Privacy-Preserving Distributed Similarity Retrieval of Large CT Image Sequence Database in Mobile Telemedicine Networks

Abstract

As computed tomography image (CTI) sequence can be regarded as a medical image set, which contains several neighboring and visually similar CTI s with temporal information, conducting an efficient similarity retrieval of the large CTI sequences poses great challenge. Finding the similar CTI sequences can assist diagnosis and treatment by allowing physicians to quickly locate pathological images of lesion tissues, accurately find the source of disease. The paper proposes a progressive Privacy-preserving similarity Retrieval scheme for the CTI Sequences in the mobile telemedicine network (MTN) called the P RS method. To better facilitate the P RS processing, five enabling techniques are devised: 1) key CTI (KCTI)-based similarity measure, 2) local privacy preserving scheme, 3) zero-distance (ZD)-based distributed storage scheme, 4) uniform distributed index framework, and 5) crowd-assisted verification. Extensive experiments demonstrate that the retrieval efficiency of our proposed P RS method is about 90% higher than that of the existing ones.

Keywords

• Computed tomography image
• privacy preserving
• mobile telemedicine network
• similarity retrieval