PIMFP: An accurate tool for the prediction of intramuscular fat percentage in live pigs using ultrasound images based on deep learning

Abstract

Intramuscular fat (IMF) percentage is the proportion of fat between the muscle fibers of the loin eye, which contributes significantly to the flavor and tenderness of the pork. Traditional IMF percentage is measured after slaughter, which requires a high cost, and the slaughtered pig with high IMF percentage can not be directly retained for breeding. Instead of slaughter, using ultrasound images to predict IMF percentage has been gradually proposed as an alternative measurement. However, due to the high cost of dataset construction and limited feature extraction capability of traditional image analysis methods, there is still a lack of an accurate and robust method based on the large-scale dataset for predicting IMF percentage. Here, to establish an accurate model for non-invasive prediction of IMF percentage in pigs, a total number of 4,552 ultrasound images and their corresponding IMF percentage of 945 pigs are collected in this study. We proposed a general-purpose model, PIMFP, to accurately predict IMF percentage based on the deep convolutional neural network. The PIMFP model comprises three primary modules: image preprocessing, feature extraction, and IMF percentage prediction. The preprocessing procedures for the raw ultrasound images include channel conversion, region of interest selection, and contrast enhancement. The feature extraction module characterizes the preprocessed images using the residual neural network as the backbone to extract features. The image features are then delivered to the IMF percentage prediction module depending on the fully connected layer. Our proposed model exhibits significant advantages over existing models in predictive performance, computational speed, classification ability, robustness, and interpretability. For easier use, we also provide a user-friendly web tool for predicting IMF percentage automatically in a single step. In conclusion, our study demonstrates the power of the PIMFP model for predicting IMF percentage, which has great potential in future breeding and highlights the application of artificial intelligence algorithms in livestock.