Computer vision model for the detection of canine pododermatitis and neoplasia of the paw.

BACKGROUND: Artificial intelligence (AI) has been used successfully in human dermatology. AI utilises convolutional neural networks (CNN) to accomplish tasks such as image classification, object detection and segmentation, facilitating early diagnosis. Computer vision (CV), a field of AI, has shown great results in detecting signs of human skin diseases. Canine paw skin diseases are a common problem in general veterinary practice, and computer vision tools could facilitate the detection and monitoring of disease processes. Currently, no such tool is available in veterinary dermatology. ANIMALS: Digital images of paws from healthy dogs and paws with pododermatitis or neoplasia were used. OBJECTIVES: We tested the novel object detection model Pawgnosis, a Tiny YOLOv4 image analysis model deployed on a microcomputer with a camera for the rapid detection of canine pododermatitis and neoplasia. MATERIALS AND METHODS: The prediction performance metrics used to evaluate the models included mean average precision (mAP), precision, recall, average precision (AP) for accuracy and frames per second (FPS) for speed. RESULTS: A large dataset labelled by a single individual (Dataset A) used to train a Tiny YOLOv4 model provided the best results with a mean mAP of 0.95, precision of 0.86, recall of 0.93 and 20 FPS. CONCLUSIONS AND CLINICAL RELEVANCE: This novel object detection model has the potential for application in the field of veterinary dermatology.

Large-scale genome analysis of bovine commensal Escherichia coli reveals that bovine-adapted E. coli lineages are serving as evolutionary sources of the emergence of human intestinal pathogenic strains.

How pathogens evolve their virulence to humans in nature is a scientific issue of great medical and biological importance. Shiga toxin (Stx)-producing Escherichia coli (STEC) and enteropathogenic E. coli (EPEC) are the major foodborne pathogens that can cause hemolytic uremic syndrome and infantile diarrhea, respectively. The locus of enterocyte effacement (LEE)-encoded type 3 secretion system (T3SS) is the major virulence determinant of EPEC and is also possessed by major STEC lineages. Cattle are thought to be the primary reservoir of STEC and EPEC. However, genome sequences of bovine commensal E. coli are limited, and the emerging process of STEC and EPEC is largely unknown. Here, we performed a large-scale genomic comparison of bovine commensal E. coli with human commensal and clinical strains, including EPEC and STEC, at a global level. The analyses identified two distinct lineages, in which bovine and human commensal strains are enriched, respectively, and revealed that STEC and EPEC strains have emerged in multiple sublineages of the bovine-associated lineage. In addition to the bovine-associated lineage-specific genes, including fimbriae, capsule, and nutrition utilization genes, specific virulence gene communities have been accumulated in stx- and LEE-positive strains, respectively, with notable overlaps of community members. Functional associations of these genes probably confer benefits to these E. coli strains in inhabiting and/or adapting to the bovine intestinal environment and drive their evolution to highly virulent human pathogens under the bovine-adapted genetic background. Our data highlight the importance of large-scale genome sequencing of animal strains in the studies of zoonotic pathogens.

Hot topic: Detecting digital dermatitis with computer vision.

Digital dermatitis (DD) is linked to severe lameness, infertility, and decreased milk production in cattle. Early detection of DD provides an improved prognosis for treatment and recovery; however, this is extremely challenging on commercial dairy farms. Computer vision (COMV) models can help facilitate early DD detection on commercial dairy farms. The aim of this study was to develop and implement a novel COMV tool to identify DD lesions on a commercial dairy farm. Using a database of more than 3,500 DD lesion images, a model was trained using the YOLOv2 architecture to detect the M-stages of DD. The YOLOv2 COMV model detected DD with an accuracy of 71%, and the agreement was quantified as "moderate" by Cohen's kappa when compared with a human evaluator for the internal validation. In the external validation, the YOLOv2 COMV model detected DD with an accuracy of 88% and agreement was quantified as "fair" by Cohen's kappa. Implementation of COMV tools for DD detection provides an opportunity to identify cows for DD treatment, which has the potential to lower DD prevalence and improve animal welfare on commercial dairy farms.

Evaluating the efficacy of beef slaughter line interventions by quantifying the six major non-O157 Shiga toxin producing Escherichia coli serogroups using real-time multiplex PCR.

Six major Shiga toxin producing Escherichia coli (STEC) serogroups: O26, O103, O145, O111, O121, and O45 have been declared as adulterants in federally inspected raw beef in the USA effective June 4th, 2012 in addition to the routinely tested STEC O157: H7. This study tests a real-time multiplex PCR assay and pooling of the samples to optimize the detection and quantification (prevalence and contamination) of six major non-O157 STEC, regardless of possessing Shiga toxins. To demonstrate the practicality, one large-scale slaughter plant (Plant LS) and one small-scale slaughter plant (Plant SS) located in the Mid-Western USA were sampled, in 2011, before the establishment of 2013 USDA laboratory protocols. Carcasses were sampled at consecutive intervention stations and beef trimmings were collected at the end of the fabrication process. Plant SS had marginally more contaminated samples than Plant LS (p-value 0.08). The post-hide removal wash, steam pasteurization, and lactic acid (≤5%) spray used in Plant LS seemed to reduce the six serogroups effectively, compared to the hot-water wash and 7-day chilling at Plant SS. Compared to the culture isolation methods, quantification of the non-O157 STEC using real-time PCR may be an efficient way to monitor the efficacy of slaughter line interventions.

Comparative analysis of computer vision algorithms for the real-time detection of digital dermatitis in dairy cows.

Digital dermatitis (DD) is a bovine claw disease responsible for ulcerative lesions on the planar aspect of the hoof. DD is associated with massive herd outbreaks of lameness and influences cattle welfare and production. Early detection of DD can lead to prompt treatment and decrease lameness. Computer vision (CV) provides a unique opportunity to improve early detection. The study aims to train and compare applications for the real-time detection of DD in dairy cows. Eight CV models were trained for detection and scoring, compared using performance metrics and inference time, and the best model was automated for real-time detection using images and video. Images were collected from commercial dairy farms while facing the interdigital space on the plantar surface of the foot. Images were scored for M-stages of DD by a trained investigator using the M-stage DD classification system with distinct labels for hyperkeratosis (H) and proliferations (P). Two sets of images were compiled: the first dataset (Dataset 1) containing 1,177 M0/M4H and 1,050 M2/M2P images and the second dataset (Dataset 2) containing 240 M0, 17 M2, 51 M2P, 114 M4H, and 108 M4P images. Models were trained to detect and score DD lesions and compared for precision, recall, and mean average precision (mAP) in addition to inference time in frame per second (FPS). Seven of the nine CV models performed well compared to the ground truth of labeled images using Dataset 1. The six models, Faster R-CNN, Cascade R-CNN, YOLOv3, Tiny YOLOv3, YOLOv4, Tiny YOLOv4, and YOLOv5s achieved an mAP between 0.964 and 0.998, whereas the other two models, SSD and SSD Lite, yielded an mAP of 0.371 and 0.387 respectively. Overall, YOLOv4, Tiny YOLOv4, and YOLOv5s outperformed all other models with almost perfect precision, perfect recall, and a higher mAP. Tiny YOLOv4 outperformed all other models with respect to inference time at 333 FPS, followed by YOLOv5s at 133 FPS and YOLOv4 at 65 FPS. YOLOv4 and Tiny YOLOv4 performed better than YOLOv5s compared to the ground truth using Dataset 2. YOLOv4 and Tiny YOLOv4 yielded a similar mAP of 0.896 and 0.895, respectively. However, Tiny YOLOv4 achieved both higher precision and recall compared to YOLOv4. Finally, Tiny YOLOv4 was able to detect DD lesions on a commercial dairy farm with high performance and speed. The proposed CV tool can be used for early detection and prompt treatment of DD in dairy cows. This result is a step towards applying CV algorithms to veterinary medicine and implementing real-time DD detection on dairy farms.

A high-throughput open-array qPCR gene panel to identify, virulotype, and subtype O157 and non-O157 enterohemorrhagic Escherichia coli.

Enterohemorrhagic Escherichia coli (EHEC), including O157 and non-O157 serotypes are significant foodborne pathogens that require sensitive and discriminatory methods for detection and characterization. There are numerous PCR-based methods for the detection of EHEC virulence factors, but the time and cost involved with large-scale screening efforts and population level analyses have limited the size and scope of studies. Recent technological advancements have combined the high-throughput performance of the microarray with the specificity and sensitivity of real-time qPCR to make large-scale screening efforts both time- and cost-effective. This study identified and evaluated a panel of 28 genetic markers including known virulence and regulatory genes, O-antigen genes, and select prophage regions of O157 and non-O157 EHEC that can be used with high-throughput PCR to virulotype, serotype, and preliminarily subtype large numbers of isolates. The PCR assays for the target genes were shown to be robust using multiple extraction methods and PCR platforms. Preliminary quantitative PCR showed that an EHEC concentration of 10(4) CFU/ml or lower could be detected, with a linear range of detection over five to six orders of magnitude. The panel of 28 target genes has the potential to become an integral tool in outbreak, environmental, and genetic investigations of EHEC.

Efficient differentiation of Mycobacterium avium complex species and subspecies by use of five-target multiplex PCR.

Infections caused by the Mycobacterium avium complex (MAC) are on the rise in both human and veterinary medicine. A means of effectively discriminating among closely related yet pathogenetically diverse members of the MAC would enable better diagnosis and treatment as well as further our understanding of the epidemiology of these pathogens. In this study, a five-target multiplex PCR designed to discriminate MAC organisms isolated from liquid culture media was developed. This MAC multiplex was designed to amplify a 16S rRNA gene target common to all Mycobacterium species, a chromosomal target called DT1 that is unique to M. avium subsp. avium serotypes 2 and 3, to M. avium subsp. silvaticum, and to M. intracellulare, and three insertion sequences, IS900, IS901, and IS1311. The pattern of amplification results allowed determination of whether isolates were mycobacteria, whether they were members of the MAC, and whether they belonged to one of three major MAC subspecies, M. avium subsp. paratuberculosis, M. avium subsp. avium, and M. avium subsp. hominissuis. Analytical sensitivity was 10 fg of M. avium subsp. paratuberculosis genomic DNA, 5 to 10 fg of M. avium subsp. avium genomic DNA, and 2 to 5 fg of DNA from other mycobacterial species. Identification accuracy of the MAC multiplex was evaluated by testing 53 bacterial reference strains consisting of 28 different mycobacterial species and 12 nonmycobacterial species. Identification accuracy in a clinical setting was evaluated for 223 clinical MAC isolates independently identified by other methods. Isolate identification agreement between the MAC multiplex and these comparison assays was 100%. The novel MAC multiplex is a rapid, reliable, and simple assay for discrimination of MAC species and subspecies in liquid culture media.

Development of real-time PCR and loop-mediated isothermal amplification (LAMP) assays for the differential detection of digital dermatitis associated treponemes.

Bovine digital dermatitis (DD) is a severe infectious cause of lameness in cattle worldwide, with important economic and welfare consequences. There are three treponeme phylogroups (T. pedis, T. phagedenis, and T. medium) that are implicated in playing an important causative role in DD. This study was conducted to develop real-time PCR and loop-mediated isothermal amplification (LAMP) assays for the detection and differentiation of the three treponeme phylogroups associated with DD. The real-time PCR treponeme phylogroup assays targeted the 16S-23S rDNA intergenic space (ITS) for T. pedis and T. phagedenis, and the flagellin gene (flaB2) for T. medium. The 3 treponeme phylogroup LAMP assays targeted the flagellin gene (flaB2) and the 16S rRNA was targeted for the Treponeme ssp. LAMP assay. The real-time PCR and LAMP assays correctly detected the target sequence of all control strains examined, and no cross-reactions were observed, representing 100% specificity. The limit of detection for each of the three treponeme phylogroup real-time PCR and LAMP assays was ≤ 70 fg/µl. The detection limit for the Treponema spp. LAMP assay ranged from 7-690 fg/µl depending on phylogroup. Treponemes were isolated from 40 DD lesion biopsies using an immunomagnetic separation culture method. The treponeme isolation samples were then subjected to the real-time PCR and LAMP assays for analysis. The treponeme phylogroup real-time PCR and LAMP assay results had 100% agreement, matching on all isolation samples. These results indicate that the developed assays are a sensitive and specific test for the detection and differentiation of the three main treponeme phylogroups implicated in DD.

Gene markers of generic Escherichia coli associated with colonization and persistence of Escherichia coli O157 in cattle.

Enterohemorrhagic Escherichia coli (EHEC) O157 are important foodborne pathogens whose major reservoir are asymptomatic cattle. There is evidence suggesting that nonpathogenic E. coli and bacteriophages in the gastro-intestinal tract can influence the pathogenicity of EHEC O157. The factors contributing to the onset and persistence of shedding EHEC O157 in cattle are not completely elucidated. This study used Bayesian network analysis to identify genetic markers of generic E. coli associated with shedding of EHEC O157 in cattle from data generated during an oral experimental challenge study in 4 groups of 6 steers inoculated with three different EHEC O157 strains. The quantification of these associations was accomplished using mixed effects logistic regression. The results showed that the concurrent presence of generic E. coli carrying the prophage marker R4-N and the virulence marker stx2 increased the odds of the onset of EHEC O157 shedding. The presence of prophage markers z2322 and X011C increased, while C1.N decreased the odds of shedding EHEC O157 two days later. A significant antagonist interaction effect between the presence of the virulence marker stx2 on the day of shedding EHEC O157 and two days before shedding was also found. In terms of the persistence of EHEC O157 shedding, the presence of prophage marker R4-N (OR=16, and 95% confidence interval (CI): 1.1, 252) was found to increase the odds of stopping EHEC O157 shedding, whereas prophage marker C1.N (OR=0.16, CI: 0.03, 0.7) and the enterohemolysin gene hly (OR=0.03, CI: 0.001, 0.8) were found to significantly decrease the odds of stopping EHEC O157 shedding. In conclusion, the study found that the presence of certain genetic markers in the generic E. coli genome can influence the pathogenicity of EHEC O157.

Rapid and reliable detection of Shiga toxin-producing Escherichia coli by real-time multiplex PCR.

Escherichia coli O26, O45, O103, O111, O121, O145, and O157 are the predominant Shiga toxin-producing E. coli (STEC) serogroups implicated in outbreaks of human foodborne illness worldwide. The increasing prevalence of these pathogens has important public health implications. Beef products have been considered a main source of foodborne human STEC infections. Robust and sensitive methods for the detection and characterization of these pathogens are needed to determine prevalence and incidence of STEC in beef processing facilities and to improve food safety interventions aimed at eliminating STEC from the food supply. This study was conducted to develop Taqman real-time multiplex PCR assays for the screening and rapid detection of the predominant STEC serogroups associated with human illness. Three serogroup-specific assays targeted the O-antigen gene clusters of E. coli O26 (wzy), O103 (wzx), and O145 (wzx) in assay 1, O45 (wzy), O111 (manC), and O121 (wzx) in assay 2, and O157 (rfbE) in assay 3. The uidA gene also was included in the serogroup-specific assays as an E. coli internal amplification control. A fourth assay was developed to target selected virulence genes for Shiga toxin (stx(1) and stx(2)), intimin (eae), and enterohemolysin (ehxA). The specificity of the serogroup and virulence gene assays was assessed by testing 100 and 62 E. coli strains and non-E. coli control strains, respectively. The assays correctly detected the genes in all strains examined, and no cross-reactions were observed, representing 100 % specificity. The detection limits of the assays were 10(3) or 10(4) CFU/ml for pure cultures and artificially contaminated fecal samples, and after a 6-h enrichment period, the detection limit of the assays was 10(0) CFU/ml. These results indicate that the four real-time multiplex PCR assays are robust and effective for the rapid and reliable detection of the seven predominant STEC serogroups of major public health concern and the detection of their virulence genes.

Rapid mycobacterial liquid culture-screening method for Mycobacterium avium complex based on secreted antigen-capture enzyme-linked immunosorbent assay.

Sensors in automated liquid culture systems for mycobacteria, such as MGIT, BacT/Alert 3D, and Trek ESP II, flag growth of any type of bacteria; a positive signal does not mean that the target mycobacteria are present. All signal-positive cultures thus require additional and often laborious testing. An immunoassay was developed to screen liquid mycobacterial cultures for evidence of Mycobacterium avium complex (MAC). The method, called the MAC-enzyme-linked immunosorbent assay (ELISA), relies on detection of MAC-specific secreted antigens in liquid culture. Secreted MAC antigens were captured by the MAC-ELISA with polyclonal anti- Mycobacterium avium subsp. paratuberculosis chicken immunoglobulin Y (IgY), detected using rabbit anti-MAC IgG, and then revealed using horseradish peroxidase-conjugated goat anti-rabbit IgG. When the MAC-ELISA was evaluated using pure cultures of known mycobacterial (n = 75) and nonmycobacterial (n = 17) organisms, no false-positive or false-negative MAC-ELISA results were found. By receiver operator characteristic (ROC) analysis of 1,275 previously identified clinical isolates, at the assay optimal cutoff the diagnostic sensitivity and specificity of the MAC-ELISA were 92.6% (95% confidence interval [95% CI], 90.3 to 94.5) and 99.9% (95% CI, 99.2 to 100), respectively, with an area under the ROC curve of 0.992. Prospective evaluation of the MAC-ELISA with an additional 652 clinical samples inoculated into MGIT ParaTB medium and signaling positive per the manufacturer's instructions found that the MAC-ELISA was effective in determining those cultures that actually contained MAC species and warranting the resources required to identify the organism by PCR. Of these 652 MGIT-positive cultures, the MAC-ELISA correctly identified 96.8% (of 219 MAC-ELISA-positive cultures) as truly containing MAC mycobacteria, based on PCR or high-performance liquid chromatography (HPLC) as reference tests. Only 6 of 433 MGIT signal-positive cultures (1.4%) were MAC-ELISA false negative, and only 7 of 219 MGIT signal-negative cultures (3.2%) were false positive. The MAC-ELISA is a low-cost, rapid, sensitive, and specific test for MAC in liquid cultures. It could be used in conjunction with or independent of automated culture reading instrumentation. For maximal accuracy and subspecies-specific identification, use of a confirmatory multiplex MAC PCR is recommended.

Relationships among specific viral pathogens, virus-induced interleukin-8, and respiratory symptoms in infancy.

Both virus-mediated damage to airway tissues and induction of pro-inflammatory cytokines such as interleukin-8 (IL-8) could contribute to symptom severity during viral respiratory infections in children. To test the hypothesis that IL-8 contributes to the pathogenesis of respiratory symptoms during naturally acquired respiratory viral infections in children, nasal wash samples collected from infants with acute viral infections (n = 198) or from healthy uninfected infants (n = 31) were analysed for IL-8. Nasal wash IL-8 was positively related to age in uninfected children (rs = 0.36, p < 0.05). Respiratory syncytial virus (RSV) infection caused more severe respiratory symptoms compared to infections with influenza A, parainfluenza viruses, or rhinoviruses. In addition, RSV, parainfluenza and rhinovirus infections increased levels of IL-8 in nasal lavage fluid, and there were some differences in the ability of the viruses to induce IL-8 production (RSV>influenza, p < 0.05). Finally, there were significant correlations between nasal wash IL-8 levels and symptom scores during infections with rhinovirus (rs = 0.56, p < 0.001) or influenza A (rs = 0.45, p < 0.05), but not with parainfluenza virus or RSV. These findings provide evidence of a close relationship between the generation of IL-8 and symptoms during acute community-acquired infections with rhinovirus or influenza A. In contrast, for RSV and parainfluenza infections, factors in addition to IL-8 production appear to contribute to the generation of clinical symptoms.

Developmental cytokine response profiles and the clinical and immunologic expression of atopy during the first year of life.

BACKGROUND: Allergic diseases have been linked to abnormal patterns of immune development, and this has stimulated efforts to define the precise patterns of cytokine dysregulation that are associated with specific atopic phenotypes. OBJECTIVE: Cytokine-response profiles were prospectively analyzed over the first year of life and compared with the clinical and immunologic expressions of atopy. METHODS: Umbilical cord and 1-year PBMCs were obtained from 285 subjects from allergic families. PHA-stimulated cytokine-response profiles (IL-5, IL-10, IL-13, and IFN-gamma) were compared with blood eosinophil counts and total and specific IgE levels (dust mites, cat, egg, Alternaria species, peanut, milk, and dog) at age 1 year and at the development of atopic dermatitis and food allergy. RESULTS: For the cohort as a whole, cytokine responses did not evolve according to a strict TH1 or TH2 polarization pattern. PHA-stimulated cord blood cells secreted low levels of IL-5 (2.1 pg/mL), moderate levels of IFN-gamma (57.4 pg/mL), and greater amounts of IL-13 (281.8 pg/mL). From birth to 1 year, IL-5 responses dramatically increased, whereas IL-13 and IFN-gamma responses significantly decreased. Reduced cord blood secretion of IL-10 and IFN-gamma was associated with subsequent sensitization to egg. In addition, there was evidence of TH2 polarization (increased IL-5 and IL-13 levels) associated with blood eosinophilia and increased total IgE levels by age 1 year. CONCLUSION: These findings demonstrate that cytokine responses change markedly during the first year of life and provide further evidence of a close relationship between TH2 skewing of immune responses and the incidence of atopic manifestations in children.

Effects of dog ownership and genotype on immune development and atopy in infancy.

BACKGROUND: Exposure to furred pets might confer protection against the development of allergic sensitization through a mechanism that is incompletely understood. OBJECTIVE: The objective of this study was to determine the effects of pet exposure and genotype on immunologic development and the incidence of atopic markers and diseases in the first year of life. METHODS: Pet exposure in the home was compared with cytokine secretion patterns (mitogen-stimulated mononuclear cells at birth and age 1 year) and indicators of atopy (allergen-specific and total IgE, eosinophilia, food allergy, atopic dermatitis) in 285 infants. Interactions with genotype at the CD14 locus were also evaluated in the data analyses. RESULTS: Exposure to dogs was associated with reduced allergen sensitization (19% vs 33%, P =.020) and atopic dermatitis (30% vs 51%, P <.001). The risk for atopic dermatitis was further influenced by genotype at the CD14 locus (P =.006), even after adjusting for exposure to dogs (P =.003). Furthermore, infants with the genotype -159TT were less likely to develop atopic dermatitis if they were exposed to a dog (5% vs 43%, P =.04). Last, dog exposure was associated with increased IL-10 (117 vs 79 pg/mL, P =.002) and IL-13 (280 vs 226 pg/mL, P =.013) responses at age 1 year. CONCLUSIONS: Having a dog in infancy is associated with higher IL-10 and IL-13 cytokine secretion profiles and reduced allergic sensitization and atopic dermatitis. These findings suggest that postnatal exposure to dogs can influence immune development in a genotype-specific fashion and thereby attenuate the development of atopy in at-risk children.