Investigating the role of free-ranging wild boar (Sus scrofa) in the re-emergence of enzootic pneumonia in domestic pig herds: a pathological, prevalence and risk-factor study

Enzootic pneumonia (EP) caused by Mycoplasma hyopneumoniae has a significant economic impact on domestic pig production. A control program carried out from 1999 to 2003 successfully reduced disease occurrence in domestic pigs in Switzerland, but recurrent outbreaks suggested a potential role of free-ranging wild boar (Sus scrofa) as a source of re-infection. Since little is known on the epidemiology of EP in wild boar populations, our aims were: (1) to estimate the prevalence of M. hyopneumoniae infections in wild boar in Switzerland; (2) to identify risk factors for infection in wild boar; and (3) to assess whether infection in wild boar is associated with the same gross and microscopic lesions typical of EP in domestic pigs. Nasal swabs, bronchial swabs and lung samples were collected from 978 wild boar from five study areas in Switzerland between October 2011 and May 2013. Swabs were analyzed by qualitative real time PCR and a histopathological study was conducted on lung tissues. Risk factor analysis was performed using multivariable logistic regression modeling. Overall prevalence in nasal swabs was 26.2% (95% CI 23.3-29.3%) but significant geographical differences were observed. Wild boar density, occurrence of EP outbreaks in domestic pigs and young age were identified as risk factors for infection. There was a significant association between infection and lesions consistent with EP in domestic pigs. We have concluded that M. hyopneumoniae is widespread in the Swiss wild boar population, that the same risk factors for infection of domestic pigs also act as risk factors for infection of wild boar, and that infected wild boar develop lesions similar to those found in domestic pigs. However, based on our data and the outbreak pattern in domestic pigs, we propose that spillover from domestic pigs to wild boar is more likely than transmission from wild boar to pigs.

Lung Pattern Classification for Interstitial Lung Diseases Using a Deep Convolutional Neural Network

Automated tissue characterization is one of the most crucial components of a computer aided diagnosis (CAD) system for interstitial lung diseases (ILDs). Although much research has been conducted in this field, the problem remains challenging. Deep learning techniques have recently achieved impressive results in a variety of computer vision problems, raising expectations that they might be applied in other domains, such as medical image analysis. In this paper, we propose and evaluate a convolutional neural network (CNN), designed for the classification of ILD patterns. The proposed network consists of 5 convolutional layers with 2×2 kernels and LeakyReLU activations, followed by average pooling with size equal to the size of the final feature maps and three dense layers. The last dense layer has 7 outputs, equivalent to the classes considered: healthy, ground glass opacity (GGO), micronodules, consolidation, reticulation, honeycombing and a combination of GGO/reticulation. To train and evaluate the CNN, we used a dataset of 14696 image patches, derived by 120 CT scans from different scanners and hospitals. To the best of our knowledge, this is the first deep CNN designed for the specific problem. A comparative analysis proved the effectiveness of the proposed CNN against previous methods in a challenging dataset. The classification performance (~85.5%) demonstrated the potential of CNNs in analyzing lung patterns. Future work includes, extending the CNN to three-dimensional data provided by CT volume scans and integrating the proposed method into a CAD system that aims to provide differential diagnosis for ILDs as a supportive tool for radiologists.