Extracting Blood Vessels From Full-Field OCT Data of Human Skin by Short-Time RPCA

Visualization of Subcutaneous Blood Vessels Based on Hyperspectral Imaging and Three-Wavelength Index Images

Blood vessel visualization technology allows nursing staff to transition from traditional palpation or touch to locate the subcutaneous blood vessels to visualized localization by providing a clear visual aid for performing various medical procedures accurately and efficiently involving blood vessels; this can further improve the first-attempt puncture success rate for nursing staff and reduce the pain of patients. We propose a novel technique for hyperspectral visualization of blood vessels in human skin. An experiment with six participants with different skin types, race, and nationality backgrounds is described. A mere separation of spectral layers for different skin types is shown to be insufficient. The use of three-wavelength indices in imaging has shown a significant improvement in the quality of results compared to using only two-wavelength indices. This improvement can be attributed to an increase in the contrast ratio, which can be as high as 25%. We propose and implement a technique for finding new index formulae based on an exhaustive search and a binary blood-vessel image obtained through an expert assessment. As a result of the search, a novel index formula was deduced, allowing high-contrast blood vessel images to be generated for any skin type.

Spatial-Temporal Speckle Variance in the En-Face View as a Contrast for Optical Coherence Tomography Angiography (OCTA)

Optical Coherence Tomography (OCT) is an adaptable depth-resolved imaging modality capable of creating a non-invasive 'digital biopsy' of the eye. One of the latest advances in OCT is optical coherence tomography angiography (OCTA), which uses the speckle variance or phase change in the signal to differentiate static tissue from blood flow. Unlike fluorescein angiography (FA), OCTA is contrast free and depth resolved. By combining high-density scan patterns and image processing algorithms, both morphometric and functional data can be extracted into a depth-resolved vascular map of the retina. The algorithm that we explored takes advantage of the temporal-spatial relationship of the speckle variance to improve the contrast of the vessels in the en-face OCT with a single frame. It also does not require the computationally inefficient decorrelation of multiple A-scans to detect vasculature, as used in conventional OCTA analysis. Furthermore, the spatial temporal OCTA (ST-OCTA) methodology tested offers the potential for post hoc analysis to improve the depth-resolved contrast of specific ocular structures, such as blood vessels, with the capability of using only a single frame for efficient screening of large sample volumes, and additional enhancement by processing with choice of frame averaging methods. Applications of this method in pre-clinical studies suggest that the OCTA algorithm and spatial temporal methodology reported here can be employed to investigate microvascularization and blood flow in the retina, and possibly other compartments of the eye.

Classification of squamous cell carcinoma from FF-OCT images: Data selection and progressive model construction

We investigate the speed and performance of squamous cell carcinoma (SCC) classification from full-field optical coherence tomography (FF-OCT) images based on the convolutional neural network (CNN). Due to the unique characteristics of SCC features, the high variety of CNN, and the high volume of our 3D FF-OCT dataset, progressive model construction is a time-consuming process. To address the issue, we develop a training strategy for data selection that makes model training 16 times faster by exploiting the dependency between images and the knowledge of SCC feature distribution. The speedup makes progressive model construction computationally feasible. Our approach further refines the regularization, channel attention, and optimization mechanism of SCC classifier and improves the accuracy of SCC classification to 87.12% at the image level and 90.10% at the tomogram level. The results are obtained by testing the proposed approach on an FF-OCT dataset with over one million mouse skin images.

Multi-slice low-rank tensor decomposition based multi-atlas segmentation: Application to automatic pathological liver CT segmentation

Liver segmentation from abdominal CT images is an essential step for liver cancer computer-aided diagnosis and surgical planning. However, both the accuracy and robustness of existing liver segmentation methods cannot meet the requirements of clinical applications. In particular, for the common clinical cases where the liver tissue contains major pathology, current segmentation methods show poor performance. In this paper, we propose a novel low-rank tensor decomposition (LRTD) based multi-atlas segmentation (MAS) framework that achieves accurate and robust pathological liver segmentation of CT images. Firstly, we propose a multi-slice LRTD scheme to recover the underlying low-rank structure embedded in 3D medical images. It performs the LRTD on small image segments consisting of multiple consecutive image slices. Then, we present an LRTD-based atlas construction method to generate tumor-free liver atlases that mitigates the performance degradation of liver segmentation due to the presence of tumors. Finally, we introduce an LRTD-based MAS algorithm to derive patient-specific liver atlases for each test image, and to achieve accurate pairwise image registration and label propagation. Extensive experiments on three public databases of pathological liver cases validate the effectiveness of the proposed method. Both qualitative and quantitative results demonstrate that, in the presence of major pathology, the proposed method is more accurate and robust than state-of-the-art methods.

Generation of Augmented Capillary Network Optical Coherence Tomography Image Data of Human Skin for Deep Learning and Capillary Segmentation

The segmentation of capillaries in human skin in full-field optical coherence tomography (FF-OCT) images plays a vital role in clinical applications. Recent advances in deep learning techniques have demonstrated a state-of-the-art level of accuracy for the task of automatic medical image segmentation. However, a gigantic amount of annotated data is required for the successful training of deep learning models, which demands a great deal of effort and is costly. To overcome this fundamental problem, an automatic simulation algorithm to generate OCT-like skin image data with augmented capillary networks (ACNs) in a three-dimensional volume (which we called the ACN data) is presented. This algorithm simultaneously acquires augmented FF-OCT and corresponding ground truth images of capillary structures, in which potential functions are introduced to conduct the capillary pathways, and the two-dimensional Gaussian function is utilized to mimic the brightness reflected by capillary blood flow seen in real OCT data. To assess the quality of the ACN data, a U-Net deep learning model was trained by the ACN data and then tested on real in vivo FF-OCT human skin images for capillary segmentation. With properly designed data binarization for predicted image frames, the testing result of real FF-OCT data with respect to the ground truth achieved high scores in performance metrics. This demonstrates that the proposed algorithm is capable of generating ACN data that can imitate real FF-OCT skin images of capillary networks for use in research and deep learning, and that the model for capillary segmentation could be of wide benefit in clinical and biomedical applications.

Extraction and Visualization of Ocular Blood Vessels in 3D Medical Images Based on Geometric Transformation Algorithm

Data extraction and visualization of 3D medical images of ocular blood vessels are performed by geometric transformation algorithm, which first performs random resonance response in a global sense to achieve detection of high-contrast coarse blood vessels and then redefines the input signal as a local image shielding the global detection result to achieve enhanced detection of low-contrast microfine vessels and complete multilevel random resonance segmentation detection. Finally, a random resonance detection method for fundus vessels based on scale decomposition is proposed, in which the images are scale decomposed, the high-frequency signals containing detailed information are randomly resonantly enhanced to achieve microfine vessel segmentation detection, and the final vessel segmentation detection results are obtained after fusing the low-frequency image signals. The optimal stochastic resonance response of the nonlinear model of neurons in the global sense is obtained to detect the high-grade intensity signal; then, the input signal is defined as a local image with high-contrast blood vessels removed, and the parameters are optimized before the detection of the low-grade intensity signal. Finally, the multilevel random resonance response is fused to obtain the segmentation results of the fundus retinal vessels. The sensitivity of the multilevel segmentation method proposed in this paper is significantly improved compared with the global random resonance results, indicating that the method proposed in this paper has obvious advantages in the segmentation of vessels with low-intensity levels. The image library was tested, and the experimental results showed that the new method has a better segmentation effect on low-contrast microscopic blood vessels. The new method not only makes full use of the noise for weak signal detection and segmentation but also provides a new idea of how to achieve multilevel segmentation and recognition of medical images.

Submicron spatial resolution optical coherence tomography for visualising the 3D structures of cells cultivated in complex culture systems

Three-dimensional (3D) configuration of in vitro cultivated cells has been recognised as a valuable tool in developing stem cell and cancer cell therapy. However, currently available imaging approaches for live cells have drawbacks, including unsatisfactory resolution, lack of cross-sectional and 3D images, and poor penetration of multi-layered cell products, especially when cells are cultivated on semitransparent carriers. Herein, we report a prototype of a full-field optical coherence tomography (FF-OCT) system with isotropic submicron spatial resolution in en face and cross-sectional views that provides a label-free, non-invasive platform with high-resolution 3D imaging. We validated the imaging power of this prototype by examining (1) cultivated neuron cells (N2A cell line); (2) multilayered, cultivated limbal epithelial sheets (mCLESs); (3) neuron cells (N2A cell line) and mCLESs cultivated on a semitransparent amniotic membrane (stAM); and (4) directly adherent colonies of neuron-like cells (DACNs) covered by limbal epithelial cell sheets. Our FF-OCT exhibited a penetrance of up to 150 μm in a multilayered cell sheet and displayed the morphological differences of neurons and epithelial cells in complex coculture systems. This FF-OCT is expected to facilitate the visualisation of cultivated cell products in vitro and has a high potential for cell therapy and translational medicine research.

Guided filtering-based nonlocal means despeckling of optical coherence tomography images

This Letter presents a guided filtering (GF)-based nonlocal means (NLM) method for despeckling of optical coherence tomography (OCT) images. Unlike existing NLM methods that determine weights using image intensities or features, the proposed method first uses the GF to capture both grayscale information and features of the input image and then introduces them into the NLM for accurate weight computation. The boosting and iterative strategies are further incorporated to ensure despeckling performance. Experiments on the real OCT images demonstrate that our method outperforms the compared methods by delivering sufficient noise reduction and preserving image details well.

Advances in Doppler optical coherence tomography and angiography

Since the first demonstration of Doppler optical coherence tomography (OCT) in 1997, several functional extensions of Doppler OCT have been developed, including velocimetry, angiogram, and optical coherence elastography. These functional techniques have been widely used in research and clinical applications, particularly in ophthalmology. Here, we review the principles, representative methods, and applications of different Doppler OCT techniques, followed by discussion on the innovations, limitations, and future directions of each of these techniques.

SNR-Adaptive OCT Angiography Enabled by Statistical Characterization of Intensity and Decorrelation With Multi-Variate Time Series Model

In OCT angiography (OCTA), decorrelation computation has been widely used as a local motion index to identify dynamic flow from static tissues, but its dependence on SNR severely degrades the vascular visibility, particularly in low-SNR regions. To mathematically characterize the decorrelation-SNR dependence of OCT signals, we developed a multi-variate time series (MVTS) model. Based on the model, we derived a universal asymptotic linear relation of decorrelation to inverse SNR (iSNR), with the variance in static and noise regions determined by the average kernel size. Accordingly, with the population distribution of static and noise voxels being explicitly calculated in the iSNR and decorrelation (ID) space, a linear classifier is developed by removing static and noise voxels at all SNR, to generate a SNR-adaptive OCTA, termed as ID-OCTA. Then, flow phantom and human skin experiments were performed to validate the proposed ID-OCTA. Both qualitative and quantitative assessments demonstrated that the ID-OCTA offers a superior visibility of blood vessels, particularly in the deep layer. Finally, the implications of this work on both system design and hemodynamic quantification are further discussed.