提出新型MRI重建模型，兼顾高频细节与跨模态泛化能力。
SHFormer: Dynamic Spectral Filtering Convolutional Neural Network and High-pass Kernel Generation Transformer for Adaptive MRI Reconstruction
- 通过动态高通核生成机制增强高频信息建模能力。
- 在未见数据上实现约1 dB的PSNR提升和0.01的SSIM增益。
- 适合需要高保真重建与多模态泛化的医学影像研究者。
注意力机制（AM）能聚焦关键信息并捕捉远距离像素间的关联，适用于加速MRI重建，因其成像过程涉及傅里叶域测量，影响图像表示具有非局部性。然而，基于AM的模型更擅长捕捉低频信息，对高频表征能力有限，导致重建结果趋于平滑；且在多模态MRI数据中需针对不同模式重新训练，因其知识局限于局部上下文变化，难以捕获跨异构域的可迁移特征。为此，我们提出一种基于神经调制的判别性多谱注意力机制，实现可扩展的MRI重建，具备（i）传播上下文感知的高频细节以实现高质量重建，（ii）在异构多模态MRI数据中捕获可复用特征的能力。所提网络由谱滤波卷积神经网络（用于提取模式特异性可迁移特征）和动态高通核生成变压器（专注高频细节）组成。我们在监督与自监督学习、基于扩散模型的训练、同分布与开放集泛化以及可解释性分析等方面进行了对比评估。该方法在未见场景下实现最高约1 dB的PSNR提升和约0.01的SSIM增益，具备可扩展性和高重建质量。
原文摘要 · Abstract (English)
Attention Mechanism (AM) selectively focuses on essential information for imaging tasks and captures relationships between distant pixel neighborhoods to compute feature representations. Accelerated MRI reconstruction benefits from AM, as the imaging process involves Fourier domain measurements that influence image representation non-locally. However, AM-based models are more adept at capturing low-frequency information with limited capacity for high-frequency representations, restricting models to smooth reconstruction. Additionally, AM-based models need mode-specific retraining for multimodal MRI data, as their knowledge is restricted to local contextual variations that may be inadequate to capture transferable features across heterogeneous domains. To address these challenges, we propose a neuromodulation-based discriminative multi-spectral AM for scalable MRI reconstruction that can (i) propagate context-aware high-frequency details for high-quality reconstruction, and (ii) capture features reusable across deviated unseen domains in multimodal MRI. The proposed network consists of a spectral filtering CNN to capture mode-specific transferable features and a dynamic high-pass kernel generation transformer focusing on high-frequency details. We evaluate our model on comparative studies in supervised and self-supervised learning, diffusion model-based training, closed-set and open-set generalization under heterogeneous MRI data, and interpretation-based analysis. Our method offers scalable, high-quality reconstruction with best improvement margins of ~1 dB in PSNR and ~0.01 in SSIM under unseen scenarios. Code: https://github.com/sriprabhar/SHFormer
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。