Latest in Veterinary AI
Curated articles from research, industry, and news sources
Loading articles...
Curated articles from research, industry, and news sources
Integrative transcriptomics and machine learning reveal key regulatory genes for meat quality traits in pigs.
The ImageVue DR50 Plus Veterinary Digital Imaging System combines high-definition imaging that relies on artificial intelligence (AI). The digital solution system from IDEXX also uses artificial intelligence to help improve veterinary team workflows.
Comparing the performance of deep learning video-based models and trained veterinarians in cattle pain assessment.
The SATELLAI Collar offers AI-powered insights into dogs' behavior, energy levels, and rest patterns, representing a new partnership bringing artificial intelligence technology to pet health monitoring.
Presents machine-learning and hybrid deep-learning models for animal disease prediction using eight classifiers including Support Vector Machine, Random Forest, and hybrid variants (RF-CNN and RF-ANN) for early detection of animal health risks.
Validates a machine learning model designed to classify wellness visits for dogs and cats. Machine learning techniques employed to structure and derive insights from veterinary clinical data, facilitating automated extraction of information from clinical narratives.
Describes current state of AI in veterinary diagnostic imaging including machine learning applications for CT texture analysis, ultrasound radiomics, and automated image quality evaluation in canine thoracic radiographs.
This paper proposes a deep learning-based approach for the automated classification of canine skin diseases using the EfficientNetV2 architecture. The results prove that deep learning methods can be helpful in supporting veterinary diagnosis.
Satellai Collar Go features Petsense AI software that combines location tracking with motion, temperature, and sleep data analysis to create behavioral insights and detect potential diseases in dogs before symptoms appear.
Fi Series 3+ uses proprietary AI trained on thousands of dogs' data to detect barking, licking, scratching, eating, and drinking behaviors that can signal important health markers before issues become serious.
Overview of emerging veterinary technologies including AI-powered diagnostic systems for analyzing radiographs, ultrasounds, and CT scans with remarkable accuracy, helping veterinarians detect subtle abnormalities in imaging.
ACVIM position statement on AI in veterinary medicine covering ethical frameworks, performance metrics, and clinical applications of convolutional neural networks in diagnostic imaging including radiographs, CT, and MRI analysis.
The global veterinary AI diagnostics market size was estimated at USD 798.42 million in 2025 and is predicted to increase to approximately USD 3917.31 million by 2035. The market is growing due to increasing pet ownership, rising demand for early disease detection, and growing adoption of AI-powered imaging and decision-support tools across veterinary clinics.
Emerging diagnostic technologies, including Artificial Intelligence (AI)-enhanced imaging, liquid biopsies, molecular diagnostics can improve early detection capabilities in veterinary medicine. The integration of AI in veterinary imaging relies on sophisticated machine learning algorithms, particularly deep learning models like convolutional neural networks (CNNs).
Presents an FFT- and AI-enhanced Walk-over Weighing System (WoWS) for scalable herd-level health surveillance. Enables continuous monitoring, early detection of abnormal weight trends, and remote decision-making while supporting One Health principles.
Presents a multi-modal artificial intelligence framework for health status and welfare detection of dairy cows. Data from milking systems, internal sensing devices, and thermal cameras were jointly analyzed to enable comprehensive health monitoring and early disease detection.
PetPace V3.0 features AI-driven pain detection, epilepsy monitoring, and machine learning algorithms for continuous vital signs monitoring, representing a breakthrough in AI-powered pet health technology.
Details integration of artificial intelligence with complete blood morphology analysis in veterinary CBC machines. Features deep learning algorithms for cell image examination, with Ozelle's AI technology trained on over 40 million patient samples achieving 97%+ accuracy in cell classification matching expert pathologist performance.
Discusses AI-enhanced imaging technology, automated lab diagnostics, and predictive analytics in veterinary hospitals. Covers AI's role in faster diagnosis, treatment planning, and telemedicine platforms, emphasizing AI as decision-support tools rather than replacements for veterinary expertise.
The application of artificial intelligence (AI) in veterinary oncology is rapidly expanding, mirroring its advancements in human medicine. This scoping review was conducted to systematically map the literature on AI in veterinary oncology, identifying the clinical applications, techniques, and data sources being utilized.
A new elective course 'Artificial Intelligence and Digital Tools for Next-Generation Veterinarians' approved at Texas A&M College of Veterinary Medicine, scheduled to launch in Spring 2026, providing comprehensive AI training for veterinary students including scribe tools and diagnostic AI.
Just under half of surveyed veterinary professionals (47%) said they wanted to know more about adding veterinary AI tools to their practice in 2025. Interest extends beyond scribe technology to AI-powered workflow automation, diagnostic tools, and client education systems.
The global integration of artificial intelligence (AI) into veterinary medicine is advancing, yet its adoption in major markets like China remains uncharacterized. This study provides the first exploratory analysis of AI perception and adoption among veterinary professionals in China.
UC Davis is now working with the ScribbleVet digital scribe designed to complete veterinary SOAP notes during patient exams by recording appointments and streamlining medical record-keeping and documentation.
Examines AI technologies in animal agriculture including machine learning, computer vision, and IoT tools for early health issue identification, behavior tracking, and automated health evaluations in livestock management.
Reviews AI applications in dairy farming focusing on computer vision systems for animal identification, behavior monitoring, and large language models for data integration and decision-making in precision livestock farming.
Presents SM-GBoost-LSTM hybrid model combining SMOTE, Gradient Boosting, and LSTM networks for early disease detection in dairy cattle, achieving 93.56% accuracy in health monitoring using IoT smart collars.
PetPace unveils V3.0—the world's most advanced smart collar for dogs and cats with AI-driven pain detection, epilepsy monitoring, and 24/7 veterinary telehealth access using proprietary machine learning algorithms.
Review of digital pathology evolution in veterinary medicine, discussing digitization of clinical pathology specimens for diagnostic evaluation, teaching, and research, with focus on AI potential for image analysis of clinical pathology specimens.
Study demonstrating deep learning applications for cytological analysis in canine lymphoma diagnosis, part of growing research in AI-assisted pathology for veterinary oncology.
The use of machine learning in veterinary medicine has gained significant attention, particularly for early detection and classification of animal diseases. A DenseNet-121 CNN model was used for identifying and classifying Lumpy Skin Disease in cattle.
This paper proposes a multimodal artificial intelligence (AI) and large language model (LLM)-based diagnostic method for 6 common types of porcine gastrointestinal infectious diseases, using ChatGPT and image augmentation techniques along with CNN models for classification.
This article presents a comprehensive review of the manifold applications of AI within the domain of veterinary science, categorizing them into four domains: clinical practice, biomedical research, public health, and administration.
Evaluation of AI segmentation tool (VISTA) for enhancing accuracy and reducing time in canine radiograph segmentation. Study compares performance of novice, intermediate, and expert users when using AI-assisted versus manual segmentation methods.
AI in diagnostic imaging typically refers to machine learning algorithms trained to recognize patterns, detect anomalies, and assist in the interpretation of radiographs, ultrasounds, CT scans, and MRIs.
The American College of Veterinary Radiology (ACVR) and the European College of Veterinary Diagnostic Imaging (ECVDI) recognize the transformative potential of AI in veterinary diagnostic imaging and radiation oncology.
The application of artificial intelligence (AI) in veterinary oncology is rapidly expanding, mirroring its advancements in human medicine. The most mature applications involve image-based diagnostics, including digital pathology and radiomics.
Canine gait analysis using inertial sensors and deep learning for orthopedic and neurological disorders.
Characterising responses in group-housed pigs to Salmonella typhimurium infection through integrated computer vision-based behavioural monitoring and statistical analyses.
Mounting posture is an important visual indicator of estrus in dairy cattle. However, achieving reliable mounting pose estimation in real-world environments remains challenging due to cluttered backgrounds and frequent inter-animal occlusion. We present FSMC-Pose, a top-down framework that integrate
Depth estimation and 3D reconstruction have been extensively studied as core topics in computer vision. Starting from rigid objects with relatively simple geometric shapes, such as vehicles, the research has expanded to address general objects, including challenging deformable objects, such as human
Creating high-fidelity, animatable 3D dog avatars remains a formidable challenge in computer vision. Unlike human digital doubles, animal reconstruction faces a critical shortage of large-scale, annotated datasets for specialized applications. Furthermore, the immense morphological diversity across
Pet health wearables function by continuously collecting and analyzing biometric data using AI Algorithms to interpret the data, detecting patterns and deviations. Cloud Platform allows pet owners to access near-real-time dashboards and historical reports, and can share them with their vets. This creates continuous monitoring and tracking, empowering pet owners to take the best care of their pets and allowing vets to practice data-driven, proactive care.
Mars plans to expand its digital health portfolio throughout 2025 to offer tools that provide real time insights into overall wellbeing, all at the click of a button including GREENIES™ Canine Dental Check – the first AI-powered tool that helps pet parents monitor their dog's dental health with just a smartphone photo.
Companies such as PetPace have deepened their collaboration with veterinary clinics, deploying smart collars nationwide that monitor vital signs and behavior, enabling early detection of health issues and supporting clinical decision-making. The surge in AI-powered behavior analysis further distinguishes the U.S. market, with startups introducing devices capable of interpreting barking patterns and stress levels.
Machine learning in pathology shows promise for both human and veterinary medicine, yielding favorable results and in some cases surpassing the accuracy of human pathologists. The study addresses telepathology and digital pathology enhanced with AI as groundbreaking technology advancements offering automated diagnosis with high precision through computerized approaches.
Reviews AI applications in veterinary clinical pathology including Zoetis Diagnostics' Vetscan Imagyst, an AI deep learning-based tool for supporting veterinary practitioners in diagnostics of urine sediment preparations, blood smears, dermatologic samples, and fecal samples. Discusses the veterinary clinical pathologist's active role in defining intended use and qualification of AI methods.
Introduces AI terminology for veterinary pathologists and laboratory technologists, focusing on pre-clinical development and evaluation of AI-based decision support systems like neural networks. Presents overview of AI development stages for image-based tasks with emphasis on rigorous evaluation AI must undergo before clinical implementation.
Study developing deep learning models for classifying canine chronic kidney disease stages using renal ultrasound images. The research compared AI diagnostic performance with veterinary imaging specialists, representing one of few AI applications to veterinary ultrasonography.
Industry analysis noting roughly two dozen companies now market AI-powered software for veterinary practices. SignalPET's platform interprets 50,000+ X-ray films weekly, and a 2024 AAHA survey showed 30% of veterinarians already use some form of AI daily or weekly.
Explores AI applications in companion animal care including health monitoring, behavior analysis, parasite detection, and veterinary support systems using machine learning algorithms and computer vision.
Proposes comprehensive IoT-based model integrating machine learning algorithms for real-time animal health assessment, anomaly detection, and predictive analytics in digital farming environments.
Explores integration of AI within veterinary education as foundation for responsible clinical practice. Examines AI-driven tools including generative and multimodal language models, intelligent tutoring systems, and AI-based decision support applied to imaging, epidemiology, parasitology, and food safety.
Discusses Zoetis' Vetscan OptiCell™, combining innovative technology with AI-powered processing for automated blood count analysis. Examines how AI is making impact in hematology with advanced analyzers detecting blood cell abnormalities with unprecedented speed and precision.
In this retrospective diagnostic accuracy study, a commercially available convolutional neural network AI product (Vetology AI®) was assessed on 56 thoracic radiographic studies of pulmonary nodules and masses. The AI software detected pulmonary nodules/masses in 31 of 56 confirmed cases with accuracy of 69.3%, balanced accuracy 74.6%, sensitivity 55.4%, and specificity 93.75%.
The authors are optimistic about the AI's clinical utility, suggesting that 'broader use of AI could reliably increase diagnostic availability' in veterinary medicine, provided humans remain in the loop. As of March 2024, SignalRAY® services more than 2,300 clinics world-wide, with anecdotal reports of reaching 3,000 clinics.
The field of veterinary diagnostic imaging is undergoing significant transformation with the integration of artificial intelligence (AI) tools. The manuscript delves into various applications of AI across different imaging modalities, such as radiology, ultrasound, computed tomography, and magnetic resonance imaging.
The US FDA's Center for Veterinary Medicine (CVM) is advancing its leadership in veterinary science by integrating AI and machine learning (ML) into its regulatory framework and scientific initiatives. This includes developing AI/ML-driven tools for antimicrobial resistance research, genome editing safety, and postmarketing safety surveillance.
Monitoring fish growth behavior provides relevant information about fish health in aquaculture and home aquariums. Yet, monitoring fish sizes poses different challenges, as fish are small and subject to strong refractive distortions in aquarium environments. Image-based measurement offers a practica
Monocular 3D animal reconstruction is challenging due to complex articulation, self-occlusion, and fine-scale details such as fur. Existing methods often produce distorted geometry and inconsistent textures due to the lack of articulated 3D supervision and limited availability of back-view images in
4D reconstruction of equine family (e.g. horses) from monocular video is important for animal welfare. Previous mainstream 4D animal reconstruction methods require joint optimization of motion and appearance over a whole video, which is time-consuming and sensitive to incomplete observation. In this
Image processing-based automatic tooth segmentation and age estimation in sheep using deep learning.
Identification of gut microbiota features of diarrheic calves using the full-length 16S rRNA gene amplicon sequencing and machine learning.
Increased Space Allowance Improves Productivity and Welfare in Growing Pigs Assessed Using Artificial Intelligence-Based Monitoring of Agonistic Behavior.
Cross-Generational Validation of a Feedforward Neural Network for Milk Yield Prediction in Dairy Cattle.
Errors in transcription can create confusion, slow workflow, and potentially risk patient care. How do we define transcription accuracy in veterinary medicine?
Dog emotion recognition plays a crucial role in enhancing human-animal interactions, veterinary care, and the development of automated systems for monitoring canine well-being. However, accurately interpreting dog emotions is challenging due to the subjective nature of emotional assessments and the
Holstein-Friesian detection and re-identification (Re-ID) methods capture individuals well when targets are spatially separate. However, existing approaches, including YOLO-based species detection, break down when cows group closely together. This is particularly prevalent for species which have out
A challenge in marine bioacoustic analysis is the detection of animal signals, like calls, whistles and clicks, for behavioral studies. Manual labeling is too time-consuming to process sufficient data to get reasonable results. Thus, an automatic solution to overcome the time-consuming data analysis
Performance of an Artificial Intelligence Convolution Neural Network Software for the Detection of Confirmed Heart Failure in Dogs and Cats.
Deep learning cascade networks for segmentation of fluorine-18 sodium fluoride positron emission tomography scans of equine metacarpo- and metatarsophalangeal joints outperform atlas-based method.
From machine learning to digital twin integration for livestock production and research.
Assessing the Role of Large Language Models in Veterinary Dentistry Client Communication.
Histopathological diagnosis of Ovine Pulmonary Adenocarcinoma (OPA) based on ensemble model.
An automated vertebral heart scale measurement tool based on deep learning: Facilitating screening for prevention of canine cardiomegaly.
Uncovering biosecurity gaps: risk factors for PRRSV seropositivity in Costa Rican pig farms identified through machine learning.
Standardizing case definitions for hoof lesions and lameness: A scoping review to improve machine learning applications in dairy cattle.
Machine learning-based prediction and quantification of OCD surgery and pedigree effects on racehorse performance.
Multi-model large-scale AI framework for avian influenza surveillance and preparedness: Harnessing large language models to enhance risk communication, real-time decision support, and public health response strategies.
In this session: Anne Metzler, DVM, MS, Dipl. ACVO, describes techniques for examination of the retina and optic nerve with a goal of differentiating pathologic changes from normal variations. A brief overview of species-specific variation in retinal and optic nerve anatomy is also provided.
AI and predictive analytics are reshaping how animal health is approached. Findings shared at a 2024 symposium on artificial intelligence in veterinary medicine illustrate how AI is moving from research to practice, with diagnostic tools being integrated into radiology and diagnostics.
Accurate identification of cat breeds from images is a challenging task due to subtle differences in fur patterns, facial structure, and color. In this paper, we present a deep learning-based approach for classifying cat breeds using a subset of the Oxford-IIIT Pet Dataset, which contains high-resol
Precise identification of individual cows is a fundamental prerequisite for comprehensive digital management in smart livestock farming. While existing animal identification methods excel in controlled, single-camera settings, they face severe challenges regarding cross-camera generalization. When m
Evaluation of a Deep Active Learning Model for the Segmentation of Canine Thoracic Radiographs.
Automated detection of asymmetrical udders in dairy goats using a camera and deep-learning model YOLOv12.
Intelligent identification of medical and veterinary intracellular protozoa by using self-supervised learning.
Machine learning for detection of subclinical mastitis: A Bayesian approach incorporating diagnostic test properties.
This framework integrates multiple deep learning models to automatically compute metrics relevant to assessing animal well-being, including modules for markerless animal identification and health status assessment (locomotion score and body condition score) using AI-based vision adapted from industrial applications.
At present, AI is still an emerging technology in veterinary medicine and, as such, is raising increasing interest among in board-certified radiologists and general practitioners alike. Among other applications, AI is mainly used as a supportive tool to guide the interpretation of medical images in veterinary medicine.
Artificial intelligence (AI) is rapidly transforming veterinary diagnostic imaging, offering improved accuracy, speed, and efficiency in analyzing complex anatomical structures. AI-powered systems, including deep learning and convolutional neural networks, show promise in interpreting medical images from various modalities.
The US FDA's Center for Veterinary Medicine (CVM) is advancing its leadership in veterinary science by integrating AI and machine learning (ML) into its regulatory framework and scientific initiatives.
The field of veterinary medicine is expected to undergo a significant transformation due to artificial intelligence, with applications including development of a dog health score using an AI disease prediction algorithm based on multifaceted data and advancements in AI technology for improving animal welfare.
Artificial Intelligence (AI) is rapidly transforming veterinary science by offering innovative, data-driven solutions that enhance diagnosis, disease tracking, reproductive management, and research. By using machine learning (ML) and deep learning (DL), AI improves diagnostic accuracy, speeds up vaccine development, and advances research in antimicrobial resistance (AMR) and oncology.
Assessment of commercially available AI-based software for detecting common radiographic dental pathologies in dogs and cats, utilizing artificial neural networks, deep learning, and machine learning approaches for intraoral dental radiology applications.
Review examining AI applications in veterinary anatomical imaging including convolutional neural networks and deep learning for enhanced diagnostic accuracy, surgical planning, and personalized treatment strategies in animal healthcare.
Study comparing deep learning-based reconstruction (DLR) with conventional MRI methods for canine brain imaging, demonstrating DLR can reduce scan time by 50-75% while maintaining image quality through 12 healthy beagle dogs.
AI chatbots are often used as virtual assistants on clinic websites or client portals. Pet owners can get answers to common questions without speaking directly with a team member, gaining instant information on basic topics.
AI is helping veterinarians detect disease earlier, develop personalized treatments, and improve outcomes for pets and their families.