Automated prediction of isthmus areas in scar-related atrial tachycardias using artificial intelligence.

INTRODUCTION: Ablation of scar-related reentrant atrial tachycardia (SRRAT) involves identification and ablation of a critical isthmus. A graph convolutional network (GCN) is a machine learning structure that is well-suited to analyze the irregularly-structured data obtained in mapping procedures and may be used to identify potential isthmuses. METHODS: Electroanatomic maps from 29 SRRATs were collected, and custom electrogram features assessing key tissue and wavefront properties were calculated for each point. Isthmuses were labeled off-line. Training data was used to determine the optimal GCN parameters and train the final model. Putative isthmus points were predicted in the training and test populations and grouped into proposed isthmus areas based on density and distance thresholds. The primary outcome was the distance between the centroids of the true and closest proposed isthmus areas. RESULTS: A total of 193 821 points were collected. Thirty isthmuses were detected in 29 tachycardias among 25 patients (median age 65.0, 5 women). The median (IQR) distance between true and the closest proposed isthmus area centroids was 8.2 (3.5, 14.4) mm in the training and 7.3 (2.8, 16.1) mm in the test group. The mean overlap in areas, measured by the Dice coefficient, was 11.5 ± 3.2% in the training group and 13.9 ± 4.6% in the test group. CONCLUSION: A GCN can be trained to identify isthmus areas in SRRATs and may help identify critical ablation targets.

Robust, high-density lesion mapping in the left atrium with near-infrared spectroscopy.

Significance: Radiofrequency ablation (RFA) procedures for atrial fibrillation frequently fail to prevent recurrence, partially due to limitations in assessing extent of ablation. Optical spectroscopy shows promise in assessing RFA lesion formation but has not been validated in conditions resembling those in vivo. Aim: Catheter-based near-infrared spectroscopy (NIRS) was applied to porcine hearts to demonstrate that spectrally derived optical indices remain accurate in blood and at oblique incidence angles. Approach: Porcine left atria were ablated and mapped using a custom-fabricated NIRS catheter. Each atrium was mapped first in phosphate-buffered saline (PBS) then in porcine blood. Results: NIRS measurements showed little angle dependence up to 60 deg. A trained random forest model predicted lesions with a sensitivity of 81.7%, a specificity of 86.1%, and a receiver operating characteristic curve area of 0.921. Predicted lesion maps achieved a mean structural similarity index of 0.749 and a mean normalized inner product of 0.867 when comparing maps obtained in PBS and blood. Conclusions: Catheter-based NIRS can precisely detect RFA lesions on left atria submerged in blood. Optical parameters are reliable in blood and without perpendicular contact, confirming their ability to provide useful feedback during in vivo RFA procedures.

Compressed sensing on displacement signals measured with optical coherence tomography.

Optical coherence tomography (OCT) is capable of angstrom-scale vibrometry of particular interest to researchers of auditory mechanics. We develop a method for compressed sensing vibrometry using OCT that significantly reduces acquisition time for dense motion maps. Our method, based on total generalized variation with uniform subsampling, can reduce the number of samples needed to measure motion maps by a factor of ten with less than 5% normalized mean square error when tested on a diverse set of in vivo measurements from the gerbil cochlea. This opens up the possibility for more complex in vivo experiments for cochlear mechanics.

Compressed sensing of human breast optical coherence 3-D image volume data using predictive coding.

There are clinical needs for optical coherence tomography (OCT) of large areas within a short period of time, such as imaging resected breast tissue for the evaluation of cancer. We report on the use of denoising predictive coding (DN-PC), a novel compressed sensing (CS) algorithm for reconstruction of OCT volumes of human normal breast and breast cancer tissue. The DN-PC algorithm has been rewritten to allow for computational parallelization and efficient memory transfer, resulting in a net reduction of computation time by a factor of 20. We compress image volumes at decreasing A-line sampling rates to evaluate a relation between reconstruction behavior and image features of breast tissue.

Automated analysis framework for in vivo cardiac ablation therapy monitoring with optical coherence tomography.

Radiofrequency ablation (RFA) is a minimally invasive procedure that is commonly used for the treatment of atrial fibrillation. However, it is associated with a significant risk of arrhythmia recurrence and complications owing to the lack of direct visualization of cardiac substrates and real-time feedback on ablation lesion transmurality. Within this manuscript, we present an automated deep learning framework for in vivo intracardiac optical coherence tomography (OCT) analysis of swine left atria. Our model can accurately identify cardiac substrates, monitor catheter-tissue contact stability, and assess lesion transmurality on both OCT intensity and polarization-sensitive OCT data. To the best of our knowledge, we have developed the first automatic framework for in vivo cardiac OCT analysis, which holds promise for real-time monitoring and guidance of cardiac RFA therapy..

Monitoring of irrigated lesion formation with single fiber based multispectral system using machine learning.

In radiofrequency ablation (RFA) treatment of cardiac arrhythmias, intraprocedural assessment of treatment efficacy relies on indirect measures of adequate tissue destruction. Direct sensing of diffuse reflectance spectral changes at the ablation site using optically integrated RFA catheters has been shown to enable accurate prediction of lesion dimensions, ex vivo. Challenges of optical guidance can be due to obtaining reliable measurements under various catheter-tissue contact orientations. In this work, addressed this limitation by assessing the feasibility of monitoring lesion progression using single-fiber reflectance spectroscopy (SFRS). A total of 110 endocardial lesions of various sizes were generated in freshly excised swine right ventricular tissue using a custom-built, irrigated SFRS-RFA catheter. Models were developed for assessing catheter-tissue contact, the presence of nontransmural or transmural lesions and lesion depth percentage. These results support the use of SFRS-based catheters for irrigated lesion assessment and motivate further exploration of using multi-SFRS catheters for omnidirectionality.

Cardiac endocardial left atrial substrate and lesion depth mapping using near-infrared spectroscopy.

Atrial fibrillation (AF) is a rapid irregular electrical activity in the upper chamber and the most common sustained cardiac arrhythmia. Many patients require radiofrequency ablation (RFA) therapy to restore sinus rhythm. Pulmonary vein isolation requires distinguishing normal atrial wall from the pulmonary vein tissue, and atrial substrate ablation requires differentiating scar tissue, fibrosis, and adipose tissue. However, current anatomical mapping methods for strategically locating ablation sites by identifying structural substrates in real-time are limited. An intraoperative tool that accurately provides detailed structural information and classifies endocardial substrates could help improve RF guidance during RF ablation therapy. In this work, we propose a 7F NIRS integrated ablation catheter and demonstrate endocardial mapping on ex vivo swine (n = 12) and human (n = 5) left atrium (LA). First, pulmonary vein (PV) sleeve, fibrosis and ablation lesions were identified with NIRS-derived contrast indices. Based on these key spectral features, classification algorithms identified endocardial substrates with high accuracy (<11% error). Then, a predictive model for lesion depth was evaluated on classified lesions. Model predictions correlated well with histological measurements of lesion dimensions (R = 0.984). Classified endocardial substrates and lesion depth were represented in 2D spatial maps. These results suggest NIRS integrated mapping catheters can serve as a complementary tool to the current electroanatomical mapping system to improve treatment efficacy.

Millimeter-scale chip-based supercontinuum generation for optical coherence tomography.

Supercontinuum sources for optical coherence tomography (OCT) have raised great interest as they provide broad bandwidth to enable high resolution and high power to improve imaging sensitivity. Commercial fiber-based supercontinuum systems require high pump powers to generate broad bandwidth and customized optical filters to shape/attenuate the spectra. They also have limited sensitivity and depth performance. We introduce a supercontinuum platform based on a 1-mm2 Si3N4 photonic chip for OCT. We directly pump and efficiently generate supercontinuum near 1300 nm without any postfiltering. With a 25-pJ pump pulse, we generate a broadband spectrum with a flat 3-dB bandwidth of 105 nm. Integrating the chip into a spectral domain OCT system, we achieve 105-dB sensitivity and 1.81-mm 6-dB sensitivity roll-off with 300-µW optical power on sample. We image breast tissue to demonstrate strong imaging performance. Our chip will pave the way toward portable OCT and incorporating integrated photonics into optical imaging technologies.

3-D compressed sensing optical coherence tomography using predictive coding.

We present a compressed sensing (CS) algorithm and sampling strategy for reconstructing 3-D Optical Coherence Tomography (OCT) image volumes from as little as 10% of the original data. Reconstruction using the proposed method, Denoising Predictive Coding (DN-PC), is demonstrated for five clinically relevant tissue types including human heart, retina, uterus, breast, and bovine ligament. DN-PC reconstructs the difference between adjacent b-scans in a volume and iteratively applies Gaussian filtering to improve image sparsity. An a-line sampling strategy was developed that can be easily implemented in existing Spectral-Domain OCT systems and reduce scan time by up to 90%.

Anisotropic Mechanical Properties of the Human Uterus Measured by Spherical Indentation.

The mechanical function of the uterus is critical for a successful pregnancy. During gestation, uterine tissue grows and stretches to many times its size to accommodate the growing fetus, and it is hypothesized the magnitude of uterine tissue stretch triggers the onset of contractions. To establish rigorous mechanical testing protocols for the human uterus in hopes of predicting tissue stretch during pregnancy, this study measures the anisotropic mechanical properties of the human uterus using optical coherence tomography (OCT), instrumented spherical indentation, and video extensometry. In this work, we perform spherical indentation and digital image correlation to obtain the tissue's force and deformation response to a ramp-hold loading regimen. We translate previously reported fiber architecture, measured via optical coherence tomography, into a constitutive fiber composite material model to describe the equilibrium material behavior during indentation. We use an inverse finite element method integrated with a genetic algorithm (GA) to fit the material model to our experimental data. We report the mechanical properties of human uterine specimens taken across different anatomical locations and layers from one non-pregnant (NP) and one pregnant (PG) patient; both patients had pathological uterine tissue. Compared to NP uterine tissue, PG tissue has a more dispersed fiber distribution and equivalent stiffness material parameters. In both PG and NP uterine tissue, the mechanical properties differ significantly between anatomical locations.

Three-dimensional collagen fiber mapping and tractography of human uterine tissue using OCT.

Automatic quantification and visualization of 3-D collagen fiber architecture using Optical Coherence Tomography (OCT) has previously relied on polarization information and/or prior knowledge of tissue-specific fiber architecture. This study explores image processing, enhancement, segmentation, and detection algorithms to map 3-D collagen fiber architecture from OCT images alone. 3-D fiber mapping, histogram analysis, and 3-D tractography revealed fiber groupings and macro-organization previously unseen in uterine tissue samples. We applied our method on centimeter-scale mosaic OCT volumes of uterine tissue blocks from pregnant and non-pregnant specimens revealing a complex, patient-specific network of fibrous collagen and myocyte bundles.

Feasibility of near-infrared spectroscopy as a tool for anatomical mapping of the human epicardium.

Epicardial ablation is necessary for the treatment of ventricular tachycardias refractory to endocardial ablation due to arrhythmic substrates involving the epicardium. The human epicardium is composed of adipose tissue and coronary vasculature embedded on the surface and within the myocardium, which can complicate electroanatomical mapping, electrogram interpretation and ablation delivery. We propose using near-infrared spectroscopy (NIRS) to decipher adipose tissue from myocardial tissue within human hearts ex vivo. Histological measurement of epicardial adipose thickness direct correlated (R = 0.884) with the adipose contrast index. These results demonstrate the potential of NIRS integrated catheters for mapping the spatial distribution of epicardial substrates and could aid in improving guidance during epicardial ablation interventions.

Fully Automated Postlumpectomy Breast Margin Assessment Utilizing Convolutional Neural Network Based Optical Coherence Tomography Image Classification Method.

BACKGROUND: The purpose of this study was to develop a deep learning classification approach to distinguish cancerous from noncancerous regions within optical coherence tomography (OCT) images of breast tissue for potential use in an intraoperative setting for margin assessment. METHODS: A custom ultrahigh-resolution OCT (UHR-OCT) system with an axial resolution of 2.7 µm and a lateral resolution of 5.5 µm was used in this study. The algorithm used an A-scan-based classification scheme and the convolutional neural network (CNN) was implemented using an 11-layer architecture consisting of serial 3 × 3 convolution kernels. Four tissue types were classified, including adipose, stroma, ductal carcinoma in situ, and invasive ductal carcinoma. RESULTS: The binary classification of cancer versus noncancer with the proposed CNN achieved 94% accuracy, 96% sensitivity, and 92% specificity. The mean five-fold validation F1 score was highest for invasive ductal carcinoma (mean standard deviation, 0.89 ± 0.09) and adipose (0.79 ± 0.17), followed by stroma (0.74 ± 0.18), and ductal carcinoma in situ (0.65 ± 0.15). CONCLUSION: It is feasible to use CNN based algorithm to accurately distinguish cancerous regions in OCT images. This fully automated method can overcome limitations of manual interpretation including interobserver variability and speed of interpretation and may enable real-time intraoperative margin assessment.

Imaging of subendocardial adipose tissue and fiber orientation distributions in the human left atrium using optical coherence tomography.

BACKGROUND: Optical coherence tomography (OCT) has the potential to provide real-time imaging guidance for atrial fibrillation ablation, with promising results for lesion monitoring. OCT can also offer high-resolution imaging of tissue composition, but there is insufficient cardiac OCT data to inform the use of OCT to reveal important tissue architecture of the human left atrium. Thus, the objective of this study was to define OCT imaging data throughout the human left atrium, focusing on the distribution of adipose tissue and fiber orientation as seen from the endocardium. METHODS AND RESULTS: Human hearts (n = 7) were acquired for imaging the left atrium with OCT. A spectral-domain OCT system with 1325 nm center wavelength, 6.5 µm axial resolution, 15 µm lateral resolution, and a maximum imaging depth of 2.51 mm in the air was used. Large-scale OCT image maps of human left atrial tissue were developed, with adipose thickness and fiber orientation extracted from the imaging data. OCT imaging showed scattered distributions of adipose tissue around the septal and pulmonary vein regions, up to a depth of about 0.43 mm from the endocardial surface. The total volume of adipose tissue detected by OCT over one left atrium ranged from 1.42 to 28.74 mm3 . Limited fiber orientation information primarily around the pulmonary veins and the septum could be identified. CONCLUSION: OCT imaging could provide adjunctive information on the distribution of subendocardial adipose tissue, particularly around thin areas around the pulmonary veins and septal regions. Variations in OCT-detected tissue composition could potentially assist ablation guidance.

Chip-based frequency comb sources for optical coherence tomography.

Optical coherence tomography (OCT) is a powerful interferometric imaging technique widely used in medical fields such as ophthalmology, cardiology and dermatology. Superluminescent diodes (SLDs) are widely used as light sources in OCT. Recently integrated chip-based frequency combs have been demonstrated in numerous platforms and the possibility of using these broadband chip-scale combs for OCT has been raised extensively over the past few years. However, the use of these chip-based frequency combs as light sources for OCT requires bandwidth and power compatibility with current OCT systems and have not been shown to date. Here we generate frequency combs based on chip-scale lithographically-defined microresonators and demonstrate its capability as a novel light source for OCT. The combs are designed with a small spectral line spacing of 0.21 nm which ensure imaging range comparable to commercial system and operated at non-phase locked regime which provide conversion efficiency of 30%. The comb source is shown to be compatible with a standard commercial spectral domain (SD) OCT system and enables imaging of human tissue with image quality comparable to the one achieved with tabletop commercial sources. The comb source also provides a path towards fully integrated OCT systems.

Characterization of the human myocardium by optical coherence tomography.

Imaging of cardiac tissue structure plays a critical role in the treatment and understanding of cardiovascular disease. Optical coherence tomography (OCT) offers the potential to provide valuable, high-resolution imaging of cardiac tissue. However, there is a lack of comprehensive OCT imaging data of the human heart, which could improve identification of structural substrates underlying cardiac abnormalities. The objective of this study was to provide qualitative and quantitative analysis of OCT image features throughout the human heart. Fifty human hearts were acquired, and tissues from all chambers were imaged with OCT. Histology was obtained to verify tissue composition. Statistical differences between OCT image features corresponding to different tissue types and chambers were estimated using analysis of variance. OCT imaging provided features that were able to distinguish structures such as thickened collagen, as well as adipose tissue and fibrotic myocardium. Statistically significant differences were found between atria and ventricles in attenuation coefficient, and between adipose and all other tissue types. This study provides an overview of OCT image features throughout the human heart, which can be used for guiding future applications such as OCT-integrated catheter-based treatments or ex vivo investigation of structural substrates.

Anisotropic Material Characterization of Human Cervix Tissue Based on Indentation and Inverse Finite Element Analysis.

The cervix is essential to a healthy pregnancy as it must bear the increasing load caused by the growing fetus. Preterm birth is suspected to be caused by the premature softening and mechanical failure of the cervix. The objective of this paper is to measure the anisotropic mechanical properties of human cervical tissue using indentation and video extensometry. The human cervix is a layered structure, where its thick stromal core contains preferentially aligned collagen fibers embedded in a soft ground substance. The fiber composite nature of the tissue provides resistance to the complex three-dimensional loading environment of pregnancy. In this work, we detail an indentation mechanical test to obtain the force and deformation response during loading which closely matches in vivo conditions. We postulate a constitutive material model to describe the equilibrium material behavior to ramp-hold indentation, and we use an inverse finite element method based on genetic algorithm (GA) optimization to determine best-fit material parameters. We report the material properties of human cervical slices taken at different anatomical locations from women of different obstetric backgrounds. In this cohort of patients, the anterior internal os (the area where the cervix meets the uterus) of the cervix is stiffer than the anterior external os (the area closest to the vagina). The anatomic anterior and posterior quadrants of cervical tissue are more anisotropic than the left and right quadrants. There is no significant difference in material properties between samples of different parities (number of pregnancies reaching viable gestation age).

Optical coherence tomography imaging of cardiac substrates.

Cardiovascular disease is the leading cause of morbidity and mortality in the United States. Knowledge of a patient's heart structure will help to plan procedures, potentially identifying arrhythmia substrates, critical structures to avoid, detect transplant rejection, and reduce ambiguity when interpreting electrograms and functional measurements. Similarly, basic research of numerous cardiac diseases would greatly benefit from structural imaging at cellular scale. For both applications imaging on the scale of a myocyte is needed, which is approximately 100 µm × 10 µm. The use of optical coherence tomography (OCT) as a tool for characterizing cardiac tissue structure and function has been growing in the past two decades. We briefly review OCT principles and highlight important considerations when imaging cardiac muscle. In particular, image penetration, tissue birefringence, and light absorption by blood during in vivo imaging are important factors when imaging the heart with OCT. Within the article, we highlight applications of cardiac OCT imaging including imaging heart tissue structure in small animal models, quantification of myofiber organization, monitoring of radiofrequency ablation (RFA) lesion formation, structure-function analysis enabled by functional extensions of OCT and multimodal analysis and characterizing important substrates within the human heart. The review concludes with a summary and future outlook of OCT imaging the heart, which is promising with progress in optical catheter development, functional extensions of OCT, and real time image processing to enable dynamic imaging and real time tracking during therapeutic procedures.

Towards real-time multispectral endoscopic imaging for cardiac lesion quality assessment.

Atrial fibrillation (Afib) can lead to life threatening conditions such as heart failure and stroke. During Afib treatment, clinicians aim to repress unusual electrical activity by electrically isolating the pulmonary veins (PV) from the left atrium (LA) using radiofrequency ablation. However, current clinical tools are limited in reliably assessing transmurality of the ablation lesions and detecting the presence of gaps within ablation lines, which can warrant repeat procedures. In this study, we developed an endoscopic multispectral reflectance imaging (eMSI) system for enhanced discrimination of tissue treatment at the PV junction. The system enables direct visualization of cardiac lesions through an endoscope at acquisition rates up to 25 Hz. Five narrowband, high-power LEDs were used to illuminate the sample (450, 530, 625, 810 and 940nm) and combinatory parameters were calculated based on their relative reflectance. A stitching algorithm was employed to generate large field-of-view, multispectral mosaics of the ablated PV junction from individual eMSI images. A total of 79 lesions from 15 swine hearts were imaged, ex vivo. Statistical analysis of the acquired five spectral data sets and ratiometric maps revealed significant differences between transmural lesions, non-transmural lesions around the venoatrial junctions, unablated posterior wall of left atrium tissue, and pulmonary vein (p < 0.0001). A pixel-based quadratic discriminant analysis classifier was applied to distinguish four tissue types: PV, untreated LA, non-transmural and transmural lesions. We demonstrate tissue type classification accuracies of 80.2% and 92.1% for non-transmural and transmural lesions, and 95.0% and 92.8% for PV and untreated LA sites, respectively. These findings showcase the potential of eMSI for lesion validation and may help to improve AFib treatment efficacy.

High-speed collagen fiber modeling and orientation quantification for optical coherence tomography imaging.

Quantifying collagen fiber architecture has clinical and scientific relevance across a variety of tissue types and adds functionality to otherwise largely qualitative imaging modalities. Optical coherence tomography (OCT) is uniquely suited for this task due to its ability to capture the collagen microstructure over larger fields of view than traditional microscopy. Existing image processing techniques for quantifying fiber architecture, while accurate and effective, are very slow for processing large datasets and tend to lack structural specificity. We describe here a computationally efficient method for quantifying and visualizing collagen fiber organization. The algorithm is demonstrated on swine atria, bovine anterior cruciate ligament, and human cervical tissue samples. Additionally, we show an improved performance for images with crimped fiber textures and low signal to noise when compared to similar methods.