An intensity-based self-supervised domain adaptation method for intervertebral disc segmentation in magnetic resonance imaging.

BACKGROUND AND OBJECTIVE: Accurate IVD segmentation is crucial for diagnosing and treating spinal conditions. Traditional deep learning methods depend on extensive, annotated datasets, which are hard to acquire. This research proposes an intensity-based self-supervised domain adaptation, using unlabeled multi-domain data to reduce reliance on large annotated datasets. METHODS: The study introduces an innovative method using intensity-based self-supervised learning for IVD segmentation in MRI scans. This approach is particularly suited for IVD segmentations due to its ability to effectively capture the subtle intensity variations that are characteristic of spinal structures. The model, a dual-task system, simultaneously segments IVDs and predicts intensity transformations. This intensity-focused method has the advantages of being easy to train and computationally light, making it highly practical in diverse clinical settings. Trained on unlabeled data from multiple domains, the model learns domain-invariant features, adeptly handling intensity variations across different MRI devices and protocols. RESULTS: Testing on three public datasets showed that this model outperforms baseline models trained on single-domain data. It handles domain shifts and achieves higher accuracy in IVD segmentation. CONCLUSIONS: This study demonstrates the potential of intensity-based self-supervised domain adaptation for IVD segmentation. It suggests new directions for research in enhancing generalizability across datasets with domain shifts, which can be applied to other medical imaging fields.

Salmonellosis in adult cattle in Central Argentina: case series.

Salmonellosis is an infectious disease caused by bacteria belonging to the Salmonella genus. Bovine salmonellosis is more frequent in young cattle under intensive overcrowd husbandry conditions, and therefore uncommon in adults. We report four outbreaks of clinical salmonellosis due to Salmonella Typhimurium, Salmonella Newport and Salmonella Dublin provoking outbreaks of diarrheic/septicemic disease in adult cattle of Central Argentina. Anamnesis information, clinical, pathological, and bacteriological findings were retrospective analyzed. This report emphasizes the importance to include salmonellosis among the differential diagnosis of clinical enteric/septicemic disease in adult cattle under different husbandry conditions in Argentina. The source of Salmonella could not be established in these outbreaks.

FetalBrainAwareNet: Bridging GANs with anatomical insight for fetal ultrasound brain plane synthesis.

Over the past decade, deep-learning (DL) algorithms have become a promising tool to aid clinicians in identifying fetal head standard planes (FHSPs) during ultrasound (US) examination. However, the adoption of these algorithms in clinical settings is still hindered by the lack of large annotated datasets. To overcome this barrier, we introduce FetalBrainAwareNet, an innovative framework designed to synthesize anatomically accurate images of FHSPs. FetalBrainAwareNet introduces a cutting-edge approach that utilizes class activation maps as a prior in its conditional adversarial training process. This approach fosters the presence of the specific anatomical landmarks in the synthesized images. Additionally, we investigate specialized regularization terms within the adversarial training loss function to control the morphology of the fetal skull and foster the differentiation between the standard planes, ensuring that the synthetic images faithfully represent real US scans in both structure and overall appearance. The versatility of our FetalBrainAwareNet framework is highlighted by its ability to generate high-quality images of three predominant FHSPs using a singular, integrated framework. Quantitative (Fréchet inception distance of 88.52) and qualitative (t-SNE) results suggest that our framework generates US images with greater variability compared to state-of-the-art methods. By using the synthetic images generated with our framework, we increase the accuracy of FHSP classifiers by 3.2% compared to training the same classifiers solely with real acquisitions. These achievements suggest that using our synthetic images to increase the training set could provide benefits to enhance the performance of DL algorithms for FHSPs classification that could be integrated in real clinical scenarios.

On the use of contrastive learning for standard-plane classification in fetal ultrasound imaging.

BACKGROUND: To investigate the effectiveness of contrastive learning, in particular SimClr, in reducing the need for large annotated ultrasound (US) image datasets for fetal standard plane identification. METHODS: We explore SimClr advantage in the cases of both low and high inter-class variability, considering at the same time how classification performance varies according to different amounts of labels used. This evaluation is performed by exploiting contrastive learning through different training strategies. We apply both quantitative and qualitative analyses, using standard metrics (F1-score, sensitivity, and precision), Class Activation Mapping (CAM), and t-Distributed Stochastic Neighbor Embedding (t-SNE). RESULTS: When dealing with high inter-class variability classification tasks, contrastive learning does not bring a significant advantage; whereas it results to be relevant for low inter-class variability classification, specifically when initialized with ImageNet weights. CONCLUSIONS: Contrastive learning approaches are typically used when a large number of unlabeled data is available, which is not representative of US datasets. We proved that SimClr either as pre-training with backbone initialized via ImageNet weights or used in an end-to-end dual-task may impact positively the performance over standard transfer learning approaches, under a scenario in which the dataset is small and characterized by low inter-class variability.

Generalizability and robustness evaluation of attribute-based zero-shot learning.

In the field of deep learning, large quantities of data are typically required to effectively train models. This challenge has given rise to techniques like zero-shot learning (ZSL), which trains models on a set of "seen" classes and evaluates them on a set of "unseen" classes. Although ZSL has shown considerable potential, particularly with the employment of generative methods, its generalizability to real-world scenarios remains uncertain. The hypothesis of this work is that the performance of ZSL models is systematically influenced by the chosen "splits"; in particular, the statistical properties of the classes and attributes used in training. In this paper, we test this hypothesis by introducing the concepts of generalizability and robustness in attribute-based ZSL and carry out a variety of experiments to stress-test ZSL models against different splits. Our aim is to lay the groundwork for future research on ZSL models' generalizability, robustness, and practical applications. We evaluate the accuracy of state-of-the-art models on benchmark datasets and identify consistent trends in generalizability and robustness. We analyze how these properties vary based on the dataset type, differentiating between coarse- and fine-grained datasets, and our findings indicate significant room for improvement in both generalizability and robustness. Furthermore, our results demonstrate the effectiveness of dimensionality reduction techniques in improving the performance of state-of-the-art models in fine-grained datasets.

[Antithrombotic therapy after surgical mitral valve repair: review of the evidence and updated proposals]. / La terapia antitrombotica dopo chirurgia riparativa della valvola mitrale: revisione delle evidenze e suggerimenti aggiornati.

Surgical mitral valve repair (SMVR) is performed with various techniques that involve the implantation of non-biological material, such as the prolene of the suture threads, the polytetrafluoroethylene of the neo-chordae or the prosthetic ring for the remodeling of the valve annulus, whose exposure to the bloodstream is capable of triggering the blood coagulation cascade and consequently the development of thrombotic/thromboembolic events. The indications of the literature on the use of antithrombotic drugs after SMVR are weak and not univocal given the absence of randomized data and the availability of only small observational case series, which are generally contaminated by the lack of homogeneity of the populations examined. Indeed in these studies, patients not only undergoing SMVR, but also transcatheter repair of the mitral valve or surgical implantation of a biological valve prosthesis (not only in the mitral position) are included. In addition, the indication for antithrombotic therapy, and in particular anticoagulation, is often conditioned by the concomitant presence of atrial fibrillation that either preexists or develops postoperatively. In this review, the current evidence regarding antithrombotic therapy in patients undergoing SMVR, both in the presence or absence of atrial fibrillation, is summarized and updated treatment algorithms are proposed.

Infectious sporadic bovine abortions: retrospective analysis.

Infectious sporadic abortions in cattle are mainly caused by opportunistic bacteria and fungi usually present in environmental or gastrointestinal and reproductive microbiota of healthy animals. A retrospective analysis was carried out to evaluate the main opportunistic microorganisms involved in bovine abortions recorded at INTA Balcarce (Argentina) from 1997 to 2023, accounting for 2.2% of the total diagnosed etiologies of bovine abortion. The opportunistic agents identified as the cause of abortion in 29 fetuses were bacteria (90%) and fungi (10%). Escherichia coli (n = 8), Trueperella pyogenes (n = 5), and Histophilus somni (n = 4) were the bacterial species most often identified as causing infectious abortions, whereas Aspergillus spp. (n = 3) was implicated in all fungal abortions identified. Pure culture of bacteria or fungus was achieved from abomasal content and/or lung essential. Main microscopic findings were bronchopneumonia, myo- and epicarditis, meningitis, and portal hepatitis. Herein, we highlight the importance of detecting potential infectious bacteria in cultures to improve etiological diagnosis of bovine abortions associated with compatible microscopic findings to confirm the etiology.

Classifying Vocal Folds Fixation from Endoscopic Videos with Machine Learning.

Vocal folds motility evaluation is paramount in both the assessment of functional deficits and in the accurate staging of neoplastic disease of the glottis. Diagnostic endoscopy, and in particular videoendoscopy, is nowadays the method through which the motility is estimated. The clinical diagnosis, however, relies on the examination of the videoendoscopic frames, which is a subjective and professional-dependent task. Hence, a more rigorous, objective, reliable, and repeatable method is needed. To support clinicians, this paper proposes a machine learning (ML) approach for vocal cords motility classification. From the endoscopic videos of 186 patients with both vocal cords preserved motility and fixation, a dataset of 558 images relative to the two classes was extracted. Successively, a number of features was retrieved from the images and used to train and test four well-grounded ML classifiers. From test results, the best performance was achieved using XGBoost, with precision = 0.82, recall = 0.82, F1 score = 0.82, and accuracy = 0.82. After comparing the most relevant ML models, we believe that this approach could provide precise and reliable support to clinical evaluation.Clinical Relevance- This research represents an important advancement in the state-of-the-art of computer-assisted otolaryngology, to develop an effective tool for motility assessment in the clinical practice.

Exploiting class activation mappings as prior to generate fetal brain ultrasound images with GANs.

The identification of fetal-head standard planes (FHSPs) from ultrasound (US) images is of fundamental importance to visualize cerebral structures and diagnose neural anomalies during gestation in a standardized way. To support the activity of healthcare operators, deep-learning algorithms have been proposed to classify these planes. To date, the translation of such algorithms in clinical practice is hampered by several factors, including the lack of large annotated datasets to train robust and generalizable algorithms. This paper proposes an approach to generate synthetic FHSP images with conditional generative adversarial network (cGAN), using class activation maps (CAMs) obtained from FHSP classification algorithms as cGAN conditional prior. Using the largest publicly available FHSP dataset, we generated realistic images of the three common FHSPs: trans-cerebellum, trans-thalamic and trans-ventricular. The evaluation through t-SNE shows the potential of the proposed approach to attenuate the problem of limited availability of annotated FHSP images.

Evaluating Prophylactic Effect of Bovine Colostrum on Intestinal Barrier Function in Zonulin Transgenic Mice: A Transcriptomic Study.

The intestinal barrier comprises a single layer of epithelial cells tightly joined to form a physical barrier. Disruption or compromise of the intestinal barrier can lead to the inadvertent activation of immune cells, potentially causing an increased risk of chronic inflammation in various tissues. Recent research has suggested that specific dietary components may influence the function of the intestinal barrier, potentially offering a means to prevent or mitigate inflammatory disorders. However, the precise mechanism underlying these effects remains unclear. Bovine colostrum (BC), the first milk from cows after calving, is a natural source of nutrients with immunomodulatory, anti-inflammatory, and gut-barrier fortifying properties. This novel study sought to investigate the transcriptome in BC-treated Zonulin transgenic mice (Ztm), characterized by dysbiotic microbiota, intestinal hyperpermeability, and mild hyperactivity, applying RNA sequencing. Seventy-five tissue samples from the duodenum, colon, and brain of Ztm and wild-type (WT) mice were dissected, processed, and RNA sequenced. The expression profiles were analyzed and integrated to identify differentially expressed genes (DEGs) and differentially expressed transcripts (DETs). These were then further examined using bioinformatics tools. RNA-seq analysis identified 1298 DEGs and 20,952 DETs in the paired (Ztm treatment vs. Ztm control) and reference (WT controls) groups. Of these, 733 DEGs and 10,476 DETs were upregulated, while 565 DEGs and 6097 DETs were downregulated. BC-treated Ztm female mice showed significant upregulation of cingulin (Cgn) and claudin 12 (Cldn12) duodenum and protein interactions, as well as molecular pathways and interactions pertaining to tight junctions, while BC-treated Ztm males displayed an upregulation of transcripts like occludin (Ocln) and Rho/Rac guanine nucleotide exchange factor 2 (Arhgf2) and cellular structures and interfaces, protein-protein interactions, and organization and response mechanisms. This comprehensive analysis reveals the influence of BC treatment on tight junctions (TJs) and Nuclear factor kappa-light-chain-enhancer of activated B cells (NF-kB) signaling pathway gene expressions. The present study is the first to analyze intestinal and brain samples from BC-treated Ztm mice applying high-throughput RNA sequencing. This study revealed molecular interaction in intestinal barrier function and identified hub genes and their functional pathways and biological processes in response to BC treatment in Ztm mice. Further research is needed to validate these findings and explore their implications for dietary interventions aimed at improving intestinal barrier integrity and function. The MGH Institutional Animal Care and Use Committee authorized the animal study (2013N000013).

Do Organochlorine Contaminants Modulate the Parasitic Infection Degree in Mediterranean Trout (Salmo trutta)?

We investigated the occurrence of organochlorine pollutants (OCs) in the muscle of brown trout and evaluated their potential modulation of parasite infection. The toxicological risk for consumer health was assessed, too. Trout were collected from the Sila National Park (Calabria region, South of Italy). The highest concentrations emerged for the sum of the 6 non-dioxin-like (ndl) indicator polychlorinated biphenyls (Σ6ndl-PCBs), followed by the 1,1,1-trichloro-2,2-di(4-chlorophenyl)-ethane (DDT), dioxin-like PCBs, hexachlorobenzene (HCB), and dieldrin. Measured on lipid weight (LW), the mean value of Σ6ndl-PCBs amounted to 201.9 ng g-1, that of ΣDDTs (the sum of DDT-related compounds) to 100.2 ng g-1, with the major contribution of the DDT-metabolite p,p'-DDE which was detected in all sample units (97.6 ng g-1 on average). Among dioxin-like congeners, PCB 118 showed the highest mean concentration (21.96 ng g-1 LW) and was detected in all sample units. Regression analysis of intestinal parasites on OC concentration was performed, controlling for two potential confounding factors, namely sex and sexual stage. The results evidenced the existence of interactions between the dual stressors in the host-parasite system in the wild. A negative and statistically significant correlation was estimated, suggesting that OCs may decrease parasite infection degree. Regarding the toxicological risk evaluation, OC concentrations were consistently below the current European Maximum Residue Limits.

A review on deep-learning algorithms for fetal ultrasound-image analysis.

Deep-learning (DL) algorithms are becoming the standard for processing ultrasound (US) fetal images. A number of survey papers in the field is today available, but most of them are focusing on a broader area of medical-image analysis or not covering all fetal US DL applications. This paper surveys the most recent work in the field, with a total of 153 research papers published after 2017. Papers are analyzed and commented from both the methodology and the application perspective. We categorized the papers into (i) fetal standard-plane detection, (ii) anatomical structure analysis and (iii) biometry parameter estimation. For each category, main limitations and open issues are presented. Summary tables are included to facilitate the comparison among the different approaches. In addition, emerging applications are also outlined. Publicly-available datasets and performance metrics commonly used to assess algorithm performance are summarized, too. This paper ends with a critical summary of the current state of the art on DL algorithms for fetal US image analysis and a discussion on current challenges that have to be tackled by researchers working in the field to translate the research methodology into actual clinical practice.

Human coagulation factor X and CD5 antigen-like are potential new members of the zonulin family proteins.

Zonulin is a physiologic epithelial and endothelial permeability modulator. Zonulin increases antigen trafficking from the gut lumen into the bloodstream and in between body compartments, a mechanism linked to many chronic inflammatory diseases. Upon its initial discovery, it was noted that zonulin was not a single protein, but rather a family of structurally and functionally related proteins referred to as the zonulin family proteins (ZFPs). ZFPs are members of the mannose associated serine proteases (MASP) family and are the result of high mutation rates leading to many zonulin polymorphisms. Pre-haptoglobin 2, the precursor of haptoglobin 2, was identified as the first eukaryotic member of the ZFPs, and properdin, a key positive regulator of the alternative pathway, as a second member. In this study, we report two additional proteins that are likely ZFPs. Human coagulation factor X (FX) and CD5 antigen-like (CD5L). Both FX and CD5L recombinant proteins were detected by anti-zonulin antibody in Western immunoblot analysis, and both proteins decreased epithelial barrier competency of Caco-2 cell monolayers as established by the Trans Epithelial Electrical Resistance (TEER) assay. These results indicate that FX and CD5L have structural and functional similarities with previously identified ZFPs and, therefore, can be considered new members of this family of proteins.

Clinical-pathological findings induced by Histophilus somni isolated in subacute cardiac death in feedlot cattle.

The purpose of this report is to provide information about the different presentations of cardiac and extra-cardiac histophilosis and, to assess the antimicrobial (ATM) susceptibility of Histophilus somni isolated from these cardiac lesions to different ATM agents commonly used for treating bovine bacterial respiratory pathogens. Eight feedlot calves, which died after suffering from food rejection, apathy, hyperthermia, cough and nasal mucous discharge, and lack of response to ATM therapy, were studied. Cardiac lesions observed at necropsy included valvular/mural endocarditis, myocardial infarction, and necrotizing myocarditis, miliar non-suppurative myocarditis, myocardic necrotic sequestrum, and/or pericarditis. Histopathological, bacteriological and molecular studies confirmed the presence of a fastidious microorganism in the affected organs. H. somni showed no resistance to most ATM tested (ceftiofur, gamithromycin, enrofloxacin, florfenicol, tilmicosin). The results obtained in this study confirmed that H. somni was the main cause of the subacute cardiac lesions associated with hyperthermia, apathy and respiratory signs observed in cattle examined in this research. These presentations must be considered by veterinary practitioners in order to establish a rational therapeutic.

Mycoplasma bovis-pneumonia and polyarthritis in feedlot calves in Argentina: First local isolation / Neumonía y poliartritis por Mycoplasma bovis en terneros de feedlot: primeraislamiento local

Abstract Bovine respiratory disease (BRD) is one of the most frequent clinical concerns inweaned calves after their arrival at the feedlot. This work reports the first local isolation ofMycoplasma bovis from feedlot calves with pneumonia and polyarthritis in Argentina. Twentyfour out of 545 calves showed progressive, subacute to chronic respiratory distress, coughing,and fever. Thirty percent of the affected calves also showed lameness and swelling of elbowor carpal, and knee or tarsal joints. Five necropsies were performed and severe multifocal tocoalescent pulmonary nodules, containing white-yellowish caseous exudate encircled by fibroustissue, and fibrinonecrotic arthritis and tenosynovitis were detected. Mycoplasma was isolatedfrom lung and joint samples. The 16S-23S rRNA ITS consensus sequence obtained from theseisolates showed 100% similarity with the same region of M. bovis strains. Since there are no com-mercially available vaccines in the region for the prevention and control of M. bovis pneumoniaand arthritis, surveillance is a priority to reduce the source of disease to naïve animals.

Resumen La enfermedad respiratoria bovina es uno de los problemas sanitarios más fre-cuentes en terneros recién destetados luego de su arribo a los corrales de encierre (feedlots).Este trabajo describe el primer aislamiento local de Mycoplasma bovis de terneros de feedlotcon neumonía y poliartritis en Argentina. Se vieron afectados 24 de 545 terneros; mostraron enfermedad respiratoria progresiva, subaguda a crónica, tos y fiebre. De los terneros afecta-dos, el 30% presentó, además, problemas en articulaciones carpales o tarsales. Se realizaron5 necropsias de terneros afectados y se observaron nódulos pulmonares multifocales a coa-lescentes, que contenían un exudado caseoso blanco-amarillento, rodeados de tejido fibroso,artritis y tenosinovitis fibrinonecrótica. Se aisló Mycoplasma de muestras de pulmón y artic-ulación. La secuencia consenso del gen codificante del ARNr 16S-23S rRNA obtenido de estosaislamientos mostró un 100% de similitud con la misma región de cepas de M. bovis. Teniendoen cuenta que no hay vacunas disponibles comercialmente en la región para la prevencióny el control de neumonías y poliartritis por M. bovis, es importante realizar una vigilanciaepidemiológica a fin de reducir las fuentes de infección para animales susceptibles.

A deep learning approach to median nerve evaluation in ultrasound images of carpal tunnel inlet.

Ultrasound (US) imaging is recognized as a useful support for Carpal Tunnel Syndrome (CTS) assessment through the evaluation of median nerve morphology. However, US is still far to be systematically adopted to evaluate this common entrapment neuropathy, due to US intrinsic challenges, such as its operator dependency and the lack of standard protocols. To support sonographers, the present study proposes a fully-automatic deep learning approach to median nerve segmentation from US images. We collected and annotated a dataset of 246 images acquired in clinical practice involving 103 rheumatic patients, regardless of anatomical variants (bifid nerve, closed vessels). We developed a Mask R-CNN with two additional transposed layers at segmentation head to accurately segment the median nerve directly on transverse US images. We calculated the cross-sectional area (CSA) of the predicted median nerve. Proposed model achieved good performances both in median nerve detection and segmentation: Precision (Prec), Recall (Rec), Mean Average Precision (mAP) and Dice Similarity Coefficient (DSC) values are 0.916 ± 0.245, 0.938 ± 0.233, 0.936 ± 0.235 and 0.868 ± 0.201, respectively. The CSA values measured on true positive predictions were comparable with the sonographer manual measurements with a mean absolute error (MAE) of 0.918 mm2. Experimental results showed the potential of proposed model, which identified and segmented the median nerve section in normal anatomy images, while still struggling when dealing with infrequent anatomical variants. Future research will expand the dataset including a wider spectrum of normal anatomy and pathology to support sonographers in daily practice.

A review of cardiac blackleg in cattle, and report of 2 cases without skeletal muscle involvement in Argentina.

Blackleg is an infectious disease caused by Clostridium chauvoei. Cardiac blackleg has been reported in ruminants as an uncommon presentation of the disease; its pathogenesis is not understood completely. We include here a literature review of cardiac blackleg and a description of 2 cases in 12-15-mo-old feedlot steers in Argentina. Fourteen of 1,190 steers died suddenly over a period of 10 d. Postmortem examinations were performed on 5 of these animals. Grossly, severe, diffuse, fibrinous pericarditis and pleuritis, multifocal necrohemorrhagic myocarditis, diffuse pulmonary congestion, mild splenomegaly, and moderate congestion of meningeal vessels were observed. No significant gross lesions were observed in the skeletal muscles of any animal. Histology was performed on 2 of the steers. The main microscopic features were necrotizing myocarditis with myriad intralesional gram-positive rods with subterminal spores plus fibrinosuppurative pericarditis and pleuritis. C. chauvoei was detected by immunohistochemistry and PCR in the myocardium of both animals. These findings confirm a diagnosis of cardiac blackleg in these 2 steers and presumptively in the other affected animals.

Spatial-temporal trends and economic losses associated with bovine abortifacients in central Argentina.

The aims of this work are, firstly, to provide the geolocalization of cases of bovine abortion with definitive diagnosis and, secondly, to estimate the economic losses due to the most frequent abortifacients diagnosed agents in cattle in Buenos Aires province, Argentina. The total beef and dairy cattle population at risk of abortion is 8,358,186 and 538,076, respectively. In beef cattle, the overall risk of abortion was estimated at 4.5% for all pregnancies, where 27.9% are due to Campylobacter fetus, Neospora caninum, Leptospira spp., Brucella abortus, and bovine viral diarrhea virus with economic losses of US$ 440 per abortion, being the annual loss to the beef industry of US$ 50,144,101. In dairy cattle, there was an 8.0% risk of suffering abortion, 26.1% produced by the same abortigenic agents. The economic losses were estimated at US$ 1,415 per abortion, which equals a total loss of US$ 17,298,498 for the dairy industry in the region. The results of this study show that infectious causes are highly prevalent in Buenos Aires province, and they caused severe economic impacts in the dairy and beef industries. Furthermore, changes in temporal trends of infectious abortion occurrence were detected, probably related to the inclusion of molecular diagnostic techniques with more sensitivity or different epidemiological or husbandry conditions in the region analyzed.

Mycoplasma bovis-pneumonia and polyarthritis in feedlot calves in Argentina: First local isolation.

Bovine respiratory disease (BRD) is one of the most frequent clinical concerns in weaned calves after their arrival at the feedlot. This work reports the first local isolation of Mycoplasma bovis from feedlot calves with pneumonia and polyarthritis in Argentina. Twenty four out of 545 calves showed progressive, subacute to chronic respiratory distress, coughing, and fever. Thirty percent of the affected calves also showed lameness and swelling of elbow or carpal, and knee or tarsal joints. Five necropsies were performed and severe multifocal to coalescent pulmonary nodules, containing white-yellowish caseous exudate encircled by fibrous tissue, and fibrinonecrotic arthritis and tenosynovitis were detected. Mycoplasma was isolated from lung and joint samples. The 16S-23S rRNA ITS consensus sequence obtained from these isolates showed 100% similarity with the same region of M. bovis strains. Since there are no commercially available vaccines in the region for the prevention and control of M. bovis pneumonia and arthritis, surveillance is a priority to reduce the source of disease to naïve animals.