A method for labelling lesions for machine learning and some new observations on osteochondrosis in computed tomographic scans of four pig joints.

BACKGROUND: Osteochondrosis is a major cause of leg weakness in pigs. Selection against osteochondrosis is currently based on manual scoring of computed tomographic (CT) scans for the presence of osteochondrosis manifesta lesions. It would be advantageous if osteochondrosis could be diagnosed automatically, through artificial intelligence methods using machine learning. The aim of this study was to describe a method for labelling articular osteochondrosis lesions in CT scans of four pig joints to guide development of future machine learning algorithms, and to report new observations made during the labelling process. The shoulder, elbow, stifle and hock joints were evaluated in CT scans of 201 pigs. RESULTS: Six thousand two hundred fifty osteochondrosis manifesta and cyst-like lesions were labelled in 201 pigs representing a total volume of 211,721.83 mm3. The per-joint prevalence of osteochondrosis ranged from 64.7% in the hock to 100% in the stifle joint. The lowest number of lesions was found in the hock joint at 208 lesions, and the highest number of lesions was found in the stifle joint at 4306 lesions. The mean volume per lesion ranged from 26.21 mm3 in the shoulder to 42.06 mm3 in the elbow joint. Pigs with the highest number of lesions had small lesions, whereas pigs with few lesions frequently had large lesions, that have the potential to become clinically significant. In the stifle joint, lesion number had a moderate negative correlation with mean lesion volume at r = - 0.54, p < 0.001. CONCLUSIONS: The described labelling method is an important step towards developing a machine learning algorithm that will enable automated diagnosis of osteochondrosis manifesta and cyst-like lesions. Both lesion number and volume should be considered during breeding selection. The apparent inverse relationship between lesion number and volume warrants further investigation.

Development and validation of a regression model for Listeria monocytogenes growth in roast beefs.

Food business operators are responsible for food safety and assessment of shelf lives for their ready-to-eat products. For assisting them, a customized software based on predictive models, ListWare, is being developed. The aim of this study was to develop and validate a predictive model for the growth of Listeria monocytogenes in sliced roast beef. A challenge study was performed comprising 51 different combinations of variables. The growth curves followed the Baranyi and Roberts model with no clear lag phase and specific growth rates in the range <0.005-0.110 hr-1. A linear regression model was developed based on 528 observations and had an adjusted R-square of 0.80. The significant predictors were storage temperature, sodium lactate, interactions between sodium acetate and temperature, and MAP packaging and temperature. The model was validated in four laboratories in three countries. For conditions where the model predicted up to + log 2 cfu/g Listeria concentration, the observed concentrations were true or below the predicted concentration in 90% of the cases. For the remaining 10%, the roast beef was coated with spices and therefore different from the others. The model will be implemented in ListWare web-application for calculation of "Listeria shelf life".

A QTL for Number of Teats Shows Breed Specific Effects on Number of Vertebrae in Pigs: Bridging the Gap Between Molecular and Quantitative Genetics.

Modern breeding schemes for livestock species accumulate a large amount of genotype and phenotype data which can be used for genome-wide association studies (GWAS). Many chromosomal regions harboring effects on quantitative traits have been reported from these studies, but the underlying causative mutations remain mostly undetected. In this study, we combine large genotype and phenotype data available from a commercial pig breeding scheme for three different breeds (Duroc, Landrace, and Large White) to pinpoint functional variation for a region on porcine chromosome 7 affecting number of teats (NTE). Our results show that refining trait definition by counting number of vertebrae (NVE) and ribs (RIB) helps to reduce noise from other genetic variation and increases heritability from 0.28 up to 0.62 NVE and 0.78 RIB in Duroc. However, in Landrace, the effect of the same QTL on NTE mainly affects NVE and not RIB, which is reflected in reduced heritability for RIB (0.24) compared to NVE (0.59). Further, differences in allele frequencies and accuracy of rib counting influence genetic parameters. Correction for the top SNP does not detect any other QTL effect on NTE, NVE, or RIB in Landrace or Duroc. At the molecular level, haplotypes derived from 660K SNP data detects a core haplotype of seven SNPs in Duroc. Sequence analysis of 16 Duroc animals shows that two functional mutations of the Vertnin (VRTN) gene known to increase number of thoracic vertebrae (ribs) reside on this haplotype. In Landrace, the linkage disequilibrium (LD) extends over a region of more than 3 Mb also containing both VRTN mutations. Here, other modifying loci are expected to cause the breed-specific effect. Additional variants found on the wildtype haplotype surrounding the VRTN region in all sequenced Landrace animals point toward breed specific differences which are expected to be present also across the whole genome. This Landrace specific haplotype contains two missense mutations in the ABCD4 gene, one of which is expected to have a negative effect on the protein function. Together, the integration of largescale genotype, phenotype and sequence data shows exemplarily how population parameters are influenced by underlying variation at the molecular level.

Monitoring lean meat percentage predictions from optical grading probes by a commercial cutting pattern.

The lean meat percentage (LMP) classification in Norwegian slaughterhouses is obtained by Hennessy Grading Probe 7 (HGP7), an optical tool. Even though the HGP7 method is validated frequently, there is industrial and legislative demand to reconsider the applied LMP equation, typically due to the introduction of new breeds. A deboning pilot plant generates precise yield data using cutting and deboning stratified pork carcasses by a specific commercial cutting pattern (CCP) at an annual rate of approximately 250 slaughter pigs. This paper shows how results obtained by CCP can be used to measure LMP in pork and how these results can be used for monitoring the quality of LMP predicted by HGP7. The effect of gender, maternal- and paternal lines on validity of HGP7 predictions was evaluated. The effect of introducing a new maternal line (TN70) seems to be substantial, whereas the effects of the tested paternal lines are small to negligible.

The use of deep learning to automate the segmentation of the skeleton from CT volumes of pigs.

Computed tomography (CT) scanning of pigs has been shown to produce detailed phenotypes useful in pig breeding. Due to the large number of individuals scanned and corresponding large data sets, there is a need for automatic tools for analysis of these data sets. In this paper, the feasibility of deep learning for fully automatic segmentation of the skeleton of pigs from CT volumes is explored. To maximize performance, given the training data available, a series of problem simplifications are applied. The deep-learning approach can replace our currently used semiautomatic solution, with increased robustness and little or no need for manual control. Accuracy was highly affected by training data, and expanding the training set can further increase performance making this approach especially promising.

Effects of dietary beef, pork, chicken and salmon on intestinal carcinogenesis in A/J Min/+ mice.

The International Agency for Research on Cancer has classified red meat as "probably carcinogenic to humans" (Group 2A). In mechanistic studies exploring the link between intake of red meat and CRC, heme iron, the pigment of red meat, is proposed to play a central role as a catalyzer of luminal lipid peroxidation and cytotoxicity. In the present work, the novel A/J Min/+ mouse was used to investigate the effects of dietary beef, pork, chicken, or salmon (40% muscle food (dry weight) and 60% powder diet) on Apc-driven intestinal carcinogenesis, from week 3-13 of age. Muscle food diets did not differentially affect carcinogenesis in the colon (flat ACF and tumors). In the small intestine, salmon intake resulted in a lower tumor size and load than did meat from terrestrial animals (beef, pork or chicken), while no differences were observed between the effects of white meat (chicken) and red meat (pork and beef). Additional results indicated that intestinal carcinogenesis was not related to dietary n-6 polyunsaturated fatty acids, intestinal formation of lipid peroxidation products (thiobarbituric acid reactive substances, TBARS), or cytotoxic effects of fecal water on Apc-/+ cells. Notably, the amount of heme reaching the colon appeared to be relatively low in this study. The greatest tumor load was induced by the reference diet RM1, underlining the importance of the basic diets in experimental CRC. The present study in A/J Min/+ mice does not support the hypothesis of a role of red meat in intestinal carcinogenesis.