Deep Learning for Face Detection and Pain Assessment in Japanese macaques (Macaca fuscata).

Facial expressions have increasingly been used to assess emotional states in mammals. The recognition of pain in research animals is essential for their well-being and leads to more reliable research outcomes. Automating this process could contribute to early pain diagnosis and treatment. Artificial neural networks have become a popular option for image classification tasks in recent years due to the development of deep learning. In this study, we investigated the ability of a deep learning model to detect pain in Japanese macaques based on their facial expression. Thirty to 60 min of video footage from Japanese macaques undergoing laparotomy was used in the study. Macaques were recorded undisturbed in their cages before surgery (No Pain) and one day after the surgery before scheduled analgesia (Pain). Videos were processed for facial detection and image extraction with the algorithms RetinaFace (adding a bounding box around the face for image extraction) or Mask R-CNN (contouring the face for extraction). ResNet50 used 75% of the images to train systems; the other 25% were used for testing. Test accuracy varied from 48 to 54% after box extraction. The low accuracy of classification after box extraction was likely due to the incorporation of features that were not relevant for pain (for example, background, illumination, skin color, or objects in the enclosure). However, using contour extraction, preprocessing the images, and fine-tuning, the network resulted in 64% appropriate generalization. These results suggest that Mask R-CNN can be used for facial feature extractions and that the performance of the classifying model is relatively accurate for nonannotated single-frame images.

Investigating subtle changes in facial expression to assess acute pain in Japanese macaques.

Changes in facial expression provide cues for assessing emotional states in mammals and may provide non-verbal signals of pain. This study uses geometric morphometrics (GMM) to explore the facial shape variation in female Japanese macaques who underwent experimental laparotomy. Face image samples were collected from video footage of fourteen macaques before surgery and 1, 3, and 7 days after the procedure. Image samples in the pre-surgical condition were considered pain-free, and facial expressions emerging after surgery were investigated as potential indicators of pain. Landmarks for shape analysis were selected based on the underlying facial musculature and their corresponding facial action units and then annotated in 324 pre-surgical and 750 post-surgical images. The expression of pain is likely to vary between individuals. Tightly closed eyelids or squeezed eyes and lip tension were the most commonly observed facial changes on day 1 after surgery (p < 0.01974). A good overall inter-rater reliability [ICC = 0.99 (95% CI 0.75-1.0)] was observed with the method. The study emphasizes the importance of individualized assessment and provides a better understanding of facial cues to pain for captive macaque care.

Early reversal of ketamine/dexmedetomidine chemical immobilization by atipamezole in golden-headed lion tamarins (Leontopithecus chrysomelas).

BACKGROUND: A smooth and rapid recovery from anesthesia allowing safe release is desirable, especially for wild species. This study describes the clinical effects of the combination of dexmedetomidine and ketamine and the partial reversal with atipamezole in golden-headed lion tamarins. METHODS: Dexmedetomidine 10 µg kg-1 and ketamine 15 mg kg-1 were administered to 45 golden-headed lion tamarins undergoing vasectomy. Following surgery, animals were assigned to three groups: control (SAL; 0.9% NaCl), atipamezole 20 µg kg-1 (ATI20), and atipamezole 40 µg kg-1 (ATI40). RESULTS AND CONCLUSIONS: All animals presented great scores of sedation and muscle relaxation during the procedure. Recovery in the control group was smooth and uneventful. Salivation, muscle tremors, and head movements were observed in ATI 20 and ATI40. The administration of atipamezole did not change total recovery times (ATI20 69 ± 23 minutes; ATI40 72 ± 45 minutes; SAL 57 ± 23 minutes).

Continuous infusion of propofol or intermittent bolus of tiletamine-zolazepam in squirrel monkeys (Saimiri sciureus).

OBJECTIVE: To investigate an infusion of propofol for anesthesia in comparison to tiletamine-zolazepam anesthesia, evaluating physiological variables and recovery in squirrel monkeys. STUDY DESIGN: Prospective non-blinded randomized study. ANIMALS: Eight healthy squirrel monkeys (Saimiri sciureus), aged 3 years and weighing 0.340-0.695 kg. METHODS: Premedication was intramuscular midazolam (0.5 mg) and meperidine (4 mg). Anesthesia was induced with intravenous (IV) propofol (4 mg kg(-1)  minute(-1) ) and maintained with propofol starting at 0.4 mg kg(-1)  minute(-1) (PRO, n = 4) or IV tiletamine-zolazepam (5 mg kg(-1) ) and maintained with supplementary doses of TZ (TZ, n = 4). Cardiopulmonary variables were measured continuously. Arterial blood gases and lactate concentration were measured at the end of anesthesia. Quality and times of recovery were determined. Repeatedly measured data for significant differences were tested between groups with t-test and within groups by anova. RESULTS: Median time for induction of anesthesia in PRO was 180 seconds. Mean maintenance infusion rate of propofol was 0.43 ± 0.05 mg kg(-1)  minute(-1) , varying during the 1 hour period. One monkey died after administration of TZ; others required 1, 4, or 8 supplemental doses. Cardiopulmonary variables were similar between groups, but hypotension was recorded. Recovery times to ventral recumbency in PRO (32 ± 17 minutes) and TZ (84 ± 11 minutes) and normal ambulation in PRO (58 ± 22 minutes) and TZ (358 ± 109minutes) were significantly different (p < 0.05). Recovery quality was superior in PRO, with less ataxia and fewer unsuccessful attempts to stand. Lactate concentration was not different between treatments. CONCLUSIONS AND CLINICAL RELEVANCE: Cardiopulmonary variables were similar between protocols, aside from the higher incidence of hypotension in PRO, indicating that further studies with a larger number of animals are required. Compared to tiletamine-zolazepam, propofol anesthesia provided faster and superior anesthetic recovery in these animals.

Continuous infusion of propofol or intermittent bolus of tiletamine-zolazepam in feline night monkeys (Aotus infulatus).

BACKGROUND: Although commonly used, dissociative anesthesia results in unsatisfactory and long recovery periods. The intravenous anesthetic propofol seems to be the most advantageous solution. The objectives of this study were to investigate the required infusion rate of propofol to maintain surgical anesthesia and to compare it to tiletamine-zolazepam in Aotus infulatus. METHODS: Eight healthy feline night monkeys were anesthetized with propofol (PRO) or tiletamine-zolazepam (TZ) during 60 minutes. Cardiopulmonary parameters, arterial blood gases and lactate and quality and times to recovery were determined. RESULTS: Mean infusion rate of propofol was 0.53 ± 0.10 mg/kg/minute. Cardiopulmonary effects did not show marked differences between groups. Times for hanging, ventral recumbency, and normal ambulation were lower in PRO. Establishment of desirable anesthetic depth was easier, recovery quality was superior, and lactate levels were lower in PRO. CONCLUSIONS: Compared with tiletamine-zolazepam, minor post-anesthetic adverse events should be expected with propofol anesthesia, as well as faster and better anesthetic recovery.