在光显微镜中隐含的神经表示
Sophie Louise Hauser1, Johanna Brosig2, Bhargavi Murthy3
1Department Artificial Intelligence in Biomedical Engineering, Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), Germany.
Biomedical optics express
|April 18, 2024
概括
称为SIREN的深度神经网络可以预测缺失的图像平面,并在3D显微镜中修复运动工件,改善神经解剖学研究. 这项技术提高了图像采集和后处理效率.
科学领域:
- 神经科学是一个神经科学.
- 计算生物学 计算生物学
- 显微镜成像技术 显微镜成像技术
背景情况:
- 同焦点和双光子显微镜对于神经解剖学研究至关重要.
- 获取高分辨率的3D图像堆是耗时的,容易发生光漂白,并受到体内运动工件的影响.
研究的目的:
- 调查SIREN用于预测中间图像平面的适用性.
- 开发一种无监督的方法来纠正运动工件,并在3D显微镜数据中进行无效化.
主要方法:
- 使用深度神经网络,具有编码隐式神经表示 (SIREN) 的正弦激活函数.
- 应用SIREN用于预测跨多微米的中间平面.
- 开发了一个无监督的管道,用于运动工件的校正和消除噪音.
主要成果:
- 实现了对中间图像平面的准确估计.
- 完全自动和无监督的运动校正和无色图像被生成.
- 通过下游的消噪网络观察并纠正SIRENs对噪声统计的影响,通过树突脊柱恢复证明了这一点.
结论:
- 在3D显微镜中,SIREN显示出预测中间平面的前景.
- 开发的方法提供了自动,无监督的运动校正和无噪声.
- 这些进步可以导致更高效的图像采集和神经成像中优异的后处理.
相关概念视频
01:24Vision
Vision is the result of light being detected and transduced into neural signals by the retina of the eye. This information is then further analyzed and interpreted by the brain. First, light enters the front of the eye and is focused by the cornea and lens onto the retina—a thin sheet of neural tissue lining the back of the eye. Because of refraction through the convex lens of the eye, images are projected onto the retina upside-down and reversed.
01:21G-Protein Gated Ion Channels
GPCRs are primarily responsible for our sense of smell, taste, and vision. The binding of a sensory stimulus activates GPCR to stimulate effector proteins, many of which are ion channels in the sensory organs. GPCRs modulate the opening and closing of the target ion channels either directly by binding them, or by releasing second messengers that activate these channels. As ions move across the membrane, the membrane potential is altered, which induces an appropriate response.
Sensory organs,...
Sensory organs,...