Related Experiment Video
Updated: May 7, 2026
A Method for 2-Photon Imaging of Blood Flow in the Neocortex through a Cranial Window
Published on: February 25, 2008
A Deep Learning Approach for Improving Two-Photon Vascular Imaging Speeds
Annie Zhou1, Samuel A Mihelic1, Shaun A Engelmann1
1Department of Biomedical Engineering, The University of Texas at Austin, 107 W. Dean Keeton C0800, Austin, TX 78712, USA.
Abstract:
A potential method for tracking neurovascular disease progression over time in preclinical models is multiphoton fluorescence microscopy (MPM), which can image cerebral vasculature with capillary-level resolution. However, obtaining high-quality, three-dimensional images with traditional point scanning MPM is time-consuming and limits sample sizes for chronic studies. Here, we present a convolutional neural network-based (PSSR Res-U-Net architecture) algorithm for fast upscaling of low-resolution or sparsely sampled images and combine it with a segmentation-less vectorization process for 3D reconstruction and statistical analysis of vascular network structure. In doing so, we also demonstrate that the use of semi-synthetic training data can replace the expensive and arduous process of acquiring low- and high-resolution training pairs without compromising vectorization outcomes, and thus open the possibility of utilizing such approaches for other MPM tasks where collecting training data is challenging. We applied our approach to images with large fields of view from a mouse model and show that our method generalizes across imaging depths, disease states and other differences in neurovasculature. Our pretrained models and lightweight architecture can be used to reduce MPM imaging time by up to fourfold without any changes in underlying hardware, thereby enabling deployability across a range of settings.
Insights
We developed a fast AI algorithm to improve 3D imaging of brain blood vessels using multiphoton fluorescence microscopy (MPF). This method significantly speeds up image acquisition, enabling better tracking of neurovascular disease progression in preclinical models.
Area of Science:
- Neuroscience
- Biomedical Imaging
- Computational Biology
Background:
- Multiphoton fluorescence microscopy (MPF) enables high-resolution imaging of cerebral vasculature for tracking neurovascular disease.
- Traditional MPF is time-consuming, limiting sample sizes for chronic studies.
- Acquiring paired low- and high-resolution images for training AI models is challenging.
Purpose of the Study:
- To develop a fast, AI-based method for upscaling low-resolution MPF images.
- To enable efficient 3D reconstruction and analysis of vascular networks.
- To demonstrate the utility of semi-synthetic data for training AI models in MPF.
Main Methods:
- A convolutional neural network (PSSR Res-U-Net) was used for image upscaling.
- A segmentation-less vectorization process was employed for 3D reconstruction.
- Semi-synthetic training data was utilized to train the AI model.
Main Results:
- The AI algorithm significantly reduces MPF imaging time by up to fourfold.
- The method successfully reconstructs and analyzes 3D vascular networks from upscaled images.
- The approach generalizes across different imaging depths and disease states in mouse models.
- Using semi-synthetic data yields comparable results to using real image pairs.
Conclusions:
- This AI-driven approach accelerates MPF imaging for neurovascular research.
- The method facilitates more extensive preclinical studies of neurovascular diseases.
- The use of semi-synthetic data offers a practical solution for training AI in challenging imaging scenarios.
