A Novel End-to-End 3-D Residual and Attention Enhancement Joint Few-Shot Learning Model for Huntington Clinical Assessment

Jiehui Huang, Lishan Lin, Jiaying Lin, Jun Zhou, Baiqiao Yin, Weichen Lyu, Fengjuan Su, Kang Yuan, Mansi Cai, Yucheng Li, Haifan Kong, Jean-Marc Burgunder, Zhong Pei, Calvin Yu-Chian Chen

Abstract: Sign assessment in Huntington’s disease (HD) holds significant importance for its treatment. However, most of the existing methods to assess motor signs have shortcomings. Newer ones are in development but may be expensive, and few studies have employed end-to-end video-based motor assessments. To fill this research gap, we developed a few-shot learning model based on a 3-D residual and attention enhancement joint learning approach. We first collected video data from 48 HD patients and enhanced the key data. We then designed a 3-D convolutional module based on channel-spatial attention to initially extract data features. After that, an excitation-based 3-D residual convolutional module was designed for feature learning. Finally, we used a fully connected layer based on the channel-spatial attention to complete feature compression and obtain the assessment results. Our results show that the classification accuracy and recall of our model achieve state-of-the-art performance. The proposed lightweight HD disease motor assessment model is an improvement over other previous methods. Further developments in the methods are expected to provide a suitable baseline and follow-up assessment tool for future HD video-based studies. Furthermore, our proposed solution can be implemented with consumer-grade cameras, holding considerable potential for extensive implementation in HD telemedicine. The source code can be found at: https://github.com/JackAILab/RAJNet.