基于2D监督的生物医学体数据超分辨率
Super-resolution of biomedical volumes with 2D supervision
AI总结：
针对3D体显微技术临床应用的成像慢、z轴分辨率低、高质量体数据不足问题，提出利用2D高分辨率数据训练的掩膜切片扩散超分辨率方法MSDSR，借助生物标本空间维度数据分布等价性实现跨平面泛化，在SRH场景中通过新指标SliceFID验证其性能优于基线，推动3D体显微的临床应用。
摘要：
体生物医学显微技术有望提升从临床组织标本中提取的诊断信息，同时提高人类病理学家和计算病理学模型的诊断准确率。遗憾的是，将三维（3D）体显微技术应用于临床医学仍存在诸多障碍，包括成像时间长、深度/z轴分辨率差，以及高质量体数据数量不足。利用海量高分辨率2D显微数据，我们提出了用于超分辨率的掩膜切片扩散（masked slice diffusion for super-resolution, MSDSR）方法，该方法利用了生物标本所有空间维度上数据生成分布的内在等价性。这一固有特性使得在某一平面（如XY平面）的高分辨率图像上训练的超分辨率模型，能够有效泛化到其他平面（XZ、YZ平面），打破了传统方法对方向的依赖。我们重点将MSDSR应用于受激拉曼组织学（stimulated Raman histology, SRH）——这是一种用于生物标本分析和术中诊断的光学成像模式，特点是能快速采集高分辨率2D图像，但光学z切片速度慢且成本高。为评估MSDSR的效能，我们提出了一种新的性能指标SliceFID，并通过大量评估证明MSDSR的性能优于基线模型。研究结果表明，MSDSR不仅能显著提升3D体数据的质量和分辨率，还解决了阻碍3D体显微技术在临床诊断和生物医学研究中更广泛应用的主要障碍。
英文摘要：
Volumetric biomedical microscopy has the potential to increase the diagnostic information extracted from clinical tissue specimens and improve the diagnostic accuracy of both human pathologists and computational pathology models. Unfortunately, barriers to integrating 3-dimensional (3D) volumetric microscopy into clinical medicine include long imaging times, poor depth / z-axis resolution, and an insufficient amount of high-quality volumetric data. Leveraging the abundance of high-resolution 2D microscopy data, we introduce masked slice diffusion for super-resolution (MSDSR), which exploits the inherent equivalence in the data-generating distribution across all spatial dimensions of biological specimens. This intrinsic characteristic allows for super-resolution models trained on high-resolution images from one plane (e.g., XY) to effectively generalize to others (XZ, YZ), overcoming the traditional dependency on orientation. We focus on the application of MSDSR to stimulated Raman histology (SRH), an optical imaging modality for biological specimen analysis and intraoperative diagnosis, characterized by its rapid acquisition of high-resolution 2D images but slow and costly optical z-sectioning. To evaluate MSDSR's efficacy, we introduce a new performance metric, SliceFID, and demonstrate MSDSR's superior performance over baseline models through extensive evaluations. Our findings reveal that MSDSR not only significantly enhances the quality and resolution of 3D volumetric data, but also addresses major obstacles hindering the broader application of 3D volumetric microscopy in clinical diagnostics and biomedical research.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
