Scoring pleurisy in slaughtered pigs using convolutional neural networks.

Diseases of the respiratory system are known to negatively impact the profitability of the pig industry, worldwide. Considering the relatively short lifespan of pigs, lesions can be still evident at slaughter, where they can be usefully recorded and scored. Therefore, the slaughterhouse represents a key check-point to assess the health status of pigs, providing unique and valuable feedback to the farm, as well as an important source of data for epidemiological studies. Although relevant, scoring lesions in slaughtered pigs represents a very time-consuming and costly activity, thus making difficult their systematic recording. The present study has been carried out to train a convolutional neural network-based system to automatically score pleurisy in slaughtered pigs. The automation of such a process would be extremely helpful to enable a systematic examination of all slaughtered livestock. Overall, our data indicate that the proposed system is well able to differentiate half carcasses affected with pleurisy from healthy ones, with an overall accuracy of 85.5%. The system was better able to recognize severely affected half carcasses as compared with those showing less severe lesions. The training of convolutional neural networks to identify and score pneumonia, on the one hand, and the achievement of trials in large capacity slaughterhouses, on the other, represent the natural pursuance of the present study. As a result, convolutional neural network-based technologies could provide a fast and cheap tool to systematically record lesions in slaughtered pigs, thus supplying an enormous amount of useful data to all stakeholders in the pig industry.

Rift Valley Fever Virus among Wild Ruminants, Etosha National Park, Namibia, 2011.

After a May 2011 outbreak of Rift Valley fever among livestock northeast of Etosha National Park, Namibia, wild ruminants in the park were tested for the virus. Antibodies were detected in springbok, wildebeest, and black-faced impala, and viral RNA was detected in springbok. Seroprevalence was high, and immune response was long lasting.

Genetic characterization of Italian field strains of Schmallenberg virus based on N and NSs genes.

Following its first identification in Germany in 2011, the Schmallenberg virus (SBV) has rapidly spread to many other European countries. Despite the wide dissemination, the molecular characterization of the circulating strains is limited to German, Belgian, Dutch, and Swiss viruses. To fill this gap, partial genetic characterization of 15 Italian field strains was performed, based on S segment genes. Samples were collected in 2012 in two different regions where outbreaks occurred during distinct epidemic seasons. The comparative sequence analysis demonstrated a high molecular stability of the circulating viruses; nevertheless, we identified several variants of the N and NSs proteins not described in other SBV isolates circulating in Europe.

Scoring Enzootic Pneumonia-like Lesions in Slaughtered Pigs: Traditional vs. Artificial-Intelligence-Based Methods.

Artificial-intelligence-based methods are regularly used in the biomedical sciences, mainly in the field of diagnostic imaging. Recently, convolutional neural networks have been trained to score pleurisy and pneumonia in slaughtered pigs. The aim of this study is to further evaluate the performance of a convolutional neural network when compared with the gold standard (i.e., scores provided by a skilled operator along the slaughter chain through visual inspection and palpation). In total, 441 lungs (180 healthy and 261 diseased) are included in this study. Each lung was scored according to traditional methods, which represent the gold standard (Madec's and Christensen's grids). Moreover, the same lungs were photographed and thereafter scored by a trained convolutional neural network. Overall, the results reveal that the convolutional neural network is very specific (95.55%) and quite sensitive (85.05%), showing a rather high correlation when compared with the scores provided by a skilled veterinarian (Spearman's coefficient = 0.831, p < 0.01). In summary, this study suggests that convolutional neural networks could be effectively used at slaughterhouses and stimulates further investigation in this field of research.

Survey of ixodid ticks and two tick-borne pathogens in African buffaloes, Syncerus caffer, from the Caprivi Strip, Namibia.

A capture operation to ascertain health status in free-ranging buffaloes from six different areas in the Caprivi Strip in the northeast corner of Namibia was conducted in October 2009. Basic information on the ticks and tick-borne pathogens normally found in wildlife from this area are scarce. The objective of this study was to assess the host status of African buffaloes, Syncerus caffer, for ixodid ticks and two selected tick-borne pathogens in the Caprivi Strip, a key area bordering Angola, Zambia, Botswana, and Zimbabwe. Four different tick species have been identified among the 233 collected specimens, and, of 95 tested buffaloes, 54 (57%) were positive for Theileria parva, whereas only 3 (3%) showed evidence of being infected with Ehrlichia ruminantium.

Training Convolutional Neural Networks to Score Pneumonia in Slaughtered Pigs.

The slaughterhouse can act as a valid checkpoint to estimate the prevalence and the economic impact of diseases in farm animals. At present, scoring lesions is a challenging and time-consuming activity, which is carried out by veterinarians serving the slaughter chain. Over recent years, artificial intelligence(AI) has gained traction in many fields of research, including livestock production. In particular, AI-based methods appear able to solve highly repetitive tasks and to consistently analyze large amounts of data, such as those collected by veterinarians during postmortem inspection in high-throughput slaughterhouses. The present study aims to develop an AI-based method capable of recognizing and quantifying enzootic pneumonia-like lesions on digital images captured from slaughtered pigs under routine abattoir conditions. Overall, the data indicate that the AI-based method proposed herein could properly identify and score enzootic pneumonia-like lesions without interfering with the slaughter chain routine. According to European legislation, the application of such a method avoids the handling of carcasses and organs, decreasing the risk of microbial contamination, and could provide further alternatives in the field of food hygiene.

Complete Coding Sequences of Lumpy Skin Disease Virus Strains Isolated from Cutaneous Lesions in Namibian Cattle during 2016 Outbreaks.

Between September and October 2016, an outbreak of lumpy skin disease (LSD) was monitored in the Okakarara veterinary district of Namibia. The complete coding sequences were obtained for LSD virus isolates from skin nodules from two symptomatic animals.

Genetic Diversity of Rift Valley Fever Strains Circulating in Namibia in 2010 and 2011.

Outbreaks of Rift Valley fever (RVF) occurred in Namibia in 2010 and 2011. Complete genome characterization was obtained from virus isolates collected during disease outbreaks in southern Namibia in 2010 and from wildlife in Etosha National Park in 2011, close to the area where RVF outbreaks occurred in domestic livestock. The virus strains were sequenced using Sanger sequencing (Namibia_2010) or next generation sequencing (Namibia_2011). A sequence-independent, single-primer amplification (SISPA) protocol was used in combination with the Illumina Next 500 sequencer. Phylogenetic analysis of the sequences of the small (S), medium (M), and large (L) genome segments of RVF virus (RVFV) provided evidence that two distinct RVFV strains circulated in the country. The strain collected in Namibia in 2010 is genetically similar to RVFV strains circulating in South Africa in 2009 and 2010, confirming that the outbreaks reported in the southern part of Namibia in 2010 were caused by possible dissemination of the infection from South Africa. Isolates collected in 2011 were close to RVFV isolates from 2010 collected in humans in Sudan and which belong to the large lineage containing RVFV strains that caused an outbreak in 2006-2008 in eastern Africa. This investigation showed that the RVFV strains circulating in Namibia in 2010 and 2011 were from two different introductions and that RVFV has the ability to move across regions. This supports the need for risk-based surveillance and monitoring.

Assessing the role of migratory birds in the introduction of ticks and tick-borne pathogens from African countries: An Italian experience.

The continuous flow of billions of birds between Africa and Europe creates an "ecological bridge" between physically remote areas. Migratory birds fly south from their breeding grounds during late summer/fall and fly back in spring. These movements regulate the spread of internal and external parasites, as well as pathogens of potential public health concern. The aim of the present study was to investigate the possible introduction of exotic tick species and tick-borne pathogens into Europe via migratory birds. At the bird observatory of Ventotene island (Italy), 443 feeding ticks were collected from 249 birds captured and ringed during their northbound migration in spring 2013. Each tick was identified by morphological and molecular methods and then tested for bacterial and viral pathogens: Borrelia burgdorferi s.l., Rickettsia spp., Ehrlichia ruminantium and Coxiella burnetii, Crimean Congo haemorrhagic fever virus (CCHFV) and Flavivirus. Morphological and molecular identification confirmed Hyalomma rufipes as the most abundant species among the collected arthropods (366/443; 82.6%) followed by Hyalomma marginatum (10/433; 2.3%). Rickettsia aeschlimannii was identified in 158 ticks, while one engorged Amblyomma variegatum nymph was infected with Rickettsia africae. The other bacteria were not detected in any specimen. Among viruses, RNA belonging to West Nile virus and other Flavivirus were detected whereas all ticks were negative for CCHFV RNA. These results confirm how migratory birds play a role in carrying Rickettsia-infected ticks, as well as viruses of zoonotic importance, from Africa into Europe. To what extent tick species are capable of establishing a permanent population once introduced in naïve areas, is far from defined and deserve further investigation.

Antibodies against Schmallenberg virus detected in cattle in the Otjozondjupa region, Namibia.

Several ruminant species have been shown to be susceptible to Schmallenberg virus (SBV), but adult animals usually recover after showing mild or no clinical signs. However, transplacental infection can occur and lead to abortion, malformations and stillborn lambs, calves and goat kids. During November and December 2014, malformations were observed in 11 stillborn calves from two farms in the north-eastern region of Namibia. Blood samples were collected from 9 of the 11 cows that delivered stillborn and malformed calves. All these animals tested negative for Rift Valley fever, bovine viral diarrhoea and infectious bovine rhinotracheitis and were serologically positive for bluetongue virus, SBV and epizootic haemorrhagic disease virus. Clinical findings and serological results suggested that SBV may be circulating in Namibia.

A new member of the Pteropine Orthoreovirus species isolated from fruit bats imported to Italy.

A novel member of the Pteropine Orthoreovirus species has been isolated and sequenced for the whole genome from flying foxes (Pteropus vampyrus) imported to Italy from Indonesia. The new isolate named Indonesia/2010 is genetically similar to Melaka virus which has been the first virus of this species to be shown to be responsible for human respiratory disease. Our findings highlight the importance of flying foxes as vectors of potentially zoonotic viruses and the biological hazard that lies in the import of animals from geographical areas that are ecologically diverse from Europe.

First External Quality Assessment of Molecular and Serological Detection of Rift Valley Fever in the Western Mediterranean Region.

Rift Valley fever (RVF) is a mosquito-borne viral zoonosis which affects humans and a wide range of domestic and wild ruminants. The large spread of RVF in Africa and its potential to emerge beyond its geographic range requires the development of surveillance strategies to promptly detect the disease outbreaks in order to implement efficient control measures, which could prevent the widespread of the virus to humans. The Animal Health Mediterranean Network (REMESA) linking some Northern African countries as Algeria, Egypt, Libya, Mauritania, Morocco, Tunisia with Southern European ones as France, Italy, Portugal and Spain aims at improving the animal health in the Western Mediterranean Region since 2009. In this context, a first assessment of the diagnostic capacities of the laboratories involved in the RVF surveillance was performed. The first proficiency testing (external quality assessment--EQA) for the detection of the viral genome and antibodies of RVF virus (RVFV) was carried out from October 2013 to February 2014. Ten laboratories participated from 6 different countries (4 from North Africa and 2 from Europe). Six laboratories participated in the ring trial for both viral RNA and antibodies detection methods, while four laboratories participated exclusively in the antibodies detection ring trial. For the EQA targeting the viral RNA detection methods 5 out of 6 laboratories reported 100% of correct results. One laboratory misidentified 2 positive samples as negative and 3 positive samples as doubtful indicating a need for corrective actions. For the EQA targeting IgG and IgM antibodies methods 9 out of the 10 laboratories reported 100% of correct results, whilst one laboratory reported all correct results except one false-positive. These two ring trials provide evidence that most of the participating laboratories are capable to detect RVF antibodies and viral RNA thus recognizing RVF infection in affected ruminants with the diagnostic methods currently available.

First cases of Schmallenberg virus in Italy: surveillance strategies.

Following the first report of Schmallenberg virus (SBV) in the brain of a dystocic goat foetus in 2012 in Northern Italy, immediate response actions were adopted to avoid the virus circulation. The brain tested positive by 2 different one-step real-time RT-PCR protocols; these results were also confirmed by partial sequencing of the viral genome. At that time this was the first detection of the new Orthobunyavirus genus within the Bunyaviridae family in Italy. An epidemiological investigation in the involved farm was carried out in collaboration with the CESME - National Reference Centre for the study and verification of Foreign Animal Diseases (Istituto Zooprofilattico Sperimentale dell'Abruzzo e del Molise 'G. Caporale', Italy). Epidemiological information on the flock was provided and analysed, whole blood and serum samples were also collected from all animals in the farm for both virological and serological investigations. All blood samples tested negative for SBV, whereas serological positive results were obtained by virus-neutralization (VN). Epidemiological investigations indicated the possible virus circulation in the area. The subsequent surveillance actions were mainly based on the standardization and reenforcement of passive surveillance protocols, a risk-based serological surveillance programme through VN and an entomological surveillance programme in the involved geographical areas were also put in place. Eventually SBV local circulation was confirmed by real time RT-PCR in 6 Culicoides pools, collected between September and November 2011 in 3 farms in the surroundings of the area of SBV outbreak.

Preliminary report of transfrontier disease surveillance in free-ranging buffalo in the Caprivi Strip, Namibia.

A capture operation to ascertain the health status of free-ranging buffalo (Syncerus caffer) from six areas in the Caprivi Strip in the north-east corner of Namibia is described. In-depth reports on buffalo capture operations and their cost, with detailed descriptions of diseases for research purposes, sampling techniques, field processing of samples and laboratory-related costs are still lacking in the literature. This paper describes materials, methods and the related costs of a disease surveillance operation conducted among buffalo in Namibia. The survey attempted to provide information designed to improve the control of infectious diseases in the Caprivi Strip, a key area bordering Angola, Zambia, Botswana and Zimbabwe.