DEEP-squared:深度学习驱动的De-scattering与激发模式的扩散
Navodini Wijethilake1,2, Mithunjha Anandakumar1, Cheng Zheng3,4
1Center for Advanced Imaging, Faculty of Arts and Sciences, Harvard University, Cambridge, MA, USA.
Light, science & applications
|September 13, 2023
概括
研究人员开发了DEEP2,这是一种深度学习模型,可以提高深层组织成像速度. 这种方法显著提高了非线性光学显微镜的吞吐量,使生物结构在体内可更快地可视化.
科学领域:
- 生物医学光学 生物医学光学
- 显微镜的使用方法
- 深度学习 (Deep Learning) 是一种深度学习.
背景情况:
- 非线性光学显微镜,特别是点扫描多光子显微镜,在体内深层组织成像中面临吞吐量限制.
- 现有的广场成像模式更快,但通常仅限于光学清除或薄型标本.
- 之前的广场方法,如DEEP (De-scattering with Excitation Patterning) 编码了空间信息,但需要数百次模式激发来深度去散射.
研究的目的:
- 推出DEEP2,一个基于深度学习的模型,旨在加速深层组织成像中的脱散.
- 显著提高广场非线性光学显微镜的吞吐量.
- 为了使更深处的生物结构能够更快地进行体内成像.
主要方法:
- 开发DEEP2,一种使用模式式多光子激发的深度学习模型.
- 与以前的方法相比,训练和应用模型来消除图像的散射,使用的模式激发明显减少.
- 通过数值模拟和实验成像研究进行验证,包括体内小鼠模型.
主要成果:
- DEEP2成功地使用仅几十个模式激发来消除图像的散射,这比以前所需的数百个减少了.
- 与原来的DEEP方法相比,实现了几乎一个数量级的吞吐量改善.
- 在活体小鼠中,被证明有效的皮质血管成像可达4个分散长度的深度.
结论:
- DEEP2代表了深层组织成像技术的重大进步,克服了传统方法的吞吐量限制.
- 深度学习方法可以实现高效的分散,使广场非线性光学显微镜在体内应用中变得更加实用.
- 这项技术有望加速和更深入地可视化生物体中的生物过程.
相关概念视频
Double Resonance Techniques: Overview
241
Double resonance techniques in Nuclear Magnetic Resonance (NMR) spectroscopy involve the simultaneous application of two different frequencies or radiofrequency pulses to manipulate and observe two distinct nuclear spins. One important application of double resonance is spin decoupling, which selectively suppresses coupling with one type of nucleus while observing the NMR signal from another nucleus, simplifying the spectrum and enhancing resolution.
Spin decoupling is usually achieved by...
Spin decoupling is usually achieved by...
241
Deconvolution
186
Deconvolution, also known as inverse filtering, is the process of extracting the impulse response from known input and output signals. This technique is vital in scenarios where the system's characteristics are unknown, and they must be inferred from the observable signals.
Deconvolution involves several mathematical techniques to derive the impulse response. One common approach is polynomial division. In this method, the input and output sequences are treated as coefficients of...
Deconvolution involves several mathematical techniques to derive the impulse response. One common approach is polynomial division. In this method, the input and output sequences are treated as coefficients of...
186


