Estimating Salmonella Typhimurium Growth on Chicken Breast Fillets Under Simulated Less-Than-Truckload Dynamic Temperature Abuse.

Companies may have insufficient freight to fill an entire truck/trailer, and instead only pay for space that their products occupy (i.e., "less-than-truckload" shipping; LTL). As LTL delivery vehicles make multiple stops, there is an increased opportunity for product temperature abuse, which may increase microbial food safety risk. To assess LTL effects on Salmonella Typhimurium growth, commercially produced boneless skinless chicken breast fillets were inoculated and incubated under dynamic 2-h temperature cycles (i.e., 2 h at 4°C and then 2 h at 25°C), mimicking a commercially relevant LTL scenario. Bacterial kinetics were measured over 24 h and then observations compared with predictions of three published Salmonella secondary models by bias and accuracy factor measurement. One model produced more "fail-safe" estimates of Salmonella growth than the other models, although all models were defined as "acceptable." These developed tertiary models can help shippers assess supply chain performance and produce proactive food safety risk management systems.

Effect of iron fortification on microstructural, textural, and sensory characteristics of caprine milk Cheddar cheeses under different storage treatments.

In this study, we manufactured 3 types of caprine milk Cheddar cheese: a control cheese (unfortified) and 2 iron-fortified cheeses, one of which used regular ferrous sulfate (RFS) and the other used large microencapsulated ferrous sulfate (LMFS). We then compared the iron recovery rates and the microstructural, textural, and sensory properties of the 3 cheeses under different storage conditions (temperature and duration). Compositional analysis included fat, protein, ash, and moisture contents. The RFS (FeSO4·7H2O) and LMFS (with 700- to 800-µm large particle ferrous sulfate encapsulated in nonhydrogenated vegetable fat) were added to cheese curds after whey draining and were thoroughly mixed before hooping and pressing the cheese. Three batches of each type of goat cheese were stored at 2 temperatures (4°C and -18°C) for 0, 2, and 4 mo. We analyzed the microstructure of cheese using scanning electron microscopy and image analysis software. A sensory panel (n = 8) evaluated flavors and overall acceptability of cheeses using a 10-point intensity score. Results showed that the control, RFS, and LMFS cheeses contained 0.0162, 0.822, and 0.932 mg of Fe/g of cheese, respectively, with substantially higher iron levels in both fortified cheeses. The iron recovery rates of RFS and LMFS were 71.9 and 73.5%, respectively. Protein, fat, and ash contents (%) of RFS and LMFS cheeses were higher than those of the control. Scanning electron microscopy analyses revealed that LMFS cheese contained smaller and more elongated sharp-edged iron particles, whereas RFS cheese had larger-perimeter rectangular iron crystals. Iron-fortified cheeses generally had higher hardness and gumminess scores than the control cheese. The higher hardness in iron-fortified cheeses compared with the control may be attributed to proteolysis of the protein matrix and its binding with iron crystals during storage. Control cheese had higher sensory scores than the 2 iron-fortified cheeses, and LMFS cheese had the lowest scores for all tested sensory properties.

Effect of Age, Deboning Time of Carcass, and Different Cooking Conditions on the Woody Breast Myopathies in Chicken: A Meta-Analysis.

This meta-analysis review undertakes a comprehensive examination of various approaches for identifying myopathic fillets and meticulously evaluates the effects of bird age, deboning time, and different cooking and storage conditions on woody breast (WB) myopathic conditions in broiler deboned fillets. The data, meticulously collected from 20 articles based on predefined inclusion criteria sourced from various databases and online resources, reveal significant insights. For instance, the analysis uncovers that deboning time significantly affects Meullenet-Owens Razor Shear (MORS), Blunt Meullenet-Owens Razor Shear (BMORS), and descriptive analysis values (p < 0.001). Instrumentation techniques, such as compression force and shear force, along with different cooking conditions, strongly impact BMORS shear force values (R2 = 86.80%), with significance levels ranging from 0.01 to 0.001. Deboning time also substantially impacts MORS shear force values (R = 64.03%). In contrast, the effects of deboning time, bird age, and cooking conditions on descriptive sensory evaluation are minimal when compared to woody breast fillets (age of birds: R2 = 26.53%; cooking conditions: R2 = 32.57%; deboning time: R2 = 10.06%). The overall effect of bird age on chicken breast meat quality shows significant differences for the evaluated parameters (Hedges' g [95% CI] = -0.72 [0.17, 1.26], I2 = 93%, p < 0.01). The sous vide cooking method significantly affects shear force energies and sensory descriptive evaluation for woody breast fillets (Hedges' g [95% CI] = 5.30 [-50.30, 83.40], I2 = 98%, p < 0.01). These findings, with their significant implications, provide valuable insights for optimizing processing conditions in the poultry industry to reduce woody breast occurrences and enhance meat quality, instilling confidence in the robustness of the research.

Phenotyping Alfalfa (Medicago sativa L.) Root Structure Architecture via Integrating Confident Machine Learning with ResNet-18.

Background: Root system architecture (RSA) is of growing interest in implementing plant improvements with belowground root traits. Modern computing technology applied to images offers new pathways forward to plant trait improvements and selection through RSA analysis (using images to discern/classify root types and traits). However, a major stumbling block to image-based RSA phenotyping is image label noise, which reduces the accuracies of models that take images as direct inputs. To address the label noise problem, this study utilized an artificial intelligence model capable of classifying the RSA of alfalfa (Medicago sativa L.) directly from images and coupled it with downstream label improvement methods. Images were compared with different model outputs with manual root classifications, and confident machine learning (CL) and reactive machine learning (RL) methods were tested to minimize the effects of subjective labeling to improve labeling and prediction accuracies. Results: The CL algorithm modestly improved the Random Forest model's overall prediction accuracy of the Minnesota dataset (1%) while larger gains in accuracy were observed with the ResNet-18 model results. The ResNet-18 cross-population prediction accuracy was improved (~8% to 13%) with CL compared to the original/preprocessed datasets. Training and testing data combinations with the highest accuracies (86%) resulted from the CL- and/or RL-corrected datasets for predicting taproot RSAs. Similarly, the highest accuracies achieved for the intermediate RSA class resulted from corrected data combinations. The highest overall accuracy (~75%) using the ResNet-18 model involved CL on a pooled dataset containing images from both sample locations. Conclusions: ResNet-18 DNN prediction accuracies of alfalfa RSA image labels are increased when CL and RL are employed. By increasing the dataset to reduce overfitting while concurrently finding and correcting image label errors, it is demonstrated here that accuracy increases by as much as ~11% to 13% can be achieved with semi-automated, computer-assisted preprocessing and data cleaning (CL/RL).

Classification and Feature Extraction Using Supervised and Unsupervised Machine Learning Approach for Broiler Woody Breast Myopathy Detection.

Bioelectrical impedance analysis (BIA) was established to quantify diverse cellular characteristics. This technique has been widely used in various species, such as fish, poultry, and humans for compositional analysis. This technology was limited to offline quality assurance/detection of woody breast (WB); however, inline technology that can be retrofitted on the conveyor belt would be more helpful to processors. Freshly deboned (n = 80) chicken breast fillets were collected from a local processor and analyzed by hand-palpation for different WB severity levels. Data collected from both BIA setups were subjected to supervised and unsupervised learning algorithms. The modified BIA showed better detection ability for regular fillets than the probe BIA setup. In the plate BIA setup, fillets were 80.00% for normal, 66.67% for moderate (data for mild and moderate merged), and 85.00% for severe WB. However, hand-held BIA showed 77.78, 85.71, and 88.89% for normal, moderate, and severe WB, respectively. Plate BIA setup is more effective in detecting WB myopathies and could be installed without slowing the processing line. Breast fillet detection on the processing line can be significantly improved using a modified automated plate BIA.

Acceptability of Artificial Intelligence in Poultry Processing and Classification Efficiencies of Different Classification Models in the Categorisation of Breast Fillet Myopathies.

Breast meat from modern fast-growing big birds is affected with myopathies such as woody breast (WB), white striping, and spaghetti meat (SM). The detection and separation of the myopathy-affected meat can be carried out at processing plants using technologies such as bioelectrical impedance analysis (BIA). However, BIA raw data from myopathy-affected breast meat are extremely complicated, especially because of the overlap of these myopathies in individual breast fillets and the human error associated with the assignment of fillet categories. Previous research has shown that traditional statistical techniques such as ANOVA and regression, among others, are insufficient in categorising fillets affected with myopathies by BIA. Therefore, more complex data analysis tools can be used, such as support vector machines (SVMs) and backpropagation neural networks (BPNNs), to classify raw poultry breast myopathies using their BIA patterns, such that the technology can be beneficial for the poultry industry in detecting myopathies. Freshly deboned (3-3.5 h post slaughter) breast fillets (n = 100 × 3 flocks) were analysed by hand palpation for WB (0-normal; 1-mild; 2-moderate; 3-Severe) and SM (presence and absence) categorisation. BIA data (resistance and reactance) were collected on each breast fillet; the algorithm of the equipment calculated protein and fat index. The data were analysed by linear discriminant analysis (LDA), and with SVM and BPNN with 70::30: training::test data set. Compared with the LDA analysis, SVM separated WB with a higher accuracy of 71.04% for normal (data for normal and mild merged), 59.99% for moderate, and 81.48% for severe WB. Compared with SVM, the BPNN training model accurately (100%) separated normal WB fillets with and without SM, demonstrating the ability of BIA to detect SM. Supervised learning algorithms, such as SVM and BPNN, can be combined with BIA and successfully implemented in poultry processing to detect breast fillet myopathies.