Pain Assessment Archives - Tech4Animals

Comparison Between AI and Human Expert Performance in Acute Pain Assessment in Sheep

annazam — Sun, 03 Aug 2025 09:31:37 +0000

This study compares the effectiveness of Artificial Intelligence (AI) against human experts in assessing acute pain in sheep, utilizing video recordings and photographs from 48 sheep undergoing surgery. The research specifically evaluates AI’s performance using facial expression analysis (SFPES) and behavioral scoring (USAPS), which is considered the “golden standard.” Findings indicate that the AI significantly outperformed humans in facial pain recognition and equaled human performance in behavioral pain assessment, despite only having access to facial images. The authors suggest these results have substantial implications for clinical veterinary practice, proposing that AI could transform animal pain assessment by offering a more objective and less biased method than traditional human scoring.

The post Comparison Between AI and Human Expert Performance in Acute Pain Assessment in Sheep appeared first on Tech4Animals.

Automated Video-based Pain Recognition in Cats using Facial Landmarks

annazam — Sat, 03 Aug 2024 06:55:30 +0000

This study introduces a significant advancement in feline pain assessment with a fully automated, end-to-end artificial intelligence (AI) pipeline for recognizing pain in cats directly from raw video footage, eliminating the need for manual frame selection or landmark annotation. Recognizing that facial expressions reflect affective states in mammals and that assessing pain in cats is particularly challenging due to subtle facial cues and lack of consensus on behavioral indicators, this new AI pipeline addresses limitations of previous manual and static image-based methods. By analyzing changes in 48 facial landmarks over time, the pipeline achieved over 70% and 66% accuracy on two different cat pain datasets, outperforming prior single-frame approaches, which strongly indicates that dynamics matter in cat pain recognition. While the central frame contributes most to pain prediction, preceding and subsequent frames also have a notable impact. This groundbreaking work paves the way for practical applications, such as the development of mobile apps akin to PainChek for human patients, to facilitate more objective and real-time pain assessment in veterinary clinics and at home

The post Automated Video-based Pain Recognition in Cats using Facial Landmarks appeared first on Tech4Animals.

Automated Video-based Pain Recognition in Cats using Facial Landmarks

annazam — Fri, 16 Aug 2024 20:33:48 +0000

This paper introduces a significant advancement in automated video-based pain recognition in cats by presenting an end-to-end artificial intelligence (AI) pipeline that requires no manual efforts in selecting suitable images or annotating facial landmarks. Unlike previous approaches that relied on static single images, this new pipeline works with raw video input, optimizing the capture of the temporal dimension of visual information, which is critical for accurate pain detection. The AI pipeline first automatically produces 48 cat facial landmarks on each video frame, then uses this time-series signal to predict the presence of cat pain. Tested on two different cat pain datasets, Finka et al. and TiHo Cat Pain, the pipeline achieved over 70% and 66% accuracy respectively, notably outperforming previous automated landmark-based methods that used single frames, thereby indicating that dynamics matter in cat pain recognition. The study also defines metrics to measure deficiencies in video datasets, such as occluded faces or inaccurate landmark detection, and investigates their impact on performance. The research highlights the potential for practical applications, like mobile apps for use in clinical settings or by pet owners, similar to human pain assessment tools, though further work is needed to address dataset diversity and real-time computational efficiency.

The post Automated Video-based Pain Recognition in Cats using Facial Landmarks appeared first on Tech4Animals.

Deep Learning for Video-based Automated Pain Recognition in Rabbits

annazam — Wed, 16 Aug 2023 21:03:24 +0000

This study introduces the first AI model for automated detection of acute postoperative pain in rabbits, addressing a gap in pain assessment for this widely used experimental model and popular pet. Utilizing a dataset of video footage from 28 rabbits before and after surgery, the researchers developed an AI model that leverages both facial expressions and body posture. A key methodological contribution is a two-step approach that incorporates temporal information from video data without heavy computational burden, employing 1-second interval sampling and Grayscale Short-Term stacking (GrayST). Furthermore, a novel frame selection technique was applied, which selects the most informative frames based on classifier confidence levels, effectively reducing ‘noise’ from low-quality or obstructed video data. The model achieved an accuracy of over 87%, with the best performance observed when using the CLIP/ViT + Naive Bayes backbone combined with GrayST and the top-frame selection method. This approach not only improves accuracy but also effectively handles challenges like occlusion and varied camera angles often present in real-world animal video data.

The post Deep Learning for Video-based Automated Pain Recognition in Rabbits appeared first on Tech4Animals.

Explainable Automated Pain Recognition in Cats

annazam — Wed, 16 Aug 2023 21:03:28 +0000

This study investigated the feasibility of automated pain recognition in cats using AI models in a more realistic and heterogeneous setting. Researchers compared two approaches: a landmark-based (LDM) approach utilizing 48 manually annotated facial landmarks, and a deep learning (DL) approach (ResNet50), on a dataset of 84 client-owned cats of diverse breeds, ages, sexes, and medical histories, with pain levels scored by veterinary experts. The findings showed that the landmark-based approach performed better, achieving over 77% accuracy in pain detection, while the deep learning approach reached only above 65%. This suggests that the LDM approach is more robust for noisier, naturalistic populations, possibly because it better accounts for variability in cat facial morphology. Furthermore, using explainable AI methods, the study consistently revealed across both approaches that the mouth region was most important for machine pain classification, whereas the ears region was least important. The study acknowledged limitations, including the dataset size and the use of static images, suggesting future research should focus on larger datasets, video-based analysis, and the automation of facial landmark detection. The results ultimately support that AI-assisted recognition of negative affective states like pain from cat faces is feasible, although these tools should complement, not replace, clinical judgment.

The post Explainable Automated Pain Recognition in Cats appeared first on Tech4Animals.

Going Deeper than Tracking: A survey of computer-vision based recognition of animal pain and emotions

annazam — Wed, 16 Aug 2023 21:08:41 +0000

This study offers a comprehensive survey of computer vision-based research aimed at recognizing internal affective states in animals, such as pain and emotions, to enhance animal welfare. It specifically focuses on facial and bodily behavior analysis in mammals, extending beyond mere motion tracking. The survey highlights significant challenges, including the lack of a common definition for animal emotions, the inherent difficulty in establishing ground truth due to the absence of verbal communication, data scarcity, and morphological diversity across species. Methodological aspects covered include data collection practices (e.g., recording equipment and environment), annotation strategies (distinguishing between stimulus-based and behavior-based annotations), and data analysis approaches such as using single frames versus spatio-temporal sequences, parts-based versus holistic methods, and hand-crafted versus learned features (deep learning). The authors discuss the “black-box” nature of deep learning models, which can impede explainability crucial for clinical and welfare applications. To advance the field, the paper proposes best practice recommendations for handling data imbalance, applying robust cross-validation techniques (like leave-one-animal-out to ensure subject exclusivity), and exploring domain transfer methodologies. A critical future direction emphasized is the need for public, benchmark datasets to enable standardized comparisons and foster progress in this interdisciplinary area.

The post Going Deeper than Tracking: A survey of computer-vision based recognition of animal pain and emotions appeared first on Tech4Animals.

Automated Recognition of Pain in Cats

annazam — Sat, 20 Aug 2022 12:10:41 +0000

This paper presents the first comparative study on automated pain recognition in domestic short-haired cats using facial images. The researchers compared two distinct approaches: one utilizing convolutional neural networks (ResNet50) that take raw images as input, and another employing machine learning models based on 48 geometric facial landmarks, inspired by the catFACS system. Data was collected from 29 cats undergoing ovariohysterectomy at various time points corresponding to different pain intensities, with a final balanced dataset of 464 images from 26 cats classified as ‘Pain’ or ‘No Pain’. Both approaches demonstrated comparable accuracy of above 72% in classifying pain, indicating their potential for automated cat pain detection. The study concludes that the information contained within the 48 selected geometric facial landmarks is sufficient for pain classification, yielding accuracy similar to deep learning models that process raw image data. While this represents a significant step forward, the authors note that further methodological improvements, such as incorporating additional behavioral information and including more diverse cat populations, are necessary for real-world application and to increase generalizability and robustness.

The post Automated Recognition of Pain in Cats appeared first on Tech4Animals.

Comparing the Performance of Deep Learning Video-based Models and Trained Veterinarians in Cattle Pain Assessment

annazam — Wed, 18 Mar 2026 13:30:54 +0000

Accurately assessing pain in cattle remains a significant challenge because these prey animals naturally conceal signs of discomfort, which can lead to subjective and highly variable human evaluations. To address this limitation, this study introduced a novel, video-based deep learning framework designed to automatically detect subtle pain-related expressions and behavioral changes. Using computer vision techniques to analyze temporal and spatial features in video recordings of bulls, the system’s performance was compared against standardized scoring by trained veterinarians. The machine learning model achieved an impressive 97% accuracy in pain classification. This performance successfully outperformed video-based human assessments and matched the accuracy of real-time expert evaluations, offering a highly objective and scalable tool for monitoring livestock welfare.

The post Comparing the Performance of Deep Learning Video-based Models and Trained Veterinarians in Cattle Pain Assessment appeared first on Tech4Animals.

Time Budget Analysis with Large Vision Language Models for Automated Pain Assessment in Horses

annazam — Fri, 06 Mar 2026 14:22:28 +0000

Assessing pain in horses is challenging because they instinctively hide discomfort, but shifts in their daily behavioral routines can provide vital clues. To bypass the impracticality of continuous manual observation, this study developed an automated video analysis pipeline using Large Vision Language Models (LVLMs). Researchers applied these models to stall surveillance videos of hospitalized horses to track time spent on activities like resting, feeding, and moving. These time budgets were then fed into machine learning classifiers to distinguish between painful and non-painful states. The system achieved an 80% accuracy in pain detection, proving that LVLMs offer a scalable, non-invasive solution for equine welfare monitoring without requiring expensive manual data annotation.

The post Time Budget Analysis with Large Vision Language Models for Automated Pain Assessment in Horses appeared first on Tech4Animals.