eCite Digital Repository

Privacy-preserving time series medical images analysis using a hybrid deep learning framework

Citation

Yue, Z and Ding, S and Zhao, L and Zhang, Y and Cao, Z and Tanveer, M and Jolfaei, A and Zheng, X, Privacy-preserving time series medical images analysis using a hybrid deep learning framework, ACM Transactions on Internet Technology, 37, (4) Article 11. ISSN 1533-5399 (2020) [Refereed Article]

Copyright Statement

Copyright 2019 Association for Computing Machinery

Official URL: https://dl.acm.org/journal/toit

DOI: doi:10.1145/3383779

Abstract

Time series medical images are an important type of medical data that contain rich temporal and spatial information. As a state of the art, computer-aided diagnosis (CAD) algorithms are usually used on these image sequences to improve analysis accuracy. However, such CAD algorithms are often required to upload medical images to honest-but-curious servers, which introduces severe privacy concerns. To preserve privacy, the existing CAD algorithms support analysis on each encrypted image but not on the whole encrypted image sequences, which leads to the loss of important temporal information among frames. To meet this challenge, a convolutional-LSTM network, named HE-CLSTM, is proposed for analyzing time series medical images encrypted by a fully homomorphic encryption mechanism. Specifically, several convolutional blocks are constructed to extract discriminative spatial features and LSTM-based sequence analysis layers (HE-LSTM) are leveraged to encode temporal information from the encrypted image sequences. Moreover, a weighted unit and a sequence voting layer are designed to incorporate both spatial and temporal features with different weights to improve performance while reducing the missed diagnosis rate. The experimental results on two challenging benchmarks (a Cervigram dataset and the BreaKHis public dataset) provide strong evidence that our framework can encode visual representations and sequential dynamics from encrypted medical image sequences; our method achieved AUCs above 0.94 both on the Cervigram and BreaKHis datasets, constituting a significant margin of statistical improvement compared with several competing methods.

Item Details

Item Type:Refereed Article
Keywords:hybrid deep learning framework
Research Division:Information and Computing Sciences
Research Group:Machine learning
Research Field:Neural networks
Objective Division:Defence
Objective Group:Defence
Objective Field:Intelligence, surveillance and space
UTAS Author:Cao, Z (Dr Zehong Cao)
ID Code:137967
Year Published:2020 (online first 2019)
Deposited By:Information and Communication Technology
Deposited On:2020-03-17
Last Modified:2020-05-21
Downloads:0

Repository Staff Only: item control page