The paper introduces Swin UNETR, a novel architecture for semantic segmentation of brain tumors using multi-modal MRI images. The model combines a U-shaped network design with a Swin transformer as the encoder and a CNN-based decoder connected via skip connections at different resolutions. The Swin transformer encoder extracts features at five different resolutions using shifted windows for self-attention, while the decoder processes these features through skip connections. The model was evaluated on the BraTS 2021 challenge, ranking among the top-performing approaches in the validation phase and demonstrating competitive performance in the testing phase. The effectiveness of Swin UNETR is attributed to its ability to learn multi-scale contextual information and model long-range dependencies, outperforming other state-of-the-art methods in brain tumor segmentation.The paper introduces Swin UNETR, a novel architecture for semantic segmentation of brain tumors using multi-modal MRI images. The model combines a U-shaped network design with a Swin transformer as the encoder and a CNN-based decoder connected via skip connections at different resolutions. The Swin transformer encoder extracts features at five different resolutions using shifted windows for self-attention, while the decoder processes these features through skip connections. The model was evaluated on the BraTS 2021 challenge, ranking among the top-performing approaches in the validation phase and demonstrating competitive performance in the testing phase. The effectiveness of Swin UNETR is attributed to its ability to learn multi-scale contextual information and model long-range dependencies, outperforming other state-of-the-art methods in brain tumor segmentation.