Optical coherence tomography (OCT) is a widely used non-invasive biomedical imaging modality that can rapidly provide volumetric images of samples. Here, we present a deep learning-based image reconstruction framework that can generate swept-source OCT (SS-OCT) images using undersampled spectral data, without any spatial aliasing artifacts. This neural network-based image reconstruction does not require any hardware changes to the optical setup and can be easily integrated with existing swept-source or spectral-domain OCT systems to reduce the amount of raw spectral data to be acquired. To show the efficacy of this framework, we trained and blindly tested a deep neural network using mouse embryo samples imaged by an SS-OCT system. Using 2-fold undersampled spectral data (i.e., 640 spectral points per A-line), the trained neural network can blindly reconstruct 512 A-lines in 0.59 ms using multiple graphics-processing units (GPUs), removing spatial aliasing artifacts due to spectral undersampling, also presenting a very good match to the images of the same samples, reconstructed using the full spectral OCT data (i.e., 1280 spectral points per A-line). We also successfully demonstrate that this framework can be further extended to process 3× undersampled spectral data per A-line, with some performance degradation in the reconstructed image quality compared to 2× spectral undersampling. Furthermore, an A-line-optimized undersampling method is presented by jointly optimizing the spectral sampling locations and the corresponding image reconstruction network, which improved the overall imaging performance using less spectral data points per A-line compared to 2× or 3× spectral undersampling results. This deep learning-enabled image reconstruction approach can be broadly used in various forms of spectral-domain OCT systems, helping to increase their imaging speed without sacrificing image resolution and signal-to-noise ratio.
In optical coherence tomography (OCT), the axial resolution is often superior to the lateral resolution, which is sacrificed for long imaging depths. To address this anisotropy, we previously developed optical coherence refraction tomography (OCRT), which uses images from multiple angles to computationally reconstruct an image with isotropic resolution, given by the OCT axial resolution. On the other hand, spectroscopic OCT (SOCT), an extension of OCT, trades axial resolution for spectral resolution and hence often has superior lateral resolution. Here, we present spectroscopic OCRT (SOCRT), which uses SOCT images from multiple angles to reconstruct a spectroscopic image with isotropic spatial resolution limited by the OCT
- Award ID(s):
- NSF-PAR ID:
- Publisher / Repository:
- Optical Society of America
- Date Published:
- Journal Name:
- Optics Letters
- 0146-9592; OPLEDP
- Page Range / eLocation ID:
- Article No. 2091
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
Optical coherence tomography (OCT) suffers from speckle noise due to the high spatial coherence of the utilized light source, leading to significant reductions in image quality and diagnostic capabilities. In the past, angular compounding techniques have been applied to suppress speckle noise. However, existing image registration methods usually guarantee pure angular compounding only within a relatively small field of view in the focal region, but produce spatial averaging in the other regions, resulting in resolution loss and image blur. This work develops an image registration model to correctly localize the real-space location of every pixel in an OCT image, for all depths. The registered images captured at different angles are fused into a speckle-reduced composite image. Digital focusing, based on the convolution of the complex OCT images and the conjugate of the point spread function (PSF), is studied to further enhance lateral resolution and contrast. As demonstrated by experiments, angular compounding with our improved image registration techniques and digital focusing, can effectively suppress speckle noise, enhance resolution and contrast, and reveal fine structures in
Spectroscopic single-molecule localization microscopy (sSMLM) simultaneously provides spatial localization and spectral information of individual single-molecules emission, offering multicolor super-resolution imaging of multiple molecules in a single sample with the nanoscopic resolution. However, this technique is limited by the requirements of acquiring a large number of frames to reconstruct a super-resolution image. In addition, multicolor sSMLM imaging suffers from spectral cross-talk while using multiple dyes with relatively broad spectral bands that produce cross-color contamination. Here, we present a computational strategy to accelerate multicolor sSMLM imaging. Our method uses deep convolution neural networks to reconstruct high-density multicolor super-resolution images from low-density, contaminated multicolor images rendered using sSMLM datasets with much fewer frames, without compromising spatial resolution. High-quality, super-resolution images are reconstructed using up to 8-fold fewer frames than usually needed. Thus, our technique generates multicolor super-resolution images within a much shorter time, without any changes in the existing sSMLM hardware system. Two-color and three-color sSMLM experimental results demonstrate superior reconstructions of tubulin/mitochondria, peroxisome/mitochondria, and tubulin/mitochondria/peroxisome in fixed COS-7 and U2-OS cells with a significant reduction in acquisition time.
Preclinical research remains the essential platform in the development and optimization of medical therapies and advancements in translational medicines. However, specifically to animal research, federal laws, and institutional policies require investigators to apply the principles of the 3R's (replacement, reduction, and refinement). The concept of benchtop models utilizing isolated organs, in which multiple variables can be controlled to recreate human function, has been innovative advancements in preclinical research models that adhere to these principles. More specifically, isolated perfused kidney (IPK) models have been invaluable preclinical tools that have led to numerous advancements over the decades, including understanding renal physiology, pharmacologic therapies, and improvements in renal transplantation. However, pre‐existing IPK models are not without their own limitations, leaving areas for improvement. An isolated perfused kidney apparatus was designed to best recreate human use conditions as a preclinical tool. Porcine renal blocks were chosen over the more commonly used rodent models, due to their greater similarities to human anatomies. Sixteen porcine kidney pairs obtained en bloc were extracted and placed onto an apparatus where aortic flows, pressures, and overall systemic temperatures were controlled. Organ viability was assessed in 10 renal blocks (
n= 8 fresh and n= 2 previously frozen specimens) via both urinary flows and compositions at timepoints up to 180 min. Multimodality imaging, which included fluoroscopy, ultrasound, optical coherence tomography (OCT), and video scopes, was also employed to capture internal and external images to determine renal artery orientations and dimensions. Anatomical measurements and viability assessments of porcine renal blocks were successfully achieved in our perfusion model. Renal main artery diameters averaged smaller in our sample size than in human anatomy while also having more superior takeoff angles. Yet, the average lengths of each main segment were comparable to human anatomy: 32.09 ± 7.97 mm and 42.23 ± 7.33 mm in the left and right renal main artery, respectively. Urine production and urine composition of the fresh renal blocks, when compared to the frozen blocks and baseline perfusate, showed kidney viabilities of up to 3 h via excretion and retention of various metabolites. In this paper, we described a protocol for an isolated perfused kidney apparatus using large mammalian renal blocks. We believe this protocol to be an improvement from similar pre‐existing models in better representing human physiologic function while allowing for multimodal imaging. The resulting Visible Kidney™ preclinical model, which has shown viability after isolation and reperfusion, can be a fast and reliable tool for the development of medical devices while also reducing the unnecessary use of animals for research.
Segmentation of multiple surfaces in optical coherence tomography (OCT) images is a challenging problem, further complicated by the frequent presence of weak boundaries, varying layer thicknesses, and mutual influence between adjacent surfaces. The traditional graph-based optimal surface segmentation method has proven its effectiveness with its ability to capture various surface priors in a uniform graph model. However, its efficacy heavily relies on handcrafted features that are used to define the surface cost for the “goodness” of a surface. Recently, deep learning (DL) is emerging as a powerful tool for medical image segmentation thanks to its superior feature learning capability. Unfortunately, due to the scarcity of training data in medical imaging, it is nontrivial for DL networks to implicitly learn the global structure of the target surfaces, including surface interactions. This study proposes to parameterize the surface cost functions in the graph model and leverage DL to learn those parameters. The multiple optimal surfaces are then simultaneously detected by minimizing the total surface cost while explicitly enforcing the mutual surface interaction constraints. The optimization problem is solved by the primal-dual interior-point method (IPM), which can be implemented by a layer of neural networks, enabling efficient end-to-end training of the whole network. Experiments on spectral-domain optical coherence tomography (SD-OCT) retinal layer segmentation demonstrated promising segmentation results with sub-pixel accuracy.more » « less