Deep learning-based artificial intelligence diagnostic models rely heavily on high-quality and exhaustively annotated data for algorithm training, but they are affected by noise label information. To enhance the robustness of the model and prevent memorization of noise labels, this study proposes a noise label image classification method based on multi-dimensional contrastive learning. This method can effectively integrate multi-dimensional contrastive learning and semi-supervised learning to combat label noise. Specifically, the proposed method consists of three carefully designed components. A mixed feature embedding module with a momentum update mechanism is designed to extract abstract distributed feature representations using mixed augmented images as input. Simultaneously, the study adjusts the features in the feature space from different dimensions by employing a multi-dimensional contrastive learning module, which combines instance contrastive learning and inter-class contrastive learning. Additionally, a noise-robust loss function is utilized to ensure that samples with correct labels dominate the learning process. Experiments conducted on CIFAR-10 and CIFAR-100 datasets demonstrate that the proposed method achieves better results than existing methods.