Deep learning enhanced NIR-II volumetric imaging of whole mice vasculature
딥 러닝 강화 NIR-II 전체 생쥐 혈관 시스템 체적 이미지
Imagen del volumen del sistema vascular de todo el ratón NIR - II mejorada por el aprendizaje profundo
Imagerie volumétrique complète du système vasculaire de souris NIR - II améliorée par apprentissage en profondeur
Улучшенная глубинным обучением объемная визуализация кровеносной системы NIR - II для всех мышей
Sitong Wu 吴丝桐 ¹ ², Zhichao Yang 杨志超 ¹ ², Chenguang Ma 马晨光 ¹, Xun Zhang 张勋 ¹, Chao Mi 米超 ¹, Jiajia Zhou 周佳佳 ², Zhiyong Guo 郭智勇 ¹ ³, Dayong Jin 金大勇 ¹ ² ³
¹ UTS-SUSTech Joint Research Centre for Biomedical Materials & Devices, Department of Biomedical Engineering, Southern University of Science and Technology, Shenzhen 518055, China
中国 深圳 南方科技大学生物医学工程系 南方科技大学-悉尼科技大学生物医学材料与仪器联合研究中心
² Institute for Biomedical Materials & Devices, Faculty of Science, University of Technology Sydney, Ultimo, New South Wales 2007, Australia
³ Guangdong Provincial Key Laboratory of Advanced Biomaterials, Southern University of Science and Technology, Shenzhen 518055, China
中国 深圳 南方科技大学 广东省先进生物材料重点实验室
Opto-Electronic Advances, 28 April 2023

Fluorescence imaging through the second near-infrared window (NIR-II,1000–1700 nm) allows in-depth imaging. However, current imaging systems use wide-field illumination and can only provide low-contrast 2D information, without depth resolution.

Here, we systematically apply a light-sheet illumination, a time-gated detection, and a deep-learning algorithm to yield high-contrast high-resolution volumetric images. To achieve a large FoV (field of view) and minimize the scattering effect, we generate a light sheet as thin as 100.5 μm with a Rayleigh length of 8 mm to yield an axial resolution of 220 µm. To further suppress the background, we time-gate to only detect long lifetime luminescence achieving a high contrast of up to 0.45Ιcontrast. To enhance the resolution, we develop an algorithm based on profile protrusions detection and a deep neural network and distinguish vasculature from a low-contrast area of 0.07Ιcontrast to resolve the 100 μm small vessels.

The system can rapidly scan a volume of view of 75 × 55 × 20 mm3 and collect 750 images within 6 mins. By adding a scattering-based modality to acquire the 3D surface profile of the mice skin, we reveal the whole volumetric vasculature network with clear depth resolution within more than 1 mm from the skin. High-contrast large-scale 3D animal imaging helps us expand a new dimension in NIR-II imaging.
Opto-Electronic Advances_1
Opto-Electronic Advances_2
Opto-Electronic Advances_3
Opto-Electronic Advances_4
Reviews and Discussions
Hybrid bound states in the continuum in terahertz metasurfaces
Deep learning assisted variational Hilbert quantitative phase imaging
Multi-foci metalens for spectra and polarization ellipticity recognition and reconstruction
Spatio-temporal isolator in lithium niobate on insulator
Measurement of optical coherence structures of random optical fields using generalized Arago spot experiment
Specialty optical fibers for advanced sensing applications
Periodic transparent nanowires in ITO film fabricated via femtosecond laser direct writing
Chiral detection of biomolecules based on reinforcement learning
High-speed visible light communication based on micro-LED: A technology with wide applications in next generation communication
Directional high-efficiency nanowire LEDs with reduced angular color shift for AR and VR displays
Comparative analysis of NovaSeq 6000 and MGISEQ 2000 single-cell RNA sequencing data
Integrated liver proteomics and metabolomics identify metabolic pathways affected by pantothenic acid deficiency in Pekin ducks

Previous Article                                Next Article
Copyright © Hot Paper