ABSTRACT
In the food industry, assessing the quality of poultry carcasses during processing is a crucial step. This study proposes an effective approach for automating the assessment of carcass quality without requiring skilled labor or inspector involvement. The proposed system is based on machine learning (ML) and computer vision (CV) techniques, enabling automated defect detection and carcass quality assessment. To this end, an end-to-end framework called CarcassFormer is introduced. It is built upon a Transformer-based architecture designed to effectively extract visual representations while simultaneously detecting, segmenting, and classifying poultry carcass defects. Our proposed framework is capable of analyzing imperfections resulting from production and transport welfare issues, as well as processing plant stunner, scalder, picker, and other equipment malfunctions. To benchmark the framework, a dataset of 7,321 images was initially acquired, which contained both single and multiple carcasses per image. In this study, the performance of the CarcassFormer system is compared with other state-of-the-art (SOTA) approaches for both classification, detection, and segmentation tasks. Through extensive quantitative experiments, our framework consistently outperforms existing methods, demonstrating re- markable improvements across various evaluation metrics such as AP, AP@50, and AP@75. Furthermore, the qualitative results highlight the strengths of CarcassFormer in capturing fine details, including feathers, and accurately localizing and segmenting carcasses with high precision. To facilitate further research and collaboration, the source code and trained models will be made publicly available upon acceptance.
Subject(s)
Chickens , Animals , Machine Learning , Meat/analysis , Image Processing, Computer-Assisted/methods , Poultry , AbattoirsABSTRACT
Cardiopulmonary bypass (CPB) causes systemic inflammation and endothelial glycocalyx damage. Hydrogen has anti-oxidant and anti-inflammatory properties; therefore, we hypothesized that hydrogen would alleviate endothelial glycocalyx damage caused by CPB. Twenty-eight male Sprague-Dawley rats were randomly divided into four groups (n = 7 per group), as follows: sham, control, 2% hydrogen, and 4% hydrogen. The rats were subjected to 90 minutes of partial CPB followed by 120 minutes of observation. In the hydrogen groups, hydrogen was administered via the ventilator and artificial lung during CPB, and via the ventilator for 60 minutes after CPB. After observation, blood collection, lung extraction, and perfusion fixation were performed, and the heart, lung, and brain endothelial glycocalyx thickness was measured by electron microscopy. The serum syndecan-1 concentration, a glycocalyx component, in the 4% hydrogen group (5.7 ± 4.4 pg/mL) was lower than in the control (19.5 ± 6.6 pg/mL) and 2% hydrogen (19.8 ± 5.0 pg/mL) groups (P < 0.001 for each), but it was not significantly different from the sham group (6.2 ± 4.0 pg/mL, P = 0.999). The endothelial glycocalyces of the heart and lung in the 4% hydrogen group were thicker than in the control group. The 4% hydrogen group had lower inflammatory cytokine concentrations (interleukin-1ß and tumor necrosis factor-α) in serum and lung tissue, as well as a lower serum malondialdehyde concentration, than the control group. The 2% hydrogen group showed no significant difference in the serum syndecan-1 concentration compared with the control group. However, non-significant decreases in serum and lung tissue inflammatory cytokine concentrations, as well as in serum malondialdehyde concentration, were observed. Administration of 4% hydrogen via artificial and autologous lungs attenuated endothelial glycocalyx damage caused by partial CPB in rats, which might be mediated by the anti-inflammatory and anti-oxidant properties of hydrogen.