Accurate classification of knee X-rays across diverse hardware remains a significant challenge due to domain shifts induced by varying scanner specifications, acquisition protocols, and post-processing software. This study investigates out-of-distribution (OOD) generalization techniques to improve the classification of knee calcium deposition across seven distinct X-ray scanners. We evaluated six OOD algorithms, including Empirical Risk Minimization (ERM), SagNet, GroupDRO, Mixup, Adaptive Risk Minimization (ARM), and Invariant Risk Minimization (IRM) to assess the robustness of Vision Transformer-based (DINOv2) versus convolutional (ResNet50) feature extractors within a supervised learning framework. Our experimental results demonstrate that DINOv2-extracted features generalized significantly better to unseen scanners than ResNet50. Among the tested OOD algorithms, SagNet emerged as the most robust approach, achieving 92.6% accuracy with std of \(\pm 0.20\) and a p-value of \(2.9\times 10^{-10}\) across the seven scanners by effectively decoupling anatomical content from scanner-specific style. In contrast, IRM exhibited instability across training and testing domains, yielding 85.1% accuracy with std of ±6.71 and a p-value of 0.667 under identical hyperparameter settings, likely due to the difficulty of identifying truly invariant features across medical imaging domains. These findings underscore how self-supervised feature learning significantly enhances robustness against distribution shifts compared to standard convolutional models. By leveraging domain generalization, we provide a scalable foundation for manufacturer-independent classifiers, facilitating more reliable and equitable performance across diverse X-ray imaging platforms.