Data Hiding Algorithms for Healthcare Applications

Thesis event information

Date and time of the thesis defence

Place of the thesis defence

L10, Linnanmaa, University of Oulu

Topic of the dissertation

Data Hiding Algorithms for Healthcare Applications

Doctoral candidate

MSc Angelos Fylakis

Faculty and unit

University of Oulu Graduate School, Faculty of Information Technology and Electrical Engineering, Center for Machine Vision and Signal Analysis

Subject of study

Computer Science and Engineering

Opponent

Associate Professor Joni Kämäräinen, Tampere University

Custos

Professor Tapio Seppänen, Oulun yliopisto

Add event to calendar

Data Hiding Algorithms for Healthcare Applications

Developments in information technology affected healthcare, producing vast amounts of data and increasing demands associated with their efficient and secure transfer, storage and analysis. This research proposes data hiding algorithms, which are designed to imperceptibly hide sensitive information or complementary data in biomedical data. Those methods do not require new data types or infrastructures. This is because the information is hosted in the existing data structures exploiting their redundancy. The solutions satisfy two problems.

The first is the hospital-centric problem of providing efficient and secure management of data in hospital networks. For this purpose, for a given biomedical object, as for example an MRI image, the sensitive information, any complementary data and information to be used for authenticity proofing are embedded in the in the image itself in a reversible manner. Thus, when the image will be used in analyses all the necessary components will be available as they will be extracted from the image, authenticity can be proved, and the host image will be reversed to its initial state. Reversing the image is vital because even imperceptible modifications can cause errors in diagnoses.

The second is the patient-centric problem, including user authentication and issues of secure and efficient data transfer in eHealth systems for which, two data hiding methods were proposed. The first one hides additional information in users’ photos to increase the robustness of face biometrics. The second method protects sensitive user data collected by smartphones by hiding it inside non sensitive components. Concluding, the proposed algorithms introduced novel data hiding applications and competitive characteristics in existing applications.
Last updated: 20.11.2019