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.
Original language | English |
---|---|
Title of host publication | 2021 IEEE EMBS International Conference on Biomedical and Health Informatics (BHI) |
Place of Publication | Piscataway |
Publisher | IEEE |
Number of pages | 4 |
ISBN (Electronic) | 9781665447706 |
ISBN (Print) | 9781665403580 |
DOIs | |
Publication status | Published - 27 Jul 2021 |
Event | IEEE International Conference on Biomedical and Health Informatics (BHI) : Reshaping healthcare through advanced AI-enabled health informatics for a better quality of life - Virtual Duration: 27 Jul 2021 → 30 Jul 2021 https://www.bhi-bsn-2021.org/?page_id=2336 |
Publication series
Name | IEEE EMBS International Conference on Biomedical and Health Informatics |
---|---|
Publisher | IEEE |
ISSN (Print) | 2641-3590 |
ISSN (Electronic) | 2641-3604 |
Conference
Conference | IEEE International Conference on Biomedical and Health Informatics (BHI) |
---|---|
Abbreviated title | IEEE BHI 2021 |
Period | 27/07/21 → 30/07/21 |
Internet address |