Current applications of optical coherence tomography for coronary intervention

Automatic lumen and anatomical layers segmentation in IVOCT images using meta learning

Automated analysis of the vessel structure in intravascular optical coherence tomography (IVOCT) images is critical to assess the health status of vessels and monitor coronary artery disease progression. However, deep learning-based methods usually require well-annotated large datasets, which are difficult to obtain in the field of medical image analysis. Hence, an automatic layers segmentation method based on meta-learning was proposed, which can simultaneously extract the surfaces of the lumen, intima, media, and adventitia using a handful of annotated samples. Specifically, we leverage a bi-level gradient strategy to train a meta-learner for capturing the shared meta-knowledge among different anatomical layers and quickly adapting to unknown anatomical layers. Then, a Claw-type network and a contrast consistency loss were designed to better learn the meta-knowledge according to the characteristic of annotation of the lumen and anatomical layers. Experimental results on the two cardiovascular IVOCT datasets show that the proposed method achieved state-of-art performance.

Ovarian cancer detection using optical coherence tomography and convolutional neural networks

Ovarian cancer has the sixth-largest fatality rate in the United States among all cancers. A non-surgical assay capable of detecting ovarian cancer with acceptable sensitivity and specificity has yet to be developed. However, such a discovery would profoundly impact the pace of the treatment and improvement to patients' quality of life. Achieving such a solution requires high-quality imaging, image processing, and machine learning to support an acceptably robust automated diagnosis. In this work, we propose an automated framework that learns to identify ovarian cancer in transgenic mice from optical coherence tomography (OCT) recordings. Classification is accomplished using a neural network that perceives spatially ordered sequences of tomograms. We present three neural network-based approaches, namely a VGG-supported feed-forward network, a 3D convolutional neural network, and a convolutional LSTM (Long Short-Term Memory) network. Our experimental results show that our models achieve a favorable performance with no manual tuning or feature crafting, despite the challenging noise inherent in OCT images. Specifically, our best performing model, the convolutional LSTM-based neural network, achieves a mean AUC (± standard error) of 0.81 ± 0.037. To the best of the authors' knowledge, no application of machine learning to analyze depth-resolved OCT images of whole ovaries has been documented in the literature. A significant broader impact of this research is the potential transferability of the proposed diagnostic system from transgenic mice to human organs, which would enable medical intervention from early detection of an extremely deadly affliction.

Optical coherence tomography

During the past decade, noninvasive imaging has emerged as a valuable tool in clinical dermatology and dermatologic research. Optical coherence tomography (OCT) is one such type of noninvasive imaging. OCT uses the principle of interferometry to produce real-time images. A low-power diode laser shines infrared light onto tissues, which reflects back to an optical fiber interferometer. Using time delay and the backscattered light intensity, a two-dimensional image akin to an ultrasound is rendered. We review the history, types, and modalities of OCT, plus the many applications of frequency domain, high definition, and dynamic OCT in practice, including its utility in diagnosis, monitoring, and grading disease severity in a variety of cutaneous conditions.

A Review on Advances in Intra-operative Imaging for Surgery and Therapy: Imagining the Operating Room of the Future

With the advent of Minimally Invasive Surgery (MIS), intra-operative imaging has become crucial for surgery and therapy guidance, allowing to partially compensate for the lack of information typical of MIS. This paper reviews the advancements in both classical (i.e. ultrasounds, X-ray, optical coherence tomography and magnetic resonance imaging) and more recent (i.e. multispectral, photoacoustic and Raman imaging) intra-operative imaging modalities. Each imaging modality was analyzed, focusing on benefits and disadvantages in terms of compatibility with the operating room, costs, acquisition time and image characteristics. Tables are included to summarize this information. New generation of hybrid surgical room and algorithms for real time/in room image processing were also investigated. Each imaging modality has its own (site- and procedure-specific) peculiarities in terms of spatial and temporal resolution, field of view and contrasted tissues. Besides the benefits that each technique offers for guidance, considerations about operators and patient risk, costs, and extra time required for surgical procedures have to be considered. The current trend is to equip surgical rooms with multimodal imaging systems, so as to integrate multiple information for real-time data extraction and computer-assisted processing. The future of surgery is to enhance surgeons eye to minimize intra- and after-surgery adverse events and provide surgeons with all possible support to objectify and optimize the care-delivery process.

Evaluation of segmentation algorithms for optical coherence tomography images of ovarian tissue

Ovarian cancer has the lowest survival rate among all gynecologic cancers predominantly due to late diagnosis. Early detection of ovarian cancer can increase 5-year survival rates from 40% up to 92%, yet no reliable early detection techniques exist. Optical coherence tomography (OCT) is an emerging technique that provides depth-resolved, high-resolution images of biological tissue in real-time and demonstrates great potential for imaging of ovarian tissue. Mouse models are crucial to quantitatively assess the diagnostic potential of OCT for ovarian cancer imaging; however, due to small organ size, the ovaries must first be separated from the image background using the process of segmentation. Manual segmentation is time-intensive, as OCT yields three-dimensional data. Furthermore, speckle noise complicates OCT images, frustrating many processing techniques. While much work has investigated noise-reduction and automated segmentation for retinal OCT imaging, little has considered the application to the ovaries, which exhibit higher variance and inhomogeneity than the retina. To address these challenges, we evaluate a set of algorithms to segment OCT images of mouse ovaries. We examine five preprocessing techniques and seven segmentation algorithms. While all preprocessing methods improve segmentation, Gaussian filtering is most effective, showing an improvement of 32 % ± 1.2 % . Of the segmentation algorithms, active contours performs best, segmenting with an accuracy of 94.8 % ± 1.2 % compared with manual segmentation. Even so, further optimization could lead to maximizing the performance for segmenting OCT images of the ovaries.

Three-dimensional texture analysis of optical coherence tomography images of ovarian tissue

Ovarian cancer has the lowest survival rate among all gynecologic cancers due to predominantly late diagnosis. Optical coherence tomography (OCT) has been applied successfully to experimentally image the ovaries in vivo; however, a robust method for analysis is still required to provide quantitative diagnostic information. Recently, texture analysis has proved to be a useful tool for tissue characterization; unfortunately, existing work in the scope of OCT ovarian imaging is limited to only analyzing 2D sub-regions of the image data, discarding information encoded in the full image area, as well as in the depth dimension. Here we address these challenges by testing three implementations of texture analysis for the ability to classify tissue type. First, we test the traditional case of extracted 2D regions of interest; then we extend this to include the entire image area by segmenting the organ from the background. Finally, we conduct a full volumetric analysis of the image volume using 3D segmented data. For each case, we compute features based on the Grey-Level Co-occurence Matrix and also by introducing a new approach that evaluates the frequency distribution in the image by computing the energy density. We test these methods on a mouse model of ovarian cancer to differentiate between age, genotype, and treatment. The results show that the 3D application of texture analysis is most effective for differentiating tissue types, yielding an average classification accuracy of 78.6%. This is followed by the analysis in 2D with the segmented image volume, yielding an average accuracy of 71.5%. Both of these improve on the traditional approach of extracting square regions of interest, which yield an average classification accuracy of 67.7%. Thus, applying texture analysis in 3D with a fully segmented image volume is the most robust approach to quantitatively characterizing ovarian tissue.

Imaging during percutaneous coronary intervention for optimizing outcomes

Angiography is the current gold standard for imaging during percutaneous coronary interventions but has significant limitations. Catheter-based intravascular imaging techniques such as intravascular ultrasound and the more recent optical coherence tomography have the potential to overcome these limitations and thus optimize clinical outcomes. In this update, we discussed the current applications of the available imaging techniques, existing evidence, continuing unmet needs, and potential areas for further research.

Effect of Plaque Composition, Morphology, and Burden on DESolve Novolimus-Eluting Bioresorbable Vascular Scaffold Expansion and Eccentricity - An Optical Coherence Tomography Analysis

OBJECTIVE

This study of patients treated with novolimus-eluting bioresorbable scaffold (BRS) investigated the impact of plaque burden on the acute mechanical performance of the BRS and the short-term outcome.

METHODS

A total of 15 patients were enrolled. The following parameters were derived from optical coherence tomography (OCT) during the final pullback: mean and minimum area, residual area stenosis, incomplete strut apposition, tissue prolapse, scaffold expansion index (SEI), scaffold eccentricity index (SEC), symmetry index, strut fracture, and edge dissection. Fibrous plaque (FP) and calcific plaque (CP) characteristics were measured at each 200 μm longitudinal cross-section. The patients were divided into two groups based on their medians of the respective plaque characteristics.

RESULTS

OCT analysis showed a lumen area of 11.4 ± 1.9 mm² and a scaffold area of 11.5 ± 2.1 mm². The mean eccentricity index overall was 0.65 ± 0.16 and mean symmetry index 0.39 ± 0.25. Statistically, scaffold expansion was not significantly influenced by a greater plaque burden as represented by greater CP area (SEI in group with CP area <0.52 mm² 84.1% vs. SEI of 86.6% in group with CP area ≥0.52 mm², p = 0.06), thicker CP (85.7% vs. 85.1%, p = 0.06), greater CP arc angle (88.0% vs. 81.7%, p = 0.08), and CP being closer to the lumen (84.2% vs. 86.5%, p = 0.08). Scaffold expansion was also not significantly influenced by FP burden. The eccentricity of the implanted scaffolds was not dependent on the CP burden. On the other hand, a greater FP burden favoured a lower eccentricity index, indicating less circular expansion. Thus, greater FP area, FP thickness, and FP arc angle resulted in a more eccentric scaffold expansion.

CONCLUSION

In contrast to previously studied BRS, the expansion and eccentricity characteristics of the novolimus-eluting scaffold did not show the strong dependency of plaque composition, morphology, and burden. As assessed by OCT, only eccentricity was significantly affected by the FP burden. A greater FP plaque arc in our cohort and device-specific properties, e.g. self-correction, may explain the lack of a relationship between plaque, expansion, and eccentricity.

Reconstruction of stented coronary arteries from optical coherence tomography images: Feasibility, validation, and repeatability of a segmentation method

Optical coherence tomography (OCT) is an established catheter-based imaging modality for the assessment of coronary artery disease and the guidance of stent placement during percutaneous coronary intervention. Manual analysis of large OCT datasets for vessel contours or stent struts detection is time-consuming and unsuitable for real-time applications. In this study, a fully automatic method was developed for detection of both vessel contours and stent struts. The method was applied to in vitro OCT scans of eight stented silicone bifurcation phantoms for validation purposes. The proposed algorithm comprised four main steps, namely pre-processing, lumen border detection, stent strut detection, and three-dimensional point cloud creation. The algorithm was validated against manual segmentation performed by two independent image readers. Linear regression showed good agreement between automatic and manual segmentations in terms of lumen area (r>0.99). No statistically significant differences in the number of detected struts were found between the segmentations. Mean values of similarity indexes were >95% and >85% for the lumen and stent detection, respectively. Stent point clouds of two selected cases, obtained after OCT image processing, were compared to the centerline points of the corresponding stent reconstructions from micro computed tomography, used as ground-truth. Quantitative comparison between the corresponding stent points resulted in median values of ~150 μm and ~40 μm for the total and radial distances of both cases, respectively. The repeatability of the detection method was investigated by calculating the lumen volume and the mean number of detected struts per frame for seven repeated OCT scans of one selected case. Results showed low deviation of values from the median for both analyzed quantities. In conclusion, this study presents a robust automatic method for detection of lumen contours and stent struts from OCT as supported by focused validation against both manual segmentation and micro computed tomography and by good repeatability.

Improved accuracy in periodontal pocket depth measurement using optical coherence tomography

Purpose

The purpose of this study was to examine whether periodontal pocket could be satisfactorily visualized by optical coherence tomography (OCT) and to suggest quantitative methods for measuring periodontal pocket depth.

Methods

We acquired OCT images of periodontal pockets in a porcine model and determined the actual axial resolution for measuring the exact periodontal pocket depth using a calibration method. Quantitative measurements of periodontal pockets were performed by real axial resolution and compared with the results from manual periodontal probing.

Results

The average periodontal pocket depth measured by OCT was 3.10±0.15 mm, 4.11±0.17 mm, 5.09±0.17 mm, and 6.05±0.21 mm for each periodontal pocket model, respectively. These values were similar to those obtained by manual periodontal probing.

Conclusions

OCT was able to visualize periodontal pockets and show attachment loss. By calculating the calibration factor to determine the accurate axial resolution, quantitative standards for measuring periodontal pocket depth can be established regardless of the position of periodontal pocket in the OCT image.

Deep feature learning for automatic tissue classification of coronary artery using optical coherence tomography

Kawasaki disease (KD) is an acute childhood disease complicated by coronary artery aneurysms, intima thickening, thrombi, stenosis, lamellar calcifications, and disappearance of the media border. Automatic classification of the coronary artery layers (intima, media, and scar features) is important for analyzing optical coherence tomography (OCT) images recorded in pediatric patients. OCT has been known as an intracoronary imaging modality using near-infrared light which has recently been used to image the inner coronary artery tissues of pediatric patients, providing high spatial resolution (ranging from 10 to 20 μm). This study aims to develop a robust and fully automated tissue classification method by using the convolutional neural networks (CNNs) as feature extractor and comparing the predictions of three state-of-the-art classifiers, CNN, random forest (RF), and support vector machine (SVM). The results show the robustness of CNN as the feature extractor and random forest as the classifier with classification rate up to 96%, especially to characterize the second layer of coronary arteries (media), which is a very thin layer and it is challenging to be recognized and specified from other tissues.

Transluminal Attenuation Gradient for the Noninvasive Assessment of Functional Significance in Coronary Artery Stenoses

Invasive and noninvasive methods currently used for imaging-based evaluation of the coronary tree reveal a high number of moderate degree coronary artery stenoses, and the decision to revascularize or not such lesions could be difficult in different clinical settings. Therefore, the need for evaluating the functional significance of such lesions appeared obvious and led to the introduction of fractional flow reserve methodology, a new tool proposed for the evaluation of the functional impact of a coronary stenosis. At the same time, new tools have been proposed for the same application, such as the transluminal attenuation gradient along a coronary artery stenosis, determined using cardiac computed angiography. The aim of this short update is to summarize the recent advances in the field of invasive and noninvasive evaluation of the functional significance of coronary artery stenoses.

The Use of Biomarkers for the Early Detection of Vulnerable Atherosclerotic Plaques and Vulnerable Patients. A Review

Acute coronary syndromes represent the most severe consequences of atherosclerosis, most often triggered by the rupture of a coronary plaque, which, for various reasons, has become unstable. In many cases, these rupture-prone vulnerable plaques are difficult to diagnose, because they do not always cause significant obstruction noticeable by coronary angiography. Therefore, new methods and tools for the identification of vulnerable plaques have been proposed, many of which are currently under study. Various biomarkers have been suggested as predictors of a vulnerable plaque, as well as indicators of an increased inflammatory status associated with higher patient susceptibility for plaque rupture. Integration of such biomarkers into multiple biomarker platforms has been suggested to identify superior diagnostic algorithms for the early detection of the high-risk condition associated with an unstable plaque. The aim of this review is to summarize recent research related to biomarkers used for the early detection of vulnerable plaques and vulnerable patients.

Use of a new intra-ocular spectral domain optical coherence tomography in vitreoretinal surgery

PURPOSE

To describe the use of a novel intra-ocular side-scanning probe enabling the acquisition of spectral-domain optical coherence tomography (SD-OCT) images during surgery in a series of patients with complex forms of retinal detachment.

METHODS

A 23-gauge, side-scanning SD-OCT probe (C7 System; LightLab Imaging, Inc/St Jude Medical, St. Paul, MN, USA) in a 20-gauge catheter, was used to acquire the intra-operative OCT images in seven patients with vitreoretinal diseases. Twenty-five gauge pars plana vitrectomy (PPV) was performed in every patient in a standard fashion. After enlarging the temporal sclerotomy to a 20-gauge port, all the patients were scanned with intra-ocular side-scanning SD-OCT, during different steps of the surgery based on surgeon needs. Scans were recorded real time and directly evaluated on a screen during surgery. Optical coherence tomography (OCT) scans were judged beneficial when they would recognize structures otherwise not seen on biomicroscopy.

RESULTS

The intra-ocular SD-OCT has been helpful in acquiring extra information during vitreoretinal surgery such as the detection of the presence of otherwise invisible membranes (epiretinal membrane, subretinal membrane), the location of small tears and the identification of the retinal plane under suboptimal conditions for visualization.

CONCLUSION

The use of an intra-ocular SD-OCT can expand upon visual cues during surgery, helping in the decision-making process and allowing additional deliberate surgical manoeuvres aimed at improving surgical outcomes.

Using optical coherence tomography to rapidly phenotype and quantify congenital heart defects associated with prenatal alcohol exposure

BACKGROUND

The most commonly used method to analyze congenital heart defects involves serial sectioning and histology. However, this is often a time-consuming process where the quantification of cardiac defects can be difficult due to problems with accurate section registration. Here we demonstrate the advantages of using optical coherence tomography, a comparatively new and rising technology, to phenotype avian embryo hearts in a model of fetal alcohol syndrome where a binge-like quantity of alcohol/ethanol was introduced at gastrulation.

RESULTS

The rapid, consistent imaging protocols allowed for the immediate identification of cardiac anomalies, including ventricular septal defects and misaligned/missing vessels. Interventricular septum thicknesses and vessel diameters for three of the five outflow arteries were also significantly reduced. Outflow and atrioventricular valves were segmented using image processing software and had significantly reduced volumes compared to controls. This is the first study to our knowledge that has 3D reconstructed the late-stage cardiac valves in precise detail to examine their morphology and dimensions.

CONCLUSIONS

We believe, therefore, that optical coherence tomography, with its ability to rapidly image and quantify tiny embryonic structures in high resolution, will serve as an excellent and cost-effective preliminary screening tool for developmental biologists working with a variety of experimental/disease models.

Intravascular optical coherence tomography light scattering artifacts: merry-go-rounding, blooming, and ghost struts

We sought to elucidate the mechanisms underlying two common intravascular optical coherence tomography (IV-OCT) artifacts that occur when imaging metallic stents: “merry-go-rounding” (MGR), which is an increase in strut arc length (SAL), and “blooming,” which is an increase in the strut reflection thickness (blooming thickness). Due to uncontrollable variables that occur in vivo, we performed an in vitro assessment of MGR and blooming in stented vessel phantoms. Using Xience V and Driver stents, we examined the effects of catheter offset, intimal strut coverage, and residual blood on SAL and blooming thickness in IV-OCT images. Catheter offset and strut coverage both caused minor MGR, while the greatest MGR effect resulted from light scattering by residual blood in the vessel lumen, with 1% hematocrit (Hct) causing a more than fourfold increase in SAL compared with saline (p<0.001 ). Residual blood also resulted in blooming, with blooming thickness more than doubling when imaged in 0.5% Hct compared with saline (p<0.001 ). We demonstrate that a previously undescribed mechanism, light scattering by residual blood in the imaging field, is the predominant cause of MGR. Light scattering also results in blooming, and a newly described artifact, three-dimensional-MGR, which results in “ghost struts” in B-scans.

Measurement of the blood flow rate and velocity in coronary artery stenosis using intracoronary frequency domain optical coherence tomography: Validation against fractional flow reserve

OBJECTIVES

The main objective of this study was to assess the blood flow rate and velocity in coronary artery stenosis using intracoronary frequency domain optical coherence tomography (FD-OCT). A correlation between fractional flow reserve (FFR) and FD-OCT derived blood flow velocity is also included in this study.

METHODS & RESULTS

A total of 20 coronary stenoses in 15 patients were assessed consecutively by quantitative coronary angiography (QCA), FFR and FD-OCT. A percutaneous coronary intervention (PCI) optimization system was used in this study which combines wireless FFR measurement and FD-OCT imaging in one platform. Stenoses were labelled severe if FFR ≤ 0.8. Blood flow rate and velocity in each stenosis segment were derived from the volumetric analysis of the FD-OCT pull back images. The FFR value was ≤ 0.80 in 5 stenoses (25%). The mean blood flow rate in severe coronary stenosis (n = 5) was 2.54 ± 0.55 ml/s as compared to 4.81 ± 1.95 ml/s in stenosis with FFR > 0.8 (n = 15). A good and significant correlation between FFR and FD-OCT blood flow velocity in coronary artery stenosis (r = 0.74, p < 0.001) was found.

CONCLUSION

The assessment of stenosis severity using FD-OCT derived blood flow rate and velocity has the ability to overcome many limitations of QCA and intravascular ultrasound (IVUS).

Numerical investigations of the haemodynamic changes associated with stent malapposition in an idealised coronary artery

The deployment of a coronary stent near complex lesions can sometimes lead to incomplete stent apposition (ISA), an undesirable side effect of coronary stent implantation. Three-dimensional computational fluid dynamics (CFD) calculations are performed on simplified stent models (with either square or circular cross-section struts) inside an idealised coronary artery to analyse the effect of different levels of ISA to the change in haemodynamics inside the artery. The clinical significance of ISA is reported using haemodynamic metrics like wall shear stress (WSS) and wall shear stress gradient (WSSG). A coronary stent with square cross-sectional strut shows different levels of reverse flow for malapposition distance (MD) between 0mm and 0.12 mm. Chaotic blood flow is usually observed at late diastole and early systole for MD=0mm and 0.12 mm but are suppressed for MD=0.06 mm. The struts with circular cross section delay the flow chaotic process as compared to square cross-sectional struts at the same MD and also reduce the level of fluctuations found in the flow field. However, further increase in MD can lead to chaotic flow not only at late diastole and early systole, but it also leads to chaotic flow at the end of systole. In all cases, WSS increases above the threshold value (0.5 Pa) as MD increases due to the diminishing reverse flow near the artery wall. Increasing MD also results in an elevated WSSG as flow becomes more chaotic, except for square struts at MD=0.06 mm.

Atherosclerosis and atheroma plaque rupture: imaging modalities in the visualization of vasa vasorum and atherosclerotic plaques

Invasive angiography has been widely accepted as the gold standard to diagnose cardiovascular pathologies. Despite its superior resolution of demonstrating atherosclerotic plaque in terms of degree of lumen stenosis, the morphological assessment for the plaque is insufficient for the analysis of plaque components, and therefore, unable to predict the risk status or vulnerability of atherosclerotic plaque. There is an increased body of evidence to show that the vasa vasorum play an important role in the initiation, progression, and complications of atherosclerotic plaque leading to major adverse cardiac events. This paper provides an overview of the evidence-based reviews of various imaging modalities with regard to their potential value for comprehensive characterization of the composition, burden, and neovascularization of atherosclerotic plaque.

Real-time fluorescence image-guided oncologic surgery

Medical imaging plays a critical role in cancer diagnosis and planning. Many of these patients rely on surgical intervention for curative outcomes. This requires a careful identification of the primary and microscopic tumors, and the complete removal of cancer. Although there have been efforts to adapt traditional-imaging modalities for intraoperative image guidance, they suffer from several constraints such as large hardware footprint, high-operation cost, and disruption of the surgical workflow. Because of the ease of image acquisition, relatively low-cost devices and intuitive operation, optical imaging methods have received tremendous interests for use in real-time image-guided surgery. To improve imaging depth under low interference by tissue autofluorescence, many of these applications utilize light in the near-infrared (NIR) wavelengths, which is invisible to human eyes. With the availability of a wide selection of tumor-avid contrast agents, advancements in imaging sensors, electronic and optical designs, surgeons are able to combine different attributes of NIR optical imaging techniques to improve treatment outcomes. The emergence of diverse commercial and experimental image guidance systems, which are in various stages of clinical translation, attests to the potential high impact of intraoperative optical imaging methods to improve speed of oncologic surgery with high accuracy and minimal margin positivity.

Exploring coronary atherosclerosis with intravascular imaging

Coronary angiography has been widely used for five decades to evaluate a range of vascular pathologies and triage patients to therapeutic interventions. The inability to directly visualize the artery wall with conventional angiographic techniques has stimulated development of a number of intravascular imaging modalities. These approaches have the potential to provide a more comprehensive characterization of the burden, composition and functionality of atherosclerotic plaque, neointimal hyperplasia and allograft vasculopathy that develop within coronary arteries. The ability to use these modalities in vivo and in a serial fashion has provided a greater insight into the factors that underlie the disease process and guide therapeutic interventions.