., Seymour K; MEDEXPRIM, Labège, France., Trouillard T; MEDEXPRIM, Labège, France., Votis K; Centre for Research & Technology Hellas, Information Technologies Institute (CERTH-ITI), Central Directorate, Thermi, Thessaloniki, Greece., Tsiknakis M; FORTH-ICS, Heraklion, Crete, Greece.
Jazyk: angličtina
Zdroj: Insights into imaging [Insights Imaging] 2024 May 31; Vol. 15 (1), pp. 130. Date of Electronic Publication: 2024 May 31.
DOI: 10.1186/s13244-024-01711-x
Abstrakt: Artificial intelligence (AI) is revolutionizing the field of medical imaging, holding the potential to shift medicine from a reactive "sick-care" approach to a proactive focus on healthcare and prevention. The successful development of AI in this domain relies on access to large, comprehensive, and standardized real-world datasets that accurately represent diverse populations and diseases. However, images and data are sensitive, and as such, before using them in any way the data needs to be modified to protect the privacy of the patients. This paper explores the approaches in the domain of five EU projects working on the creation of ethically compliant and GDPR-regulated European medical imaging platforms, focused on cancer-related data. It presents the individual approaches to the de-identification of imaging data, and describes the problems and the solutions adopted in each case. Further, lessons learned are provided, enabling future projects to optimally handle the problem of data de-identification. CRITICAL RELEVANCE STATEMENT: This paper presents key approaches from five flagship EU projects for the de-identification of imaging and clinical data offering valuable insights and guidelines in the domain. KEY POINTS: ΑΙ models for health imaging require access to large amounts of data. Access to large imaging datasets requires an appropriate de-identification process. This paper provides de-identification guidelines from the AI for health imaging (AI4HI) projects.
(© 2024. The Author(s).)
Databáze: MEDLINE
Externí odkaz:
Nepřihlášeným uživatelům se plný text nezobrazuje