Neonatal Pain Expression Recognition Using Transfer Learning

TL;DR

This paper demonstrates that transfer learning with pre-trained CNNs effectively classifies neonatal pain expressions, outperforming traditional features and improving accuracy by combining deep and handcrafted features.

Contribution

The study introduces a novel pipeline using transfer learning from face recognition CNNs for neonatal pain expression recognition, enhancing classification performance.

Findings

Achieved 0.841 AUC and 90.34% accuracy with deep features.

Combining deep and traditional features increased accuracy to 92.71% and AUC to 0.948.

Transfer learning offers a practical alternative to training CNNs from scratch for this task.

Abstract

Transfer learning using pre-trained Convolutional Neural Networks (CNNs) has been successfully applied to images for different classification tasks. In this paper, we propose a new pipeline for pain expression recognition in neonates using transfer learning. Specifically, we propose to exploit a pre-trained CNN that was originally trained on a relatively similar dataset for face recognition (VGG Face) as well as CNNs that were pre-trained on a relatively different dataset for image classification (iVGG F,M, and S) to extract deep features from neonates' faces. In the final stage, several supervised machine learning classifiers are trained to classify neonates' facial expression into pain or no pain expression. The proposed pipeline achieved, on a testing dataset, 0.841 AUC and 90.34 accuracy, which is approx. 7 higher than the accuracy of handcrafted traditional features. We also propose to combine deep features with traditional features and hypothesize that the mixed features would improve pain classification performance. Combining deep features with traditional features achieved 92.71 accuracy and 0.948 AUC. These results show that transfer learning, which is a faster and more practical option than training CNN from the scratch, can be used to extract useful features for pain expression recognition in neonates. It also shows that combining deep features with traditional handcrafted features is a good practice to improve the performance of pain expression recognition and possibly the performance of similar applications.