Deep-learning-based approach for strain estimation in phase-sensitive optical coherence elastography

Convolutional Neural Networks Enable Direct Strain Estimation in Quasistatic Optical Coherence Elastography

Assessing the biomechanical properties of tissues can provide important information for disease diagnosis and therapeutic monitoring. Optical coherence elastography (OCE) is an emerging technology for measuring the biomechanical properties of tissues. Clinical translation of this technology is underway, and steps are being implemented to streamline data collection and processing. OCE data can be noisy, data processing can require significant manual tuning, and a single acquisition may contain gigabytes of data. In this work, we introduce a convolutional neural network-based method to translate raw OCE phase data to strain for quasistatic OCE that is ~40X faster than the conventional least squares approach by bypassing many intermediate data processing steps. The results suggest that a machine learning approach may be a valuable tool for fast, efficient, and accurate extraction of biomechanical information from raw OCE data.

Optimizing numerical k-sampling for swept-source optical coherence tomography angiography

High-quality swept-source optical coherence tomography (SS-OCT) requires accurate k-sampling, which is equally vital for optical coherence tomography angiography (OCTA). Most SS-OCT systems are equipped with hardware-driven k-sampling. However, this conventional approach raises concerns over system cost, optical alignment, imaging depth, and stability in the clocking circuit. This work introduces an optimized numerical k-sampling method to replace the additional k-clock hardware. Using this method, we can realize high axial resolution (4.9-µm full-width-half-maximum, in air) and low roll-off (2.3 dB loss) over a 4-mm imaging depth. The high axial resolution and sensitivity achieved by this simple numerical method can reveal anatomic and microvascular structures with structural OCT and OCTA in both macular and deeper tissues, including the lamina cribrosa, suggesting its usefulness in imaging retinopathy and optic neuropathy.

Digital image correlation-assisted phase-sensitive optical coherence tomography

In this Letter, we introduce a digital image correlation-assisted (DIC-assisted) method to tackle the challenges of phase decorrelation and the inability to measure lateral displacement in phase-sensitive optical coherence tomography (PhS-OCT). This DIC-assisted PhS-OCT (DIC-PhS-OCT) first employs DIC to track displacements from the measured amplitude spectra and subsequently uses these tracked displacements to correct supra-pixel displacement offsets in the measured phase spectra. As a result, it effectively mitigates phase decorrelation resulting from both axial and lateral displacements while enabling the acquisition of sub-pixel-level lateral displacements during the DIC computation. Our experiments demonstrate the effectiveness of DIC-PhS-OCT in addressing these challenges while retaining the ultrahigh sensitivity of conventional PhS-OCT.

Dual-convolutional neural network-enhanced strain estimation method for optical coherence elastography

Strain estimation is vital in phase-sensitive optical coherence elastography (PhS-OCE). In this Letter, we introduce a novel, to the best of our knowledge, method to improve strain estimation by using a dual-convolutional neural network (Dual-CNN). This approach requires two sets of PhS-OCE systems: a high-resolution system for high-quality training data and a cost-effective standard-resolution system for practical measurements. During training, high-resolution strain results acquired from the former system and the pre-existing strain estimation CNN serve as label data, while the narrowed light source-acquired standard-resolution phase results act as input data. By training a new network with this data, high-quality strain results can be estimated from standard-resolution PhS-OCE phase results. Comparison experiments show that the proposed Dual-CNN can preserve the strain quality even when the light source bandwidth is reduced by over 80%.

High-resolution optical coherence tomography using gapped spectrum and real-valued iterative adaptive approach

Optical coherence tomography (OCT) is a powerful imaging technique that is capable of imaging cross-sectional structures with micrometer resolution. After combining with phase-sensitive detection, it can sense small changes in the physical quantities inside an object. In OCT, axial resolution is generally improved by expanding the bandwidth of the light source. However, when the bandwidth is expanded discontinuously, the wavelength gap induces abnormal sidelobes when estimating OCT signals in the depth domain. This problem can lead to poor axial resolution. Herein, we present a method based on a real-valued iterative adaptive approach (RIAA) to achieve a high axial resolution under a discontinuous bandwidth condition. The method uses a weighted matrix to suppress the abnormal sidelobes caused by the wavelength gap and, therefore, can realize high-resolution measurements. A single-reflector OCT spectrum was first measured for validation, and its amplitude in the depth domain was estimated using different methods. The results indicate that the RIAA had the best capability of suppressing abnormal sidelobes, thereby achieving a high axial resolution. In addition, cross-sectional images and phase-difference maps of three different samples were measured. A comparison of the results validated the practical value of this method.

Multimodal Heartbeat and Compression Optical Coherence Elastography for Mapping Corneal Biomechanics

The biomechanical properties of the cornea have a profound influence on the health, structural integrity, and function of the eye. Understanding these properties may be critical for diagnosis and identifying disease pathogenesis. This work demonstrates how two different elastography techniques can be combined for a multimodal approach to measuring corneal biomechanical properties. Heartbeat optical coherence elastography (Hb-OCE) and compression OCE were performed simultaneously to measure the stiffness of the cornea in an in vivo rabbit model. Measurements were further performed after collagen crosslinking to demonstrate how the combined technique can be used to measure changes in corneal stiffness and map mechanical contrast. The results of this work further suggest that measurements from Hb-OCE and compression OCE are comparable, meaning that Hb-OCE and compression OCE may be used interchangeably despite distinct differences in both techniques.