A deep neural network to assess spontaneous pain from mouse facial expressions

Abstract

Grimace scales quantify characteristic facial expressions associated with spontaneous pain in rodents and other mammals. However, these scales have not been widely adopted largely because of the time and effort required for highly trained humans to manually score the images. Convoluted neural networks were recently developed that distinguish individual humans and objects in images. Here, we trained one of these networks, the InceptionV3 convolutional neural net, with a large set of human-scored mouse images. Output consists of a binary pain/no-pain assessment and a confidence score. Our automated Mouse Grimace Scale integrates these two outputs and is highly accurate (94%) at assessing the presence of pain in mice across different experimental assays. In addition, we used a novel set of "pain" and "no pain" images to show that automated Mouse Grimace Scale scores are highly correlated with human scores (Pearson's r = 0.75). Moreover, the automated Mouse Grimace Scale classified a greater proportion of images as "pain" following laparotomy surgery when compared to animals receiving a sham surgery or a post-surgical analgesic. Together, these findings suggest that the automated Mouse Grimace Scale can eliminate the need for tedious human scoring of images and provide an objective and rapid way to quantify spontaneous pain and pain relief in mice.

Keywords: Spontaneous pain; animal models; facial expressions; machine learning.

Figure 1.

Setups used to capture continuous video footage of mice. Examples of mice grimacing in (a) the traditional recording setup with mice enclosed in Plexiglas boxes and (b) the new elevated cliff recording setup. Mice face towards the visual cliff for most of the recording session in the new setup, allowing the use of a single camera instead of two cameras. The camera also captures clearer images (without reflections) through air than through the Plexiglas partition.

Figure 2.

Direct correlation between human and machine grimace scores using novel grimace images. aMGS confidence scores were placed on a continuous scale, with −1.0 being equal to 100% confidence that the mouse image was not showing pain and 1.0 being equal to 100% confidence that the mouse image was showing pain. Resulting aMGS confidence scores were grouped by corresponding human MGS score. Bars represent mean ± SEM of transformed aMGS scores. Values significantly different from chance (**p < 0.01; ***p < 0.0001) according to one-sample t test. aMGS: automated Mouse Grimace Scale; MGS: Mouse Grimace Scale. “Chance”= 0.5

Figure 3.

The aMGS correctly predicted analgesic efficacy in a post-operative pain assay. High-confidence images collected 60 min (a) or 30 min (b) following surgery. Bars represent mean ± SEM of difference scores (number of pain images after surgery – number of pain images at baseline). BL: baseline; SHAM: sham surgery; LAP: laparotomized animal; LAP + CAR: laparotomized animal given 50 mg/kg of the NSAID carprofen immediately following surgery. n = 12 to 14 for all conditions. Values *p < 0.05; ***p < 0.001; °p = 0.074 as determined by Tukey Test following one-way ANOVA.