Parkinson's severity diagnosis explainable model based on 3D multi-head attention residual network

• Published in: Computers in biology and medicine Vol. 170; p. 107959
• Main Authors: Huang, Jiehui, Lin, Lishan, Yu, Fengcheng, He, Xuedong, Song, Wenhui, Lin, Jiaying, Tang, Zhenchao, Yuan, Kang, Li, Yucheng, Huang, Haofan, Pei, Zhong, Xian, Wenbiao, Yu-Chian Chen, Calvin
• Format: Journal Article
• Language: English
• Published: United States Elsevier Ltd 01.03.2024; Elsevier Limited
• Subjects: Biomarkers; Computer networks; Convolution; Data Compression; Deep learning; Diagnosis; Explainable deep learning; Humans; Magnetic resonance imaging; Mathematical models; Medical diagnosis; Movement disorders; Multi-head attention; Neural networks; Neurodegenerative diseases; Parkinson Disease - diagnosis; Parkinson's disease; Parkinson's disease diagnosis; Severity diagnosis; Software; Source code; Telemedicine; Three dimensional models; Video compression; Parkinson's disease diagnosis; Severity diagnosis; Telemedicine; Explainable deep learning; Multi-head attention
• ISSN: 0010-4825; 1879-0534
• DOI: 10.1016/j.compbiomed.2024.107959

The severity evaluation of Parkinson's disease (PD) is of great significance for the treatment of PD. However, existing methods either have limitations based on prior knowledge or are invasive methods. To propose a more generalized severity evaluation model, this paper proposes an explainable 3D multi-head attention residual convolution network. First, we introduce the 3D attention-based convolution layer to extract video features. Second, features will be fed into LSTM and residual backbone networks, which can be used to capture the contextual information of the video. Finally, we design a feature compression module to condense the learned contextual features. We develop some interpretable experiments to better explain this black-box model so that it can be better generalized. Experiments show that our model can achieve state-of-the-art diagnosis performance. The proposed lightweight but effective model is expected to serve as a suitable end-to-end deep learning baseline in future research on PD video-based severity evaluation and has the potential for large-scale application in PD telemedicine. The source code is available at https://github.com/JackAILab/MARNet. •Developed a facial video-based end-to-end PD severity diagnosis deep learning model.•The effective embedding of LSTM and attention modules enhances the model performance.•Provides an interpretable experiment consistent with clinical diagnostic experience.•The lightweight model achieves competitive and reliable diagnostic results.