Classification networks for continuous automatic pain intensity monitoring in video using facial expression on the X-ITE Pain Database

Classification networks for continuous automatic pain intensity monitoring in video using facial expression on the X-ITE Pain Database

So far, the current methods in the clinical application do not facilitate continuous monitoring for pain and are unreliable, especially for vulnerable patients. In contrast, several automated methods have been proposed for this task by using facial features that were extracted independently from every frame of a given sequence. However, the obtained results were poor due to the failure to represent movement dynamics. To solve this problem, this work introduces three distinct methods regarding classification to monitor continuous pain intensity: (1) A Random Forest classifier (RFc) baseline method, (2) Long-Short Term Memory (LSTM) method, and (3) LSTM using sample weighting method (LSTM-SW). In this study, we conducted experiments with 11 datasets regarding classification, then compared results to regression results in Othman et al. (2021). Experimental results showed that the LSTM & LSTM-SW methods for continuous automatic pain intensity recognition performed better than guessing and RFc except with small datasets such as the reduced tonic datasets.

Fulltext Access

https://doi.org/10.1016/j.jvcir.2022.103743

Citing

@inproceedings{OthmanMultimodalPain2022,
    title = {Classification networks for continuous automatic pain intensity monitoring in video using facial expression on the X-ITE Pain Database},
    author = {Ehsan Othman and Philipp Werner and Frerk Saxen and Ayoub Al-Hamadi and Sascha Gruss and Steffen Walter},
    booktitle = {Journal of Visual Communication and Image Representation},
    year = {2023}
    }