results: 研究结果表明，提posed方法可以实现实时的分子组成检测，并且维持了传统优化方法的准确性。Abstract
Spectroscopy-based imaging modalities such as near-infrared spectroscopy (NIRS) and hyperspectral imaging (HSI) represent a promising alternative for low-cost, non-invasive, and fast monitoring of functional and structural properties of living tissue. Particularly, the possibility of extracting the molecular composition of the tissue from the optical spectra in real-time deems the spectroscopy techniques as unique diagnostic tools. However, due to the highly limited availability of paired optical and molecular profiling studies, building a mapping between a spectral signature and a corresponding set of molecular concentrations is still an unsolved problem. Moreover, there are no yet established methods to streamline inference of the biochemical composition from the optical spectrum for real-time applications such as surgical monitoring. In this paper, we develop a technique for fast inference of changes in the molecular composition of brain tissue. We base our method on the Beer-Lambert law to analytically connect the spectra with concentrations and use a deep-learning approach to significantly speed up the concentration inference compared to traditional optimization methods. We test our approach on real data obtained from the broadband NIRS study of piglets' brains. The results demonstrate that the proposed method enables real-time molecular composition inference while maintaining the accuracy of traditional optimization.
摘要
Spectroscopy-based imaging modalities such as near-infrared spectroscopy (NIRS) and hyperspectral imaging (HSI) represent a promising alternative for low-cost, non-invasive, and fast monitoring of functional and structural properties of living tissue. Particularly, the possibility of extracting the molecular composition of the tissue from the optical spectra in real-time deems the spectroscopy techniques as unique diagnostic tools. However, due to the highly limited availability of paired optical and molecular profiling studies, building a mapping between a spectral signature and a corresponding set of molecular concentrations is still an unsolved problem. Moreover, there are no yet established methods to streamline inference of the biochemical composition from the optical spectrum for real-time applications such as surgical monitoring. In this paper, we develop a technique for fast inference of changes in the molecular composition of brain tissue. We base our method on the Beer-Lambert law to analytically connect the spectra with concentrations and use a deep-learning approach to significantly speed up the concentration inference compared to traditional optimization methods. We test our approach on real data obtained from the broadband NIRS study of piglets' brains. The results demonstrate that the proposed method enables real-time molecular composition inference while maintaining the accuracy of traditional optimization.Here's the translation in Traditional Chinese:这些基于spectroscopy的内部成像技术，如近赤外谱спектроскопи (NIRS) 和高分谱成像 (HSI)，具有低成本、非侵入性和快速监控生物组织功能和结构性的优点。特别是可以从光谱中提取生物组织的分子结构，使这些技术成为独特的诊断工具。然而，由于生物组织光谱对照的数据很少，因此建立光谱特征和相应的分子浓度之间的映射仍然是一个未解的问题。此外，还没有建立了将光谱特征转换为生物化学成分的方法，对于实时应用如手术监控来说，这是一个重要的障碍。在这篇论文中，我们开发了一种快速测量生物组织分子浓度变化的方法。我们基于Beer-Lambert法，使用深度学习方法来快速测量分子浓度，与传统优化方法相比，提高了速度和准确性。我们使用实验数据，从猪脑的宽带NIRS研究中获得的数据进行评估。结果显示，我们的方法可以在实时监控中提供生物化学成分的准确测量，而且与传统优化方法相比，速度更快。
X-ray dark-field via spectral propagation-based imaging
paper_authors: Jannis N. Ahlers, Konstantin M. Pavlov, Marcus J. Kitchen, Kaye S. Morgan
for: 这篇论文旨在描述一种新的黑场X射线成像技术，可以观察到不可分解的微结构。
methods: 这种技术使用了媒介频率场的模拟来恢复媒介频率场的相位信息。
results: 通过对双能X射线数据使用PBI暗场恢复算法，成功地获得了预先知道的黑场 спектраль依赖性。Abstract
Dark-field X-ray imaging is a novel modality which visualises scattering from unresolved microstructure. Current dark-field imaging techniques typically require precision optics in a stable environment. Propagation-based imaging (PBI) is an optics-free phase-contrast imaging technique that can be used to recover phase information by modelling the propagation of a diffracted wavefield. Based on the Fokker--Planck equation of X-ray imaging, we propose a dual-energy PBI approach to capture phase and dark-field effects. The equation is solved under conditions of a single-material sample with spatially slowly-varying dark-field signal, together with an a priori dark-field spectral dependence. We use single-grid dark-field imaging to fit a power law to the dark-field spectral dependence, and successfully apply the PBI dark-field retrieval algorithm to simulated and experimental dual-energy data.
摘要
黑场X射影像是一种新的显像技术，可以视化杂点不可分解的微结构。现有的黑场图像技术通常需要精炼的仪器，并在稳定的环境中进行。基于干涉图像（PBI）是一种无仪器phaseless相对幅影像技术，可以重建相对幅信息，通过模拟干涉波场的传播。基于X射影像的福克尔-普兰克方程，我们提出了双能量PBI方法，可以捕捉相对幅和黑场效应。方程在单材料样本中，空间上慢慢变化的黑场响应下解，并且使用单格黑场图像进行适应。我们成功应用PBI黑场恢复算法于实验和仿真的双能量数据。
DREAM-PCD: Deep Reconstruction and Enhancement of mmWave Radar Pointcloud
results: DREAM-PCD在重建质量和泛化性能方面胜过现有方法，并且具有优秀的实时性和可扩展性，适用于多种场景和参数。Abstract
Millimeter-wave (mmWave) radar pointcloud offers attractive potential for 3D sensing, thanks to its robustness in challenging conditions such as smoke and low illumination. However, existing methods failed to simultaneously address the three main challenges in mmWave radar pointcloud reconstruction: specular information lost, low angular resolution, and strong interference and noise. In this paper, we propose DREAM-PCD, a novel framework that combines signal processing and deep learning methods into three well-designed components to tackle all three challenges: Non-Coherent Accumulation for dense points, Synthetic Aperture Accumulation for improved angular resolution, and Real-Denoise Multiframe network for noise and interference removal. Moreover, the causal multiframe and "real-denoise" mechanisms in DREAM-PCD significantly enhance the generalization performance. We also introduce RadarEyes, the largest mmWave indoor dataset with over 1,000,000 frames, featuring a unique design incorporating two orthogonal single-chip radars, lidar, and camera, enriching dataset diversity and applications. Experimental results demonstrate that DREAM-PCD surpasses existing methods in reconstruction quality, and exhibits superior generalization and real-time capabilities, enabling high-quality real-time reconstruction of radar pointcloud under various parameters and scenarios. We believe that DREAM-PCD, along with the RadarEyes dataset, will significantly advance mmWave radar perception in future real-world applications.
摘要
Millimeter-wave (mmWave) 雷达点云提供了有前途的潜在应用，因为它在烟雾和低照明条件下具有强度。然而，现有的方法无法同时解决三大挑战在 mmWave 雷达点云重建中：损失的 Specular 信息、低角分辨率和强大的干扰和噪声。在这篇论文中，我们提出了 DREAM-PCD，一种新的框架，它将信号处理和深度学习方法结合在三个良好设计的组件中，以解决这三个挑战：非 coherent accumulation for dense points，synthetic aperture accumulation for improved angular resolution，和Real-Denoise Multiframe network for noise and interference removal。此外，DREAM-PCD 中的 causal multiframe 和 "real-denoise" 机制 significantly enhance the generalization performance。我们还介绍了 RadarEyes，最大 mmWave indoor dataset，包含超过 1,000,000 帧，其特殊设计包括两个垂直的单芯片雷达、激光和相机，这使得数据集的多样性和应用更加丰富。实验结果表明，DREAM-PCD 的重建质量胜过现有方法，并且具有优秀的普适和实时特性，可以在多种参数和场景下实现高质量的实时重建。我们认为，DREAM-PCD 和 RadarEyes 数据集将在未来实际应用中为 mmWave 雷达感知带来很大的进步。