Improving the efficiency, economic viability, and environmental sustainability of beef cattle production requires tools to identify resource-efficient animals. Validated tools to measure, monitor, and verify individual feed and water intake are needed. Here, we verify the validity of the Vytelle In-Pen Weighing Position to passively collect daily full body weights and assess the use of an integrated flow meter with a commercial waterer as a tool to measure daily water intake. This study involved 103 bulls (40 Charolais and 63 Angus) and 54 heifers (25 Charolais and 29 Angus). These animals were fed in a facility with feed intake nodes, In-Pen Weighing, and metered waterers. Body weights collected on the chute scale and total water usage measured by a residential water meter were used to evaluate body weight and water intake measured at the In-Pen Weighing Positions. We confirmed that In-Pen Weighing is highly correlated to chute weighing (Spearman’s correlation coefficient, ρ = 0.99, p < 0.0001). We observed high correlation of total water use measured at the In-Pen Weighing units with the facility’s total water use (ρ = 0.9999, p < 0.0001). This validates the accuracy of the in-pen water meters, but not the precision of applying water consumption to individual animals. The use of such passive monitoring equipment has the potential to help improve the sustainability of animal agriculture.

Early detection of breast cancer commonly relies on imaging technologies such as ultrasound, mammography and MRI. Among these, breast ultrasound is widely used by radiologists to identify and assess lesions. In this study, we developed image segmentation techniques and multiclass classification artificial intelligence (AI) tools based on pretrained models to segment lesions and detect breast cancer. The proposed workflow includes both the development of segmentation models and development of a series of classification models to classify ultrasound images as normal, benign or malignant. The pretrained models were trained and evaluated on the Breast Ultrasound Images (BUSI) dataset, a publicly available collection of grayscale breast ultrasound images with corresponding expert-annotated masks. For segmentation, images and ground-truth masks were used to pretrained encoder (ResNet18, EfficientNet-B0 and MobileNetV2)–decoder (U-Net, U-Net++ and DeepLabV3) models, including the DeepLabV3 architecture integrated with a Frequency-Domain Feature Enhancement Module (FEM). The proposed FEM improves spatial and spectral feature representations using Discrete Fourier Transform (DFT), GroupNorm, dropout regularization and adaptive fusion. For classification, each image was assigned a label (normal, benign or malignant). Optuna, an open-source software framework, was used for hyperparameter optimization and for the testing of various pretrained models to determine the best encoder–decoder segmentation architecture. Five different pretrained models (ResNet18, DenseNet121, InceptionV3, MobielNetV3 and GoogleNet) were optimized for multiclass classification. DeepLabV3 outperformed other segmentation architectures, with consistent performance across training, validation and test images, with Dice Similarity Coefficient (DSC, a metric describing the overlap between predicted and true lesion regions) values of 0.87, 0.80 and 0.83 on training, validation and test sets, respectively. ResNet18:DeepLabV3 achieved an Intersection over Union (IoU) score of 0.78 during training, while ResNet18:U-Net++ achieved the best Dice coefficient (0.83) and IoU (0.71) and area under the curve (AUC, 0.91) scores on the test (unseen) dataset when compared to other models. However, the proposed Resnet18: FrequencyAwareDeepLabV3 (FADeepLabV3) achieved a DSC of 0.85 and an IoU of 0.72 on the test dataset, demonstrating improvements over standard DeepLabV3. Notably, the frequency-domain enhancement substantially improved the AUC from 0.90 to 0.98, indicating enhanced prediction confidence and clinical reliability. For classification, ResNet18 produced an F1 score—a measure combining precision and recall—of 0.95 and an accuracy of 0.90 on the training dataset, while InceptionV3 performed best on the test dataset, with an F1 score of 0.75 and accuracy of 0.83. We demonstrate a comprehensive approach to automate the segmentation and multiclass classification of breast cancer ultrasound images into benign, malignant or normal transfer learning models on an imbalanced ultrasound image dataset.

Breast ultrasound image segmentation and classification are the two crucial steps for early diagnosis of cancer. In this work we developed a breast cancer segmentation and multiclass classification artificial intelligence tools based on pretrained models. The proposed workflow includes both the development of a segmentation model architecture and second the development of a series of classification models to classify the ultrasound greyscale images into normal, benign or malignant. The training and testing of the pretrained models were performed using the Breast Ultrasound Images (BUSI dataset). For the image segmentation task, the models were trained on the images while using masks as target variable. In the multiclass classification, each image was provided with accurate label “benign”, “normal” or “malignant” and used to train a multiclass classifier. Optuna was used for hyperparameter optimization and for the testing of various pretrained models to determine the best encoder (ResNet18, EfficientNet-B0 & MobileNetV2)-decoder (U-Net, U-Net++, DeepLabV3) image segmentation architecture. For multiclass classification, five different pretrained models (ResNet18, DenseNet121, InceptionV3, MobielNetV3, GoogleNet) were optimized and tested for their ability to classify breast cancer images. The developed Image segmentation models performed well in terms of delineating the lesion in the breast ultrasound images. DeepLabV3 outperformed other segmentation architectures with consistent performance across train, validation and test images with Dice Coefficients of 0.87, 0.80 and 0.83 respectively. ResNet18:DeepLabV3 achieved an Intersection over Union score of 0.78 during training. ResNet18: U-net++ achieved best Dice coefficient (0.83) and IoU (0.71) and AUC score of 0.91 on the test (unseen) dataset when compared to other models. For classification of breast cancer images, ResNet18 achieved an F1 score of 0.95 and an accuracy of 0.90 on the train dataset, while InceptionV3 outperformed other models on the test dataset with an F1 score of 0.75 and accuracy of 0.83. We demonstrate a comprehensive approach to automate the image segmentation and multiclass classification of breast cancer ultrasound images into benign, malignant or normal using transfer learning models on an imbalanced ultrasound image dataset.

Variation in individual animal feed intake is influenced by factors such as bunk management, digestive physiology, social hierarchy, and health status. While previous research has primarily examined feeding behavior in cattle offered high-concentrate diets, limited information exists regarding these relationships in high-forage systems. Residual Feed Intake (RFI), defined as the difference between an animal’s actual and expected feed intake based on metabolic mid-test body weight and average daily gain, serves as a key measure of feed efficiency. Animals with negative RFI values are classified as more efficient, whereas those with positive values are less efficient. This study investigated associations between feeding behavior and feed efficiency in yearling purebred Angus bulls (n = 232) and heifers (n = 58) consuming forage-based diets using a Vytelle feeding system. Upon arrival, bulls averaged 350.3 ± 3.6 kg and heifers averaged 287.5 ± 5.0 kg, with a subsequent 14-day acclimation followed by a 49-day ad libitum feeding period. In bulls, RFI was positively correlated with bunk visits (r = 0.34, p < 0.0001) and negatively correlated with duration (r = −0.16, p = 0.0124). In heifers, daily visits were negatively correlated with intake (r = −0.88, p < 0.0001), and RFI was negatively associated with RADG (r = −0.53, p < 0.0001).