Deep learning enhanced NIR-Ⅱ volumetric imaging of whole mice vasculature

被引：1

作者：

Sitong Wu ^{[1
,2
]}

Zhichao Yang ^{[1
,2
]}

Chenguang Ma ^{[1
]}

Xun Zhang ^{[1
]}

Chao Mi ^{[1
]}

Jiajia Zhou ^{[2
]}

Zhiyong Guo ^{[1
,3
]}

Dayong Jin ^{[1
,2
,3
]}

机构：

[1] UTS-SUSTech Joint Research Centre for Biomedical Materials & Devices, Department of Biomedical Engineering, Southern University of Science and Technology

[2] Institute for Biomedical Materials & Devices, Faculty of Science, University of Technology Sydney

[3] Guangdong Provincial Key Laboratory of Advanced Biomaterials, Southern University of Science and Technology

来源：

Opto-Electronic Advances | 2023年 / 6卷 / 04期

基金：

中国国家自然科学基金;

关键词：

D O I：

暂无

中图分类号：

TP18 [人工智能理论]; TP391.41 []; R318 [生物医学工程];

学科分类号：

080203 ; 081104 ; 0812 ; 0831 ; 0835 ; 1405 ;

摘要：

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 Fo V(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 0.45 Icontrast. 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 0.07 Icontrast to resolve the 100μm small vessels. The system can rapidly scan a volume of view of 75 × 55 × 20 mm3and collect 750 images within 6mins. 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.

引用

页码：8 / 17

页数：10