首页 > AI前沿 > Physics-Informed Deep Learning for Shear Wave Speed Estimation in MR Elastography

Physics-Informed Deep Learning for Shear Wave Speed Estimation in MR Elastography

arXiv机器学习 2026-11-19 21:39 10 阅读 查看原文
用户要求作为专业的新闻排版工程师,将一段纯文本新闻正文排版成语义化的HTML片段。需要遵循一系列严格的规则:只输出HTML片段本身,无Markdown围栏,无解释;每个自然段落用`

`包裹;长文用`

/

`划分小节;列表用`
  • `,引用用`
    `,代码用`
    `,重要句子可用``;保留原文所有信息,不得增删改内容;不要输出文档级标签。
    
    首先,分析提供的正文内容。正文包含几个部分:Objective, Methods, Results, Conclusion, Significance。这显然符合用`

    `或`

    `划分小节的要求,而且每个小节对应一个自然段。由于是新闻或学术摘要,可以将每个小标题作为`

    `,下面的内容用`

    `包裹。 检查是否有重要句子需要加``。比如"Objective:"、"Methods:"、"Results:"、"Conclusion:"、"Significance:"可以加粗,或者某些关键结论如"Accurate SWS quantification is possible at acceleration factors up to 19."、"Our method significantly outperforms TV..."、"We present the first end-to-end trainable MRE reconstruction method..."可以加粗以突出。但规则说“重要句子可用”,并非必须。为了保持自然且不过度,可以将各小节标题加粗,或者将关键结论加粗。考虑到原文是学术论文摘要,标题部分已经用冒号和首字母大写,可以将这些小节标题用``包裹,或者直接作为`

    `,`

    `本身已经有加粗语义。但规则要求用`

    /

    `划分小节,那么标题应该用标题标签,内容用`

    `。 再检查是否有列表、引用、代码。原文中没有明显的列表项、引用块或代码块。所以不需要使用`

      `、`
      `、`
      `。
      
      现在规划HTML结构:
      - 每个小节用`

      `作为标题,如`

      Objective

      `,然后紧跟`

      `包含该部分内容。 - 或者将“Objective:”作为标题的一部分,如`

      Objective

      `,但原文是“Objective: Magnetic Resonance...”,如果只把“Objective”作为标题,那么“Magnetic Resonance...”就属于段落。但原文是一个连贯的句子,如果拆分可能改变结构。为了保留原文所有信息且不增删改,可以将整个“Objective: Magnetic Resonance...”作为`

      `,而小节标题用`

      `。但“Objective:”本身就是小节标识,如果用`

      Objective

      `,然后`

      Magnetic Resonance...

      `,这样是合理的,且没有增删内容,只是格式上的划分。类似地处理Methods, Results, Conclusion, Significance。 但要注意,原文中“Objective:”后面直接跟句子,没有换行。如果拆分成`

      Objective

      `和`

      Magnetic...

      `,这算增删吗?不算,只是排版,保留了所有文字信息。但严格来说,原文是“Objective: Magnetic...”,如果拆成标题和段落,标题里少了“:”和后面的内容,但信息没有丢失。更稳妥的方式是把整个小节内容放在`

      `里,然后前面加`

      `作为小节标题,标题文本用“Objective”、“Methods”等,不带冒号,或者带冒号。为了更贴近原文,`

      Objective

      `,然后段落内容就是“Magnetic Resonance Elastography...”。但原文的“Objective:”是标签,可以将其作为`

      `的文本,例如`

      Objective

      `,这样语义明确。 再检查是否需要`

      `。原文不长,用`

      `足够,或者用`

      `也可以。规则说“长文用

      /

      划分小节”,这里用`

      `合适。 关于重要句子加``,可以将各部分的关键结论加粗,如“Our approach significantly reduces NRMSE by 30% compared to TV.”、“Accurate SWS quantification is possible at acceleration factors up to 19.”、“We present the first end-to-end trainable MRE reconstruction method for estimating SWS maps directly from k-space.”这些句子是重要信息,可以加粗。但需谨慎,避免过度。规则是“可用”,不是必须。为了体现专业性,适当加粗关键结论。 现在构建HTML片段:

      Objective

      Magnetic Resonance Elastography (MRE) is a non-invasive imaging technique for mapping biomechanical properties of in vivo tissue, including shear wave speed (SWS), but involves intrinsically slow data acquisition and an ill-posed wave inversion. Instead of relying on handcrafted image priors, we propose a data-driven approach jointly combining image reconstruction and MRE inversion for robust SWS estimation from undersampled k-space data.

      Methods

      Our physics-informed reconstruction framework comprises two blocks: a model-based neural network (NN)-regularized reconstruction module and a phase-gradient inversion (k-MDEV) calculating SWS from the reconstructed images. Concatenating both blocks yields an end-to-end trainable method to estimate SWS directly from measured k-space data. We evaluated the method on retrospectively highly undersampled brain MRE data and compared it to a total variation (TV) minimization-based approach. We assessed the impact of end-to-end training (qualitative images and SWS maps as targets) versus pre-training (qualitative images as targets) and applied the method also to in vivo data.

      Results

      Our approach significantly reduces NRMSE by 30% compared to TV. End-to-end training improves SWS estimation over separate image reconstruction and SWS calculation.

      Conclusion

      Accurate SWS quantification is possible at acceleration factors up to 19. Our method significantly outperforms TV, highlighting the need for data-driven regularization in this challenging MR problem. Further, our approach successfully generalizes to in vivo data.

      Significance

      We present the first end-to-end trainable MRE reconstruction method for estimating SWS maps directly from k-space. NN-based reconstruction can enable rapid stiffness mapping for dynamic studies, functional imaging, and real-time clinical feedback.

      检查是否保留原文所有信息:是的,每个字都在,只是加了标题标签和加粗,没有增删。注意原文中“Objective:”等后面的冒号,如果标题是“Objective”,那么段落里去掉了“Objective:”这几个字符吗?没有,如果标题是`

      Objective

      `,那么原文的“Objective:”中的“Objective”被提取到标题,冒号和后面的内容在段落里?不对,原文是“Objective: Magnetic Resonance...”,如果标题是“Objective”,那么段落应该是“Magnetic Resonance...”,这样“Objective:”的冒号就丢失了,因为“Objective”作为标题,冒号被省略。但规则说“不得增删改内容”,严格来说,冒号是内容的一部分吗?作为排版,将“Objective”作为标题,可以视为对原文结构的语义化,冒号在标题中通常可以省略,但为了完全保留,可以在标题里包含冒号,如`

      Objective:

      `,这样冒号保留在标题里,段落里还是“Magnetic Resonance...”。这样更稳妥,保留了冒号。同样处理其他标题。 修改为:

      Objective:

      Magnetic Resonance Elastography...

      ...

      Methods:

      ...

      Results:

      ...

      Conclusion:

      ...

      Significance:

      ... 这样,原文的冒号保留在标题中,段落内容就是冒号之后的文字,没有增删改。完美。