Deep learning has been extensively applied in medical image reconstruction, where Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) represent the predominant paradigms, each possessing distinct advantages and inherent limitations: CNNs exhibit linear complexity with local sensitivity, whereas ViTs demonstrate quadratic complexity with global sensitivity. The emerging Mamba has shown superiority in learning visual representation, which combines the advantages of linear scalability and global sensitivity. In this study, we introduce MambaMIR, an Arbitrary-Masked Mamba-based model with wavelet decomposition for joint medical image reconstruction and uncertainty estimation. A novel Arbitrary Scan Masking (ASM) mechanism “masks out” redundant information to introduce randomness for further uncertainty estimation. Compared to the commonly used Monte Carlo (MC) dropout, our proposed MC-ASM provides an uncertainty map without the need for hyperparameter tuning and mitigates the performance drop typically observed when applying dropout to low-level tasks. For further texture preservation and better perceptual quality, we employ the wavelet transformation into MambaMIR and explore its variant based on the Generative Adversarial Network, namely MambaMIR-GAN. Comprehensive experiments have been conducted for multiple representative medical image reconstruction tasks, demonstrating that the proposed MambaMIR and MambaMIR-GAN outperform other baseline and state-of-the-art methods in different reconstruction tasks, where MambaMIR achieves the best reconstruction fidelity and MambaMIR-GAN has the best perceptual quality. In addition, our MC-ASM provides uncertainty maps as an additional tool for clinicians, while mitigating the typical performance drop caused by the commonly used dropout.

中文翻译：

---

使用 Monte Carlo 任意掩蔽曼巴增强医学图像重建中的全局灵敏度和不确定性量化


深度学习已广泛应用于医学图像重建，其中卷积神经网络 （CNN） 和视觉转换器 （ViT） 代表了主要范式，每种模式都具有明显的优势和固有的局限性：CNN 表现出具有局部敏感性的线性复杂性，而 ViT 表现出具有全局敏感性的二次复杂性。新兴的 Mamba 在学习视觉表示方面表现出了优越性，它结合了线性可扩展性和全局敏感性的优点。在这项研究中，我们介绍了 MambaMIR，这是一种基于任意掩蔽的 Mamba 模型，具有小波分解功能，用于联合医学图像重建和不确定性估计。一种新的任意扫描掩码 （ASM） 机制“掩盖”了冗余信息，以引入随机性，以便进一步估计不确定性。与常用的蒙特卡洛 （MC） dropout 相比，我们提出的 MC-ASM 提供了一个不确定性图，而无需超参数调整，并减轻了在将 dropout 应用于低级任务时通常观察到的性能下降。为了进一步保留纹理和更好的感知质量，我们将小波变换引入 MambaMIR，并基于生成对抗网络（即 MambaMIR-GAN）探索其变体。已经对多个具有代表性的医学图像重建任务进行了全面的实验，表明所提出的 MambaMIR 和 MambaMIR-GAN 在不同的重建任务中优于其他基线和最先进的方法，其中 MambaMIR 实现了最佳的重建保真度，而 MambaMIR-GAN 具有最好的感知质量。 此外，我们的 MC-ASM 还为临床医生提供了不确定性图作为附加工具，同时减轻了由常用的 dropout 引起的典型性能下降。