Time series medical images are an important type of medical data that contain rich spatio-temporal information. Recently, computer-aided diagnosis algorithms are often used on honest-but-curious servers to analyze medical images, which introduces severe privacy concerns. This paper proposes a convolutional-LSTM network (HE-CLSTM) for analyzing encrypted medical image sequences. Specifically, several convolutional blocks and modified LSTM layers (HE-LSTM) are constructed to extract discriminative spatio-temporal features. Moreover, a weighted unit and sequence voting layer are designed to improve accuracy while reducing the missed diagnosis rate. The experimental results on two benchmarks prove the superiority of HE-CLSTM on analyzing encrypted medical image sequences.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.