Interpreting Deep Learning based Cerebral Palsy Prediction with Channel Attention

Zhu, Manli, Men, Qianhui, Ho, Edmond, Leung, Howard and Shum, Hubert (2021) Interpreting Deep Learning based Cerebral Palsy Prediction with Channel Attention. In: IEEE BHI 2021: IEEE International Conference on Biomedical and Health Informatics (BHI) : Reshaping healthcare through advanced AI-enabled health informatics for a better quality of life, 27-30 Jul 2021, Virtual. (In Press)

Detecting_baby_s_abnormal_movements_with_attention.pdf - Accepted Version

Download (8MB) | Preview


Early prediction of cerebral palsy is essential as it leads to early treatment and monitoring. Deep learning has shown promising results in biomedical engineering thanks to its capacity of modelling complicated data with its non-linear architecture. However, due to their complex structure, deep learning models are generally not interpretable by humans, making it difficult for clinicians to rely on the findings. In this paper, we propose a channel attention module for deep learning models to predict cerebral palsy from infants' body movements, which highlights the key features (i.e. body joints) the model identifies as important, thereby indicating why certain diagnostic results are found. To highlight the capacity of the deep network in modelling input features, we utilize raw joint positions instead of hand-crafted features. We validate our system with a real-world infant movement dataset. Our proposed channel attention module enables the visualization of the vital joints to this disease that the network considers. Our system achieves 91.67% accuracy, suppressing other state-of-the-art deep learning methods.

Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: Cerebral palsy, deep learning, artificial neural network, channel attention
Subjects: B900 Others in Subjects allied to Medicine
G400 Computer Science
Department: Faculties > Engineering and Environment > Computer and Information Sciences
Depositing User: John Coen
Date Deposited: 15 Jun 2021 07:29
Last Modified: 31 Jul 2021 11:00

Actions (login required)

View Item View Item


Downloads per month over past year

View more statistics