Wu Mengqi, Zhang Lintao, Yap Pew-Thian, Zhu Hongtu, Liu Mingxia
Department of Radiology and Biomedical Research Imaging Center, University of North Carolina at Chapel Hill, Chapel Hill, NC 27599, USA; Joint Department of Biomedical Engineering, University of North Carolina at Chapel Hill and North Carolina State University, Chapel Hill, NC 27599, USA.
Department of Radiology and Biomedical Research Imaging Center, University of North Carolina at Chapel Hill, Chapel Hill, NC 27599, USA.
Neural Netw. 2025 Apr;184:107039. doi: 10.1016/j.neunet.2024.107039. Epub 2024 Dec 16.
Brain magnetic resonance imaging (MRI) has been extensively employed across clinical and research fields, but often exhibits sensitivity to site effects arising from non-biological variations such as differences in field strength and scanner vendors. Numerous retrospective MRI harmonization techniques have demonstrated encouraging outcomes in reducing the site effects at image level. However, existing methods generally suffer from high computational requirements and limited generalizability, restricting their applicability to unseen MRIs. In this paper, we design a novel disentangled latent energy-based style translation (DLEST) framework for unpaired image-level MRI harmonization, consisting of (a) site-invariant image generation (SIG), (b) site-specific style translation (SST), and (c) site-specific MRI synthesis (SMS). Specifically, the SIG employs a latent autoencoder to encode MRIs into a low-dimensional latent space and reconstruct MRIs from latent codes. The SST utilizes an energy-based model to comprehend global latent distribution of a target domain and translate source latent codes towards the target domain, while SMS enables MRI synthesis with a target-specific style. By disentangling image generation and style translation in latent space, the DLEST can achieve efficient style translation. Our model was trained on T1-weighted MRIs from a public dataset (with 3,984 subjects across 58 acquisition sites/settings) and validated on an independent dataset (with 9 traveling subjects scanned in 11 sites/settings) in four tasks: histogram and feature visualization, site classification, brain tissue segmentation, and site-specific structural MRI synthesis. Qualitative and quantitative results demonstrate the superiority of our method over several state-of-the-arts.
脑磁共振成像（MRI）已在临床和研究领域广泛应用，但通常对由非生物变异（如场强和扫描仪供应商差异）引起的部位效应敏感。众多回顾性MRI归一化技术在减少图像层面的部位效应方面取得了令人鼓舞的成果。然而，现有方法通常存在计算要求高和泛化性有限的问题，限制了它们对未见过的MRI的适用性。在本文中，我们设计了一种新颖的基于解缠潜在能量的风格转换（DLEST）框架，用于非配对图像层面的MRI归一化，该框架由（a）部位不变图像生成（SIG）、（b）部位特定风格转换（SST）和（c）部位特定MRI合成（SMS）组成。具体而言，SIG采用潜在自动编码器将MRI编码到低维潜在空间，并从潜在代码重建MRI。SST利用基于能量的模型理解目标域的全局潜在分布，并将源潜在代码转换为目标域，而SMS则能够以目标特定风格进行MRI合成。通过在潜在空间中解缠图像生成和风格转换，DLEST可以实现高效的风格转换。我们的模型在来自公共数据集（58个采集站点/设置中的3984名受试者）的T1加权MRI上进行训练，并在四个任务中在独立数据集（11个站点/设置中扫描的9名流动受试者）上进行验证：直方图和特征可视化、部位分类、脑组织分割以及部位特定的结构MRI合成。定性和定量结果表明我们的方法优于几种现有技术。
