Electroencephalography (EEG) is a widely used tool for monitoring brain activity, but it is often disturbed by various artifacts, such as electrooculography (EOG), electromyography (EMG), and electrocardiography (ECG), which degrade signal quality and affect subsequent analysis. Effective EEG denoising is critical for enhancing the performance of EEG-based applications, including disease diagnosis and brain-computer interfaces (BCIs). While recent deep learning (DL) approaches have shown promise in this area, they often struggle to efficiently model the temporal dependencies inherent in EEG signals, as well as to capture local contextual information simultaneously. In this work, we introduce DenoiseMamba, a novel deep learning-based EEG denoising model. The model incorporates the ConvSSD module, which integrates convolutional neural networks (CNNs) with structured state-space duality (SSD) mechanisms. This allows DenoiseMamba to capture both local and global spatiotemporal features, resulting in more effective artifact suppression. Extensive experiments on three semi-simulated datasets demonstrate that DenoiseMamba outperforms existing methods in EEG reconstruction accuracy, effectively eliminating myoelectric, electrooculographic, and electrocardiographic artifacts while preserving critical EEG signal details.