Žymantienė, Judita

Digital technologies that continuously quantify animal behavior, physiology, and production offer significant potential for the early identification of health and welfare disorders of dairy cows. In this study, a multimodal artificial intelligence (AI) framework is proposed for real-time health monitoring of dairy cows through the integration of physiological, behavioral, production, and thermal imaging data, targeting veterinarian-confirmed udder, leg, and hoof infections. Predictions are generated at the cow-day level by aggregating multimodal measurements collected during daily milking events. The dataset comprised 88 lactating cows, including veterinarian-confirmed udder, leg, and hoof infections grouped under a single ‘sick’ label. To prevent information leakage, model evaluation was performed using a cow-level data split, ensuring that data from the same animal did not appear in both training and testing sets. The system is designed to detect early deviations from normal health trajectories prior to the appearance of overt clinical symptoms. All measurements, with the exception of the intra-ruminal bolus sensor, were obtained non-invasively within a commercial dairy farm equipped with automated milking and monitoring infrastructure. A key novelty of this work is the simultaneous integration of data from three independent sources: an automated milking system, a thermal imaging camera, and an intra-ruminal bolus sensor. A hybrid deep learning architecture is introduced that combines the core components of established models, including U-Net, O-Net, and ResNet, to exploit their complementary strengths for the analysis of dairy cow health states. The proposed multimodal approach achieved an overall accuracy of 91.62% and an AUC of 0.94 and improved classification performance by up to 3% compared with single-modality models, demonstrating enhanced robustness and sensitivity to early-stage disease.

Mokomoji knyga skirta Veterinarinės medicinos programos studentams, studijuojantiems naminių gyvūnų virškinimo sistemos anatomiją, histologiją ir fiziologiją. Šia knyga taip pat gali naudotis Gyvūnų mokslo bei Gyvūnų ir žmogaus sąveikos programų studentai. Leidinyje išdėstoma naminių gyvūnų virškinimo sistemos anatomija, histologinė struktūra bei funkcijos. Knyga apima tris pagrindinius skyrius: trumpą bendrąją dalį, naminių žinduolių ir paukščių virškinimo sistemos ypatumus. Knygoje išsamiai aprašomi naminių gyvūnų virškinimo sistemos anatominiai ir histologiniai ypatumai, virškinimo organų funkcijos ir reguliacijos mechanizmai. Leidinys iliustruotas paveikslais, nuotraukomis, schemomis. Pateikiami veterinarinės anatomijos ir histologijos terminai lietuvių ir lotynų kalbomis.

Abstract- Contemporary technological solutions provide significant opportunities not only to optimize dairy production on farms, but also to monitor cows physiological parameters and the overall health status of the herd. One of the most advanced animal monitoring approaches is the application of thermography. This non-invasive method enables the detection of early changes in surface temperature, particularly for identifying inflammatory processes in the mammary gland and limbs. The integration of infrared thermography (IRT)technology into the milking parlor, together with the development of machine learning algorithms (MLA), could facilitate the monitoring and early detection of limb disorders and initial signs of mastitis in cows. Early identification of subclinical disease, before the onset of clinical symptoms such as lameness, would allow timely preventive interventions, thereby reducing treatment expenses and economic losses. Lameness is one of the most prevalent and economically significant health problems affecting dairy farms worldwide. It has been shown that 55% of lactations are associated with lameness-related health issues, while 15% are linked to mastitis or uterine infections. The aim of this study was to evaluate the effectiveness of IRT method in the diagnosis of bovine limb and udder diseases, with the goal of establishing a foundation for the development of MLA. For this study, a FLIR T640 thermal camera (FLIR Systems, USA) was used: Upon entering the milking parlor, thermographic images of the front and hind limbs and of the udder (with all teats visible) were captured (ambient temperature 15°C). Image analysis was performed using the Flir Tools software. The cows milk was tested by express diagnostic method before milking using the CMT (California Mastitis Test). During milking, milk samples were collected for the determination of lactose, fat, urea, protein concentrations, and somatic cell count. After milking, clinical examinations of all limbs were conducted to assess claw pathologies. Data analysis revealed that in the region of the articulationesinterphalangeaedistales, the surface temperature of clinically healthy front limbs was 18.06 +- 1.8 C whereas limbs with confirmed pathology exhibited a temperature of 27.31 +- 3.8 C - an increase of 9.25 C (p 1 < 0.001 ). In the hind limbs, the surface temperature of clinically healthy limbs was 19.58 = 2.62 C while limbs with pathology reached 29.77 +- 2.5 C - an increase of 10.19 C (p < 0.001). Analysis of teat surface temperature showed that healthy teats exhibited a temperature of 25.82 +- 2.43 C whereas showing signs of subclinical mastitis (confirmed by CMT) reached 30.42 +- 0.92 C an increase of 4.6 C (p < 0.001). Spearman's correlation analysis indicated that clinically confirmed signs of inflammation in the hind limbs were associated with increased teat temperatures left front (LF) (rs = 0.21, p<0.01), right front (RF) (rs = 0.22 p < 0.01), left rear (LR) (rs = 0.22, p < 0.01), and right rear (RR) (rs = 0.24 , p < 0.001). However, clinically confirmed signs of inflammation in the for climbs were not associated with the temperature of all four teats (p > 0.05) . Additionally, increased teat surface temperature was negatively associated with milk protein and urea content (rs = -0.18 to -0.28, p < 0.05 ), irrespective of temperature changes detected in the front and hind limbs. The results of this dataset for the development of machine learning algorithms capable of identifying associations between limb and udder diseases in dairy cows and to predict their impact on herd health.

Previous investigations have evaluated the impact of low-frequency oscillations on udder function, milk composition, and welfare of dairy cows during milking [1]. We hypothesised that the organism of the cow may respond to a low-frequency oscillation device as an external stressor. In cattle, cortisol produced under stress conditions has been associated with reduced reproductive performance, lowered milk production, and suppression of the immune system [2, 3]. Stress also influences milk composition, decreasing fat and protein content while increasing somatic cell count, which reflects poorer milk quality [4, 5]. The objective of this study was to investigate the impact of low-frequency oscillations on cows’ stress level and milk composition. In the first trial, healthy cows were assigned into two groups of 20 cows using the principle of analogy. In the experimental group, low-frequency oscillations were applied to the udder during morning milking [1]. Blood samples were collected from the tail vein right after morning milking to determine cortisol concentration (ELISA). In the second trial, cows were divided into two groups of 10 cows and observed for two weeks. In the experimental group, conventional milking was carried out during the first week, while in the second week, udder stimulation with low-frequency oscillations was applied during each milking. The control group underwent conventional milking throughout both weeks. Daily milk yield was recorded, and at the end of each week, milk samples were collected to determine fat, protein, lactose, and urea content, as well as somatic cell count (SCC). For statistical evaluation, t test analysis was used to compare cortisol, milk yield, and milk quality parameters. In the first trial, the cortisol concentration in the blood of cows in the experimental group was 2.81 ng/mL lower (P = 0.2102) than in the control group, indicating that low-frequency oscillations did not induce stress during milking. In the second trial, application of low-frequency oscillations in the experimental group during the second week resulted in an average daily increase of 0.99l of milk per cow (P = 0.1475) compared with the first week, when no oscillations were applied. In the control group, the increase between weeks was only 0.26 L of milk per cow (P = 0.9245). These differences were not statistically significant. Analysis of milk quality parameters showed that in the experimental group, the milk fat content was 0.58% higher in the second week compared to the first week (P = 0.038). Other milk quality indicators (protein, lactose, urea, SCC) did not differ significantly between weeks in either group. In conclusion, low-frequency oscillations applied to cows during milking did not induce stress. Moreover, they tended to increase milk yield and improve milk quality indicators.

ABSTRACT Changes in body temperature provide significant information in animal-based biomedical research and veterinary practice. For this reason, training exercises (TE) in the use of infrared thermography (IRT) have been included in the Animal Physiology subject of the Veterinary Medicine study programme. IRT is an increasingly used method for monitoring thermal changes in farm and laboratory animals as it allows non-contact assessment of body surface temperature variations with multiple research applications (Ghezzi et al., 2024). Thermography can reveal physiological changes before they manifest as clinical signs, allowing early detection and therapeutic intervention (Schaefer and Cook, 2013). Two different IRT cameras are used in student training exercises: Testo 875-1 (Testo, Germany) and FLIR P640 (FLIR System Inc., USA) with its thermovision software. Students also have access to a database of thermal images on laboratory computers. They learn how to analyse thermal images, measure the surface temperature of different parts of the body, find the hottest and coldest points, and visualise temperature changes using histograms. TE provide the opportunity to evaluate thermal images of the limbs of horses and cattle, the udders of cows, as well as images of guinea pigs, rabbits, mice and rats. Furthermore, students explore thermal images with early signs of inflammation, which exhibit temperature differences in a symmetrical comparison. Also there is an opportunity to apply the acquired knowledge by using IRT in the research of students' Master's theses. In the last 5 years, 4 theses have been completed and defended in the department. Finally, integrating the use of IRT into TE has broadened students' knowledge of thermoregulation and surface blood flow. Moreover, it has provided practical experience in analyzing the surface body temperature in different animals, identifying heat dissipation windows, detecting potential circulatory disorders, and recognizing early signs of inflammation that may not be obvious by routine examination.

The application of vibration therapy of blood flow improvement in the medical field has been explored intensively during recent decades. However, compelling evidence about the health effects of vibration (especially treatment effectiveness) is still unclear. The treatment capabilities of the low power acoustic pulse therapy (APT) have been widely reported. It is known to produce various responses in biological tissues [1, 2]. APT pressure (10 ± 15 megapascal) has been shown to produce new blood vessels and improve tissue function with long term exposure [1]. In our previous investigation [3], an unbalanced vibratory motor was applied to the DeLaval Harmony model milking unit. During in vivo experiments, while milking, the vibrator induced mechanical milking-similar vibrations in the udder. The vibrations were spreading to the entire udder and caused physiotherapeutic effects such as activated physiological processes and increased udder base temperature by 0.57 , thus increasing the blood flow in the udder. The application of low-frequency vibrations did not alter observable changes in milk yield and quality parameters oranimal welfare indicators. Moreover, casein micelle size and milk fat globules can vary depending on farming factors (seasonal variation, stage of lactation), and cow genetics [4]. Here, we aimed to estimate the effect of vibration on casein micelle size in raw milk under in vitro conditions. Casein micelle size analysis was performed using Beckman Coulter - Delsa™Nano Series analyzer. Raw milk samples were exposed to the 25-Hz vertical and 41-Hz horizontal vibrations for 15 s (A sample), 1 min (B sample), 2 min (C sample) and 7 min (D sample). K sample (no vibration) served as control. Milk measurement temperature was 24.5–25.00°C, refractive index was 1.3328, viscosity was 0.8980 (cP), scattering intensity was 30617 (cps), and attenuator was 0.3 (%). The average size of casein micelle size in raw milk distributed as follows: 646.1 nm, 642.3 nm, 640.5 nm, 621.5 and 617.6 nm in K, A, B, C, and D samples, respectively. To sum up, we can state that vibration had no significant influence on casein micelle size in raw milk.

Presently, a key component of animal welfare is the animal’s affective (emotional) state and its assessment. Such studies attract great scientific interest focused primarily on negative experiences such as pain, fear, and suffering, which farm animals experience at different stages of their lives. Increased numbers of studies highlight that cows exhibit specific pain behaviours and facial expression as a new and reliable technique which could be developed to recognize and assess pain. Pain in farm animals can be caused by disease, injuries, poor hygiene and housing or inadequate management practice. However, disease (such as mastitis, lameness, peritonitis, etc.) is a major cause of pain in dairy cows, negatively affects welfare, and decreases productivity; therefore, analysis of facial expression can be a valuable early pain detection tool [1–4]. Thus, we aimed to determine parameters of dairy cows (that were affected with subclinical or clinical mastitis) on a facial expresion scale. A total of 30 cows were allocated into equal (N = 10) three groups: 1 (control, healthy cows), 2 (subclinical mastitis) and 3 (clinical mastitis); and photo images (N = 150) based on facial expressions were evaluated. Pain assessment relied on the evaluation of potential pain-related facial expression performances in four regions of the face (each region was scored on a 0–2 scale). Eye and ear position, nostril and facial expression were measured as described in scientific literature [1, 3]. The condition of the changed by 50% (P = 0.07) and 37.50% (P = 0.01), the ear by 42.85% (P = 0.06) and 42.85% (P = 0.04), the nostril by 62.50% (P = 0.18) and 50.00% (P = 0.05), and the facial expression by 33.33% (P = 0.01) and 22.22% (P = 0.001) in groups 2 and 3 of cows, respectively, compared with the group 1. Early detection (changes in a cow’s normal facial expression suggest the presence of pain) of any health problem will ensure that cows can get proper health care as soon as possible, reducing the impact on welfare, productivity and dairy farm economy. We extend our study by developing an automated system (utilizing the power of artificial intelligence) for the detection and analysis of facial expressions.

The invention belongs to the field of agriculture, specifically, to veterinary medicine. The system is intended for the excitation of mechanical vibrations in the udders of cows, through the teats, thereby activating the blood flow, which prevents the inflammatory processes occurring in the udder - cow mastitis. The system comprises at least one teat cup on which a vibration stimulating actuator is rigidly mounted on the body, by means of a holder ring, which is connected to a controller, controlled through a vacuum delivery to teat cup transducer. The system preferably comprises four individual vibrostimulation elements, each mounted on four individual teat cups. All vibrostimulation actuators are connected to a single controller, controlled via the vacuum delivery to teat cup transducer.

Brown adipose tissue (BAT) has received renewed interest as a potential treatment target for obesity and comorbidities due to its thermogenic activity capacity and contribution to energy expenditure. Murine models are among the commonest preclinical models for studying human disease, including BAT studies. C57BL/6 and BALB/c are the two most commonly used mouse strains, however, different strains manifest significant behavioural differences, levels of sociability, emotionality, exercise response, respond differently to severe spinal cord injury, show differences in susceptibility to dietinduced obesity and insulin resistance, etc. To gain a broader understanding of the peculiarities, this study aimed to investigate the effect of age, strain and gender on interscapular BAT temperature changes and to analyse some blood biochemical and behavioural parameters in the aforementioned strains. The age of the mice (5–8 weeks) did not influence the interscapular BAT area temperature. The mean temperatures of the maximum (Tmax) and the average temperatures (Tisoth) in the BALB/c mice were by 0.46 °C (P<0.001) and by 0.37 °C (P<0.001) higher than in the C57BL/6 mice. In addition, the gender of the mice also modulated the BAT area temperature, causing an increment of 0.29 °C (P<0.001) and 0.21 °C (P<0.05) in Tmax and Tisoth temperatures of males, respectively. The difference in mean glucose, cholesterol and triglyceride levels between the BALB/c and C57BL/6 strains was not substantial. Behavioural analyses disclosed a statistically insignificant distribution of grooming activities in male BALB/c and C57BL/6 mice and significant (P<0.001) differences in female mice. Collectively, our findings revealed that infrared thermography can be successfully used to measure interscapular BAT temperature in mice in vivo, and that mouse strain and gender can alter BAT measurements.

The invention belongs to the field of agriculture, specifically, to veterinary medicine. The system is intended for the excitation of mechanical vibrations in the udders of cows, through the teats, thereby activating the blood flow, which prevents the inflammatory processes occurring in the udder - cow mastitis. The system comprises at least one teat cup on which a vibration stimulating actuator is rigidly mounted on the body, by means of a holder ring, which is connected to a controller, controlled through a vacuum delivery to teat cup transducer. The system preferably comprises four individual vibrostimulation elements, each mounted on four individual teat cups. All vibrostimulation actuators are connected to a single controller, controlled via the vacuum delivery to teat cup transducer.