Alsubaie Mohammed, Perera Sirani M, Gu Linxia, Subasi Sean B, Andronesi Ovidiu C, Li Xianqi
Department of Mathematics, College of Khurma University College, Taif Univeristy, Taif, 21944, Saudi Arabia.
Department of Mathematics and Systems Engineering, Florida Institute of Technology, Melbourne, FL, 32901, USA.
J Imaging Inform Med. 2025 Sep 2. doi: 10.1007/s10278-025-01652-x.
High-resolution magnetic resonance spectroscopic imaging (MRSI) plays a crucial role in characterizing tumor metabolism and guiding clinical decisions for glioma patients. However, due to inherently low metabolite concentrations and signal-to-noise ratio (SNR) limitations, MRSI data are often acquired at low spatial resolution, hindering accurate visualization of tumor heterogeneity and margins. In this study, we propose a novel deep learning framework based on conditional denoising diffusion probabilistic models for super-resolution reconstruction of MRSI, with a particular focus on mutant isocitrate dehydrogenase (IDH) gliomas. The model progressively transforms noise into high-fidelity metabolite maps through a learned reverse diffusion process, conditioned on low-resolution inputs. Leveraging a Self-Attention UNet backbone, the proposed approach integrates global contextual features and achieves superior detail preservation. On simulated patient data, the proposed method achieved Structural Similarity Index Measure (SSIM) values of 0.956, 0.939, and 0.893; Peak Signal-to-Noise Ratio (PSNR) values of 29.73, 27.84, and 26.39 dB; and Learned Perceptual Image Patch Similarity (LPIPS) values of 0.025, 0.036, and 0.045 for upsampling factors of 2, 4, and 8, respectively, with LPIPS improvements statistically significant compared to all baselines ( ). We validated the framework on in vivo MRSI from healthy volunteers and glioma patients, where it accurately reconstructed small lesions, preserved critical textural and structural information, and enhanced tumor boundary delineation in metabolic ratio maps, revealing heterogeneity not visible in other approaches. These results highlight the promise of diffusion-based deep learning models as clinically relevant tools for noninvasive, high-resolution metabolic imaging in glioma and potentially other neurological disorders.
高分辨率磁共振波谱成像（MRSI）在表征肿瘤代谢和指导胶质瘤患者的临床决策方面发挥着关键作用。然而，由于代谢物浓度本身较低以及信噪比（SNR）的限制，MRSI数据通常在低空间分辨率下采集，这阻碍了肿瘤异质性和边界的精确可视化。在本研究中，我们提出了一种基于条件去噪扩散概率模型的新型深度学习框架，用于MRSI的超分辨率重建，特别关注突变型异柠檬酸脱氢酶（IDH）胶质瘤。该模型通过学习到的反向扩散过程，以低分辨率输入为条件，逐步将噪声转换为高保真代谢物图谱。利用自注意力UNet骨干网络，所提出的方法整合了全局上下文特征并实现了卓越的细节保留。在模拟患者数据上，对于2、4和8的上采样因子，所提出的方法分别实现了结构相似性指数测量（SSIM）值为0.956、0.939和0.893；峰值信噪比（PSNR）值为29.73、27.84和26.39 dB；以及学习感知图像块相似性（LPIPS）值为0.025、0.036和0.045，与所有基线相比，LPIPS的改进具有统计学意义（ ）。我们在健康志愿者和胶质瘤患者的体内MRSI上验证了该框架，它能够准确重建小病变，保留关键的纹理和结构信息，并增强代谢率图中的肿瘤边界描绘，揭示了其他方法中不可见的异质性。这些结果突出了基于扩散的深度学习模型作为胶质瘤及潜在其他神经系统疾病中非侵入性高分辨率代谢成像的临床相关工具的前景。
