Integrating light-sheet imaging with virtual reality to recapitulate developmental cardiac mechanics

Ding, Yichen; Abiri, Arash; Abiri, Parinaz; Li, Shuoran; Chang, Chih-Chiang; Baek, Kyung In; Hsu, Jeffrey J.; Sideris, Elias; Li, Yilei; Lee, Juhyun; Segura, Tatiana; Nguyen, Thao P.; Bui, Alexander A. T.; Packard, René R. Sevag; Fei, Peng; Hsiai, Tzung K.

doi:10.1172/jci.insight.97180

Cited by 24 publications

(23 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The application of Saak transform to segment 3-D LSFM-acquired images creates an opportunity to investigate chemotherapyinduced cardiac structure and mechanics. Previously, we needed to perform manual or semi-automated segmentation to reconstruct LSFM architectures for computational fluid dynamics [15,16] and interactive virtual reality [17,18]. The addition of edge detection to Saak transform enables the calculation of surface area in relation to the volume of myocardium.…”

Section: Discussionmentioning

confidence: 99%

“…Light-sheet fluorescence microscopy (LSFM) is instrumental in advancing the field of developmental biology and tissue regeneration [1][2][3][4]. LSFM systems have the capacity to investigate cardiac ultra-structure and function [5][6][7][8][9][10][11][12][13][14], providing the moving Baek, Zhaoqiang Wang, Mehrdad Roustaei, Dengfeng Kuang, C.-C. Jay Kuo †, and Tzung K. Hsiai † boundary conditions for computational fluid dynamics [15,16] and the specific labeling of trabecular network for interactive virtual reality [17,18]. However, efficient and robust structural segmentation of cardiac trabeculation remains a post-imaging challenge [19][20][21][22][23].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Saak Transform-Based Machine Learning for Light-Sheet Imaging of Cardiac Trabeculation

Ding

Gudapati

Lin

et al. 2019

Preprint

Self Cite

View full text Add to dashboard Cite

AbstractRecent advances in light-sheet fluorescence microscopy (LSFM) enable 3-dimensional (3-D) imaging of cardiac architecture and mechanics in toto. However, segmentation of the cardiac trabecular network to quantify cardiac injury remains a challenge. We hereby employed “subspace approximation with augmented kernels (Saak) transform” for accurate and efficient quantification of the light-sheet image stacks following chemotherapy-treatment. We established a machine learning framework with augmented kernels based on the Karhunen-Loeve Transform (KLT) to preserve linearity and reversibility of rectification. The Saak transform-based machine learning enhances computational efficiency and obviates iterative optimization of cost function needed for neural networks, minimizing the number of training data sets to three 2-D slices for segmentation in our scenario. The integration of forward and inverse Saak transforms serves as a light-weight module to filter adversarial perturbations and reconstruct estimated images, salvaging robustness of existing classification methods. The accuracy and robustness of the Saak transform are evident following the tests of dice similarity coefficients and various adversary perturbation algorithms, respectively. The addition of edge detection further allows for quantifying the surface area to volume ratio (SVR) of the myocardium in response to chemotherapy-induced cardiac remodeling. The combination of Saak transform, random forest, and edge detection augments segmentation efficiency by 20-fold as compared to manual processing; thus, establishing a robust framework for post light-sheet imaging processing, creating a data-driven machine learning for 3-D quantification of cardiac ultra-structure.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Saak Transform-Based Machine Learning for Light-Sheet Imaging of Cardiac Trabeculation

Ding

Gudapati

Lin

et al. 2019

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Parallel advances in pixel superresolution (118)(119)(120), deep learning (121)(122)(123)(124), virtual reality (125)(126)(127)(128), optogenetics (129), and laser ablation (130) further provide complementary opportunities to elucidate cardiovascular architecture and function. A subvoxel LSFM is technically implemented for high-resolution, high-throughput volumetric imaging of cardiovascular development in a large field of view (22).…”

Section: The Future Of Lsfmmentioning

confidence: 99%

Multiscale light-sheet for rapid imaging of cardiopulmonary system

Ding

Langenbacher

et al. 2018

JCI Insight

Self Cite

View full text Add to dashboard Cite

The ability to image tissue morphogenesis in real-time and in 3-dimensions (3-D) remains an optical challenge. The advent of light-sheet fluorescence microscopy (LSFM) has advanced developmental biology and tissue regeneration research. In this review, we introduce a LSFM system in which the illumination lens reshapes a thin light-sheet to rapidly scan across a sample of interest while the detection lens orthogonally collects the imaging data. This multiscale strategy provides deep-tissue penetration, high-spatiotemporal resolution, and minimal photobleaching and phototoxicity, allowing in vivo visualization of a variety of tissues and processes, ranging from developing hearts in live zebrafish embryos to ex vivo interrogation of the microarchitecture of optically cleared neonatal hearts. Here, we highlight multiple applications of LSFM and discuss several studies that have allowed better characterization of developmental and pathological processes in multiple models and tissues. These findings demonstrate the capacity of multiscale light-sheet imaging to uncover cardiovascular developmental and regenerative phenomena.

show abstract

“…The existing modalities to image and quantify the retinal vascular network are frequently confined to either 2-D or whole-mount samples 19,20 . To identify the early abnormalities and progression of OIR in 3-D, we hereby integrated selective plane illumination microscopy or known as light-sheet fluorescence microscopy (LSFM) with dualillumination, followed by quantitative analyses to acquire 3-D volumetric images [21][22][23][24][25] . Unlike confocal or two-photon microscopy which usually utilizes a point scanning approach, LSFM generates a sheet of light to rapidly scan across the optically-cleared specimens 21,26,27 .…”

Section: Introductionmentioning

confidence: 99%

Selective Plane Illumination Microscopy and Computing Reveal Differential Obliteration of Retinal Vascular Plexuses

Chang

Chu

Meyer

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

Murine models of visual impairment provide micro-vascular insights into the 3-D network disarray in retinopathy. Current imaging and analysis tend to be confined to the 2-D retinal vasculature.We hereby integrated selective plane illumination imaging or known as light-sheet fluorescence microscopy (LSFM) with dual-illumination, followed by computational analyses, to reveal the topological network of vertical sprouts bridging the primary and secondary plexuses in a postnatal mouse model of oxygen-induced retinopathy (OIR). We revealed a preferential obliteration of the secondary plexus and bridging vessels despite a relatively unscathed primary plexus. We compared the local versus global vascular connectivity using clustering coefficients and Euler numbers, respectively. The global vascular connectivity in hyperoxia-exposed retinas was significantly reduced (p < 0.05, n = 5 vs. normoxia), whereas the local connectivity was preserved (p > 0.05, n = 5 vs. normoxia). We further applied principal component analysis (PCA) to automatically segment the vertical sprouts, corroborating the preferential obliteration of the interconnection between vertical sprouts and secondary plexuses that were accompanied with impaired vascular branching and connectivity, and reduced vessel volumes and lengths (p < 0.05, n=5 vs. normoxia). Thus, integration of 3-D selective plane illumination with computational analyses allows for early detection of global and spatially-specific vaso-obliteration, but preserved local reticular structure in response to hyperoxia-induced retinopathy.

show abstract

Integrating light-sheet imaging with virtual reality to recapitulate developmental cardiac mechanics

Cited by 24 publications

References 53 publications

Saak Transform-Based Machine Learning for Light-Sheet Imaging of Cardiac Trabeculation

Saak Transform-Based Machine Learning for Light-Sheet Imaging of Cardiac Trabeculation

Multiscale light-sheet for rapid imaging of cardiopulmonary system

Selective Plane Illumination Microscopy and Computing Reveal Differential Obliteration of Retinal Vascular Plexuses

Contact Info

Product

Resources

About