Quantitative susceptibility mapping (QSM) has demonstrated great potential in quantifying tissue susceptibility in various brain diseases. However, the intrinsic ill-posed inverse problem relating the tissue phase to the underlying susceptibility distribution affects the accuracy for quantifying tissue susceptibility. Recently, deep learning has shown promising results to improve accuracy by reducing the streaking artifacts. However, there exists a mismatch between the observed phase and the theoretical forward phase estimated by the susceptibility label. In this study, we proposed a model-based deep learning architecture that followed the STI (susceptibility tensor imaging) physical model, referred to as MoDL-QSM. Specifically, MoDL-QSM accounts for the relationship between STI-derived phase contrast induced by the susceptibility tensor terms (ki13,ki23,ki33) and the acquired single-orientation phase. The convolution neural networks are embedded into the physical model to learn a regularization term containing prior information. ki33 and phase induced by ki13 and ki23 terms were used as the labels for network training. Quantitative evaluation metrics (RSME, SSIM, and HFEN) were compared with recently developed deep learning QSM methods. The results showed that MoDL-QSM achieved superior performance, demonstrating its potential for future applications.
翻译:量化敏感度绘图(QSM)在量化各种脑疾病组织易受感染程度方面显示出巨大的潜力,然而,组织阶段与基本敏感度分布之间的内在反向问题影响了组织易感分布的准确性;最近,深层学习表明,通过减少累进文物,提高准确性取得了令人乐观的成果;然而,观察到的阶段与敏感度标签估计的理论前期阶段之间存在不匹配;在本研究中,我们提出了一个基于模型的深层次学习结构,该结构遵循了科学、技术和创新(可感知性高压成像)物理模型,称为MDL-QSM。具体地说,MDL-QSM记录了由易发性词(ki13,ki23,ki33)和获得的单向阶段之间的性传播感染阶段对比关系。进进化神经网络嵌入物理模型,学习包含先前信息的正规化术语。Ki13和ki23术语引发的阶段被用作网络培训的标签。定量评价指标(RSME,SSIM,和HFENQ)与最近开发的高级学习性质量应用方法相比,展示了未来的高级SMQ结果。