Pmir: an efficient privacy-preserving medical images search in cloud-assisted scenario
Neural Computing and Applications(2023)
Abstract
With the advancement of content-based medical image retrieval (CBMIR) technology which is used as a convenient assistant for medical diagnosis. However, the potential risk of privacy disclosure in CBMIR remains a concern due to the involvement of patients’ sensitive information in medical images. To address this issue, we have proposed an efficient scheme to achieve privacy-preserving medical image retrieval, named PMIR. The primary objective of PMIR is to enhance the accuracy of medical image retrieval while ensuring privacy protection. In PMIR, medical institutions with large repositories of medical images can securely upload to the cloud server with their image data and encryption indexes. Subsequently, users who successfully registered from medical institutions are able to enjoy convenient image retrieval services without revealing their sensitive information and query attributes to the cloud server. The proposed approach emphasizes a privacy-preserving policy mechanism, which empowers users with the right to choose rather than relying solely on service providers. Through rigorous security analysis, it is demonstrated that PMIR can effectively withstand various known security threats. Additionally, experimental results highlight the substantial reduction in communication overhead achieved by PMIR, ultimately providing a seamless and secure search experience for users.
MoreTranslated text
Key words
Privacy protection,Policy mechanism,Content-based medical image retrieval (CBMIR),Cloud-assisted,Security
AI Read Science
Must-Reading Tree
Example
![](https://originalfileserver.aminer.cn/sys/aminer/pubs/mrt_preview.jpeg)
Generate MRT to find the research sequence of this paper
Chat Paper
Summary is being generated by the instructions you defined