Semisupervised Deep Learning for the Detection of Foreign Materials on Poultry Meat with Near-Infrared Hyperspectral Imaging

A novel semisupervised hyperspectral imaging technique was developed to detect foreign materials (FMs) on raw poultry meat. Combining hyperspectral imaging and deep learning has shown promise in identifying food safety and quality attributes. However, the challenge lies in acquiring a large amount of accurately annotated/labeled data for model training. This paper proposes a novel semisupervised hyperspectral deep learning model based on a generative adversarial network, utilizing an improved 1D U-Net as its discriminator, to detect FMs on raw chicken breast fillets. The model was trained by using approximately 879,000 spectral responses from hyperspectral images of clean chicken breast fillets in the near-infrared wavelength range of 1000-1700 nm. Testing involved 30 different types of FMs commonly found in processing plants, prepared in two nominal sizes: 2 × 2 mm2 and 5 × 5 mm2. The FM-detection technique achieved impressive results at both the spectral pixel level and the foreign material object level. At the spectral pixel level, the model achieved a precision of 100%, a recall of over 93%, an F1 score of 96.8%, and a balanced accuracy of 96.9%. When combining the rich 1D spectral data with 2D spatial information, the FM-detection accuracy at the object level reached 96.5%. In summary, the impressive results obtained through this study demonstrate its effectiveness at accurately identifying and localizing FMs. Furthermore, the technique's potential for generalization and application to other agriculture and food-related domains highlights its broader significance.

Time evolution of microbiological quality and content of volatile compounds in chicken fillets packed using various techniques and stored under different conditions

The aim of this study was to evaluate dependence of microbiological quality of chicken fillets and profile of volatile compounds in their packages on the applied packaging technique and storage conditions. Samples packaged in either normal atmosphere (AP, air packaging, PVC overwrap), in modified atmosphere with high oxygen content (Hi-O2-MAP), or in vacuum (VP) were stored in a cold room or exposed in a display case for 8 days. Quality of the meat was determined on day 1, 3, 6, 7, and 8 of the storage or exposition time. The microbiological quality of chicken fillets was assessed by determining the number of mesophilic aerobic bacteria, lactic acid bacteria, Pseudomonas spp. bacteria, and Enterobacteriaceae family bacteria. The profile of volatile compounds in the packaging of chicken fillets was also determined. At the beginning of the storage, bacteria of all major groups were growing at similar rates regardless of the used packaging technique. However, at the end of the period, the growth dynamic was diversified. The profile of the volatile compounds did not depend on the storage or exposition time regardless of the storage conditions and/or the packaging technique. The results of this study indicate that there is a potential to gain understanding of spoilage of packed chicken meat through the analysis of volatile compounds in association with microbiological analysis. However, future research should be based on standardized material with similar bacterial load.

Influence of storage and packaging method on chicken breast meat chemical composition and fat oxidation

The aim of this study was to determine the influence of storage conditions and packaging methods on chicken breast meat chemical composition and fat oxidation. In this study, chicken breasts available in retail sale were used for evaluation. The meat packed by three different methods (air packaging-AP, modified atmosphere packaging-MAP, and vacuum packaging-VP) was stored in a cooling room or a commercial display case for 9 D and tested for basic chemical composition, lipid oxidation (TBARS), and fatty acid composition. Meat in MAP during storage in the cooling room was characterized by higher (P ≤ 0.05) TBARS values as compared to meat packaged in AP and VP, respectively. The highest share in the fatty acid profile in chicken breasts was demonstrated by monounsaturated fatty acid, including cis C18:1 (n9 + n11) acid in the range from 31.86 to 34.66%. A high share of polyunsaturated acids was observed, including linoleic (C18:2 cis, cis) acid from 24.50 to 31.22% of all fatty acids. The simple relationship between the changes in the profile of fatty acids in meat packaged using different methods and in storage time was not determined, likely due to the variability of the composition of fatty acids in chicken breasts depending on the sample and the general low level of fat found in the meat.

Effect of high-oxygen and oxygen-free modified atmosphere packaging on the spoilage process of poultry breast fillets

A comparison was made of the effect of atmospheres containing high oxygen (70% O2 and 30% CO2) or high nitrogen (70% N2 and 30% CO2) on the spoilage process during storage (at 4°C) of poultry fillets. Four samples of each gas atmosphere were analyzed at 7 sample points during storage. For this analysis, the growth of typical spoilage organisms (Brochothrix thermosphacta, Pseudomonas spp., Enterobacteriaceae, and Lactobacilli spp.) and total viable count (TVC) were analyzed and modeled by using the Gompertz function. Sensory analyses of the poultry samples were carried out by trained sensory panelists to analyze color, odor, texture, drip loss, and general appearance. The composition of the spoilage flora differed between the oxygen-free atmosphere and the high-oxygen atmosphere. Anaerobic conditions favored the growth of Lactobacilli spp., whereas aerobic gas composition favored the growth of B. thermosphacta. However, no significant difference (P<0.05) in TVC and sensory parameters were observed for poultry samples stored under a high-oxygen atmosphere in comparison to a high-nitrogen atmosphere. These results indicate that high-oxygen packaging has no additional beneficial effect on the quality maintenance and shelf life of fresh poultry fillets.