1
|
Zhou A, Mihelic SA, Engelmann SA, Tomar A, Dunn AK, Narasimhan VM. A Deep Learning Approach for Improving Two-Photon Vascular Imaging Speeds. Bioengineering (Basel) 2024; 11:111. [PMID: 38391597 PMCID: PMC10886311 DOI: 10.3390/bioengineering11020111] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/07/2023] [Revised: 01/09/2024] [Accepted: 01/10/2024] [Indexed: 02/24/2024] Open
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.
Collapse
Affiliation(s)
- Annie Zhou
- Department of Biomedical Engineering, The University of Texas at Austin, 107 W. Dean Keeton C0800, Austin, TX 78712, USA
| | - Samuel A Mihelic
- Department of Biomedical Engineering, The University of Texas at Austin, 107 W. Dean Keeton C0800, Austin, TX 78712, USA
| | - Shaun A Engelmann
- Department of Biomedical Engineering, The University of Texas at Austin, 107 W. Dean Keeton C0800, Austin, TX 78712, USA
| | - Alankrit Tomar
- Department of Biomedical Engineering, The University of Texas at Austin, 107 W. Dean Keeton C0800, Austin, TX 78712, USA
| | - Andrew K Dunn
- Department of Biomedical Engineering, The University of Texas at Austin, 107 W. Dean Keeton C0800, Austin, TX 78712, USA
| | - Vagheesh M Narasimhan
- Department of Integrative Biology, The University of Texas at Austin, 2415 Speedway C0930, Austin, TX 78712, USA
- Department of Statistics and Data Sciences, The University of Texas at Austin, 105 E. 24th St D9800, Austin, TX 78712, USA
| |
Collapse
|
2
|
Barth BB, Redington ER, Gautam N, Pelot NA, Grill WM. Calcium image analysis in the moving gut. Neurogastroenterol Motil 2023; 35:e14678. [PMID: 37736662 PMCID: PMC10999186 DOI: 10.1111/nmo.14678] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 01/30/2023] [Revised: 08/14/2023] [Accepted: 08/28/2023] [Indexed: 09/23/2023]
Abstract
BACKGROUND The neural control of gastrointestinal muscle relies on circuit activity whose underlying motifs remain limited by small-sample calcium imaging recordings confounded by motion artifact, paralytics, and muscle dissections. We present a sequence of resources to register images from moving preparations and identify out-of-focus events in widefield fluorescent microscopy. METHODS Our algorithm uses piecewise rigid registration with pathfinding to correct movements associated with smooth muscle contractions. We developed methods to identify loss-of-focus events and to simulate calcium activity to evaluate registration. KEY RESULTS By combining our methods with principal component analysis, we found populations of neurons exhibit distinct activity patterns in response to distinct stimuli consistent with hypothesized roles. The image analysis pipeline makes deeper insights possible by capturing concurrently calcium dynamics from more neurons in larger fields of view. We provide access to the source code for our algorithms and make experimental and technical recommendations to increase data quality in calcium imaging experiments. CONCLUSIONS These methods make feasible large population, robust calcium imaging recordings and permit more sophisticated network analyses and insights into neural activity patterns in the gut.
Collapse
Affiliation(s)
- Bradley B. Barth
- Department of Biomedical Engineering, Duke University, Durham, NC 27708
| | - Emily R. Redington
- Department of Biomedical Engineering, Duke University, Durham, NC 27708
- Current employment Regeneron Pharmaceuticals, Inc. Contributions to this article were made as an employee of Duke University and the views expressed do not necessarily represent the views of Regeneron Pharmaceuticals Inc
| | - Nitisha Gautam
- Department of Biomedical Engineering, Duke University, Durham, NC 27708
| | - Nicole A. Pelot
- Department of Biomedical Engineering, Duke University, Durham, NC 27708
| | - Warren M. Grill
- Department of Biomedical Engineering, Duke University, Durham, NC 27708
| |
Collapse
|
3
|
Liu W, Pan J, Xu Y, Wang M, Jia H, Zhang K, Chen X, Li X, Liao X. Fast and Accurate Motion Correction for Two-Photon Ca 2+ Imaging in Behaving Mice. Front Neuroinform 2022; 16:851188. [PMID: 35559212 PMCID: PMC9088923 DOI: 10.3389/fninf.2022.851188] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/09/2022] [Accepted: 03/07/2022] [Indexed: 11/13/2022] Open
Abstract
Two-photon Ca2+ imaging is a widely used technique for investigating brain functions across multiple spatial scales. However, the recording of neuronal activities is affected by movement of the brain during tasks in which the animal is behaving normally. Although post-hoc image registration is the commonly used approach, the recent developments of online neuroscience experiments require real-time image processing with efficient motion correction performance, posing new challenges in neuroinformatics. We propose a fast and accurate image density feature-based motion correction method to address the problem of imaging animal during behaviors. This method is implemented by first robustly estimating and clustering the density features from two-photon images. Then, it takes advantage of the temporal correlation in imaging data to update features of consecutive imaging frames with efficient calculations. Thus, motion artifacts can be quickly and accurately corrected by matching the features and obtaining the transformation parameters for the raw images. Based on this efficient motion correction strategy, our algorithm yields promising computational efficiency on imaging datasets with scales ranging from dendritic spines to neuronal populations. Furthermore, we show that the proposed motion correction method outperforms other methods by evaluating not only computational speed but also the quality of the correction performance. Specifically, we provide a powerful tool to perform motion correction for two-photon Ca2+ imaging data, which may facilitate online imaging experiments in the future.
Collapse
Affiliation(s)
- Weiyi Liu
- Brain Research Center and State Key Laboratory of Trauma, Burns, and Combined Injury, Third Military Medical University, Chongqing, China
| | - Junxia Pan
- Brain Research Center and State Key Laboratory of Trauma, Burns, and Combined Injury, Third Military Medical University, Chongqing, China
| | - Yuanxu Xu
- Brain Research Center and State Key Laboratory of Trauma, Burns, and Combined Injury, Third Military Medical University, Chongqing, China
| | - Meng Wang
- Center for Neurointelligence, School of Medicine, Chongqing University, Chongqing, China
| | - Hongbo Jia
- Advanced Institute for Brain and Intelligence, Guangxi University, Nanning, China
- Brain Research Instrument Innovation Center, Suzhou Institute of Biomedical Engineering and Technology, Chinese Academy of Sciences, Suzhou, China
| | - Kuan Zhang
- Brain Research Center and State Key Laboratory of Trauma, Burns, and Combined Injury, Third Military Medical University, Chongqing, China
| | - Xiaowei Chen
- Brain Research Center and State Key Laboratory of Trauma, Burns, and Combined Injury, Third Military Medical University, Chongqing, China
| | - Xingyi Li
- Center for Neurointelligence, School of Medicine, Chongqing University, Chongqing, China
| | - Xiang Liao
- Center for Neurointelligence, School of Medicine, Chongqing University, Chongqing, China
| |
Collapse
|