Wang Tianshuo, Yang Huan, Zhang Chunlei, Chao Xiaohuan, Liu Mingzheng, Chen Jiahao, Liu Shuhan, Zhou Bo
College of Animal Science and Technology, Nanjing Agricultural University, Nanjing 210095, China.
Animals (Basel). 2024 Jul 27;14(15):2189. doi: 10.3390/ani14152189.
Pork belly, prized for its unique flavor and texture, is often overlooked in breeding programs that prioritize lean meat production. The quality of pork belly is determined by the number and distribution of muscle and fat layers. This study aimed to assess the number of pork belly layers using deep learning techniques. Initially, semantic segmentation was considered, but the intersection over union (IoU) scores for the segmented parts were below 70%, which is insufficient for practical application. Consequently, the focus shifted to image classification methods. Based on the number of fat and muscle layers, a dataset was categorized into three groups: three layers (n = 1811), five layers (n = 1294), and seven layers (n = 879). Drawing upon established model architectures, the initial model was refined for the task of learning and predicting layer traits from B-ultrasound images of pork belly. After a thorough evaluation of various performance metrics, the ResNet18 model emerged as the most effective, achieving a remarkable training set accuracy of 99.99% and a validation set accuracy of 96.22%, with corresponding loss values of 0.1478 and 0.1976. The robustness of the model was confirmed through three interpretable analysis methods, including grad-CAM, ensuring its reliability. Furthermore, the model was successfully deployed in a local setting to process B-ultrasound video frames in real time, consistently identifying the pork belly layer count with a confidence level exceeding 70%. By employing a scoring system with 100 points as the threshold, the number of pork belly layers in vivo was categorized into superior and inferior grades. This innovative system offers immediate decision-making support for breeding determinations and presents a highly efficient and precise method for assessment of pork belly layers.
五花肉因其独特的风味和质地而备受青睐，但在以瘦肉生产为优先的育种计划中常常被忽视。五花肉的品质由肌肉层和脂肪层的数量及分布决定。本研究旨在运用深度学习技术评估五花肉的层数。最初考虑了语义分割，但分割部分的交并比（IoU）分数低于70%，这对于实际应用来说是不够的。因此，重点转向了图像分类方法。根据脂肪层和肌肉层的数量，将数据集分为三组：三层（n = 1811）、五层（n = 1294）和七层（n = 879）。借鉴已有的模型架构，对初始模型进行了优化，以用于从五花肉的B超图像中学习和预测层数特征。在对各种性能指标进行全面评估后，ResNet18模型成为最有效的模型，训练集准确率达到了99.99%，验证集准确率为96.22%，相应的损失值分别为0.1478和0.1976。通过包括grad-CAM在内的三种可解释分析方法证实了该模型的稳健性，确保了其可靠性。此外，该模型已成功部署在本地环境中，以实时处理B超视频帧，始终以超过70%的置信水平识别五花肉的层数。通过采用以100分为阈值的评分系统，将活体五花肉的层数分为优级和劣级。这个创新系统为育种决策提供了即时的决策支持，并提出了一种高效、精确的五花肉层数评估方法。
