Interpreting Deep Learning based Cerebral Palsy Prediction with Channel Attention

manli zhu, qianhui men, edmond s. l. ho, howard leung and hubert p. h. shum
Proceedings of the 2021 IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI), 2021

Citation: 6##

Interpreting Deep Learning based Cerebral Palsy Prediction with Channel Attention
## Citation counts from Google Scholar as of 2022

Abstract

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.

Downloads

YouTube

Citations

BibTeX

@inproceedings{zhu21interpreting,
 author={Zhu, Manli and Men, Qianhui and Ho, Edmond S. L. and Leung, Howard and Shum, Hubert P. H.},
 booktitle={Proceedings of the 2021 IEEE-EMBS International Conference on Biomedical and Health Informatics},
 series={BHI '21},
 title={Interpreting Deep Learning based Cerebral Palsy Prediction with Channel Attention},
 year={2021},
 month={Jul},
 pages={1--4},
 numpages={4},
 doi={10.1109/BHI50953.2021.9508619},
 issn={2641-3604},
 publisher={IEEE},
}

RIS

TY  - CONF
AU  - Zhu, Manli
AU  - Men, Qianhui
AU  - Ho, Edmond S. L.
AU  - Leung, Howard
AU  - Shum, Hubert P. H.
T2  - Proceedings of the 2021 IEEE-EMBS International Conference on Biomedical and Health Informatics
TI  - Interpreting Deep Learning based Cerebral Palsy Prediction with Channel Attention
PY  - 2021
Y1  - Jul 2021
SP  - 1
EP  - 4
DO  - 10.1109/BHI50953.2021.9508619
SN  - 2641-3604
PB  - IEEE
ER  - 

Plain Text

Manli Zhu, Qianhui Men, Edmond S. L. Ho, Howard Leung and Hubert P. H. Shum, "Interpreting Deep Learning based Cerebral Palsy Prediction with Channel Attention," in BHI '21: Proceedings of the 2021 IEEE-EMBS International Conference on Biomedical and Health Informatics, pp. 1-4, IEEE, Jul 2021.

Similar Research

Manli Zhu, Qianhui Men, Edmond S. L. Ho, Howard Leung and Hubert P. H. Shum, "A Two-stream Convolutional Network for Musculoskeletal and Neurological Disorders Prediction", Journal of Medical Systems (JMS), 2022
Haozheng Zhang, Hubert P. H. Shum and Edmond S. L. Ho, "Cerebral Palsy Prediction with Frequency Attention Informed Graph Convolutional Networks", Proceedings of the 2022 Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), 2022
Haozheng Zhang, Edmond S. L. Ho, Xiatian Zhang and Hubert P. H. Shum, "Pose-based Tremor Classification for Parkinson’s Disease Diagnosis from Video", Proceedings of the 2022 International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), 2022
Haozheng Zhang, Edmond S. L. Ho and Hubert P. H. Shum, "CP-AGCN: Pytorch-based Attention Informed Graph Convolutional Network for Identifying Infants at Risk of Cerebral Palsy", Software Impacts (SIMPAC), 2022
Kevin D. McCay, Edmond S. L. Ho, Hubert P. H. Shum, Gerhard Fehringer, Claire Marcroft and Nicholas Embleton, "Abnormal Infant Movements Classification with Deep Learning on Pose-based Features", IEEE Access, 2020
Kevin D. McCay, Pengpeng Hu, Hubert P. H. Shum, Wai Lok Woo, Claire Marcroft, Nicholas D. Embleton, Adrian Munteanu and Edmond S. L. Ho, "A Pose-based Feature Fusion and Classification Framework for the Early Prediction of Cerebral Palsy in Infants", IEEE Transactions on Neural Systems and Rehabilitation Engineering (TNSRE), 2022
Worasak Rueangsirarak, Jingtian Zhang, Nauman Aslam and Hubert P. H. Shum, "Automatic Musculoskeletal and Neurological Disorder Diagnosis with Relative Joint Displacement from Human Gait", IEEE Transactions on Neural Systems and Rehabilitation Engineering (TNSRE), 2018

 

 
 

Last updated on 24 September 2022, RSS Feeds