Deep learning classification of ex vivo human colon tissues using spectroscopic optical coherence tomography.

Screening for colorectal cancer (CRC) with colonoscopy has improved patient outcomes; however, it remains the third leading cause of cancer-related mortality, novel strategies to improve screening are needed. Here, we propose an optical biopsy technique based on spectroscopic optical coherence tomography (OCT). Depth resolved OCT images are analyzed as a function of wavelength to measure optical tissue properties and used as input to machine learning algorithms. Previously, we used this approach to analyze mouse colon polyps. Here, we extend the approach to examine human biopsied colonic epithelial tissue samples ex vivo. Optical properties are used as input to a novel deep learning architecture, producing accuracy of up to 97.9% in discriminating tissue type. SOCT parameters are used to create false colored en face OCT images and deep learning classifications are used to enable visual classification by tissue type. This study advances SOCT toward clinical utility for analysis of colonic epithelium.

Recovery of angular scattering profiles through a flexible multimode fiber.

Endoscopic angle-resolved light scattering methods have been developed for early cancer detection but they typically require multi-element coherent fiber optic bundles to recover scattering distributions from tissues. Recent work has focused on using a single multimode fiber (MMF) to measure angle resolved scattering but this approach has practical limitations to overcome before clinical translation. Here we address these limitations by proposing an MMF-based endoscope capable of measuring angular scattering patterns suitable for determining structure. Significantly, this approach implements a spectrally resolved detection scheme to reduce speckle and leverages the azimuthal symmetry of the angular scattering patterns to enable measurements that are robust to fiber bending. This results in a unique method that does not require matrix inversion or machine learning to measure a transmitted scattering distribution. The MMF utilized here is 1000 mm in length with a 200 µm core and is demonstrated to recover angular scattering distributions even with bending displacements of up to 30 cm. This advance has a significant impact on the clinical translation of biomedical endoscopic diagnostic techniques that use angular scattering to determine the size of cell nuclei to detect early cancer.

Next-generation endoscopic probe for detection of esophageal dysplasia using combined OCT and angle-resolved low-coherence interferometry.

Angle-resolved low-coherence interferometry (a/LCI) is an optical technique that enables depth-specific measurements of nuclear morphology, with applications to detecting epithelial cancers in various organs. Previous a/LCI setups have been limited by costly fiber-optic components and large footprints. Here, we present a novel a/LCI instrument incorporating a channel for optical coherence tomography (OCT) to provide real-time image guidance. We showcase the system's capabilities by acquiring imaging data from in vivo Barrett's esophagus patients. The main innovation in this geometry lies in implementing a pathlength-matched single-mode fiber array, offering substantial cost savings while preserving signal fidelity. A further innovation is the introduction of a specialized side-viewing probe tailored for esophageal imaging, featuring miniature optics housed in a custom 3D-printed enclosure attached to the tip of the endoscope. The integration of OCT guidance enhances the precision of tissue targeting by providing real-time morphology imaging. This novel device represents a significant advancement in clinical translation of an enhanced screening approach for esophageal precancer, paving the way for more effective early-stage detection and intervention strategies.

Assessing cell viability with dynamic optical coherence microscopy.

Assessing cell viability is important in many fields of research. Current optical methods to assess cell viability typically involve fluorescent dyes, which are often less reliable and have poor permeability in primary tissues. Dynamic optical coherence microscopy (dOCM) is an emerging tool that provides label-free contrast reflecting changes in cellular metabolism. In this work, we compare the live contrast obtained from dOCM to viability dyes, and for the first time to our knowledge, demonstrate that dOCM can distinguish live cells from dead cells in murine syngeneic tumors. We further demonstrate a strong correlation between dOCM live contrast and optical redox ratio by metabolic imaging in primary mouse liver tissue. The dOCM technique opens a new avenue to apply label-free imaging to assess the effects of immuno-oncology agents, targeted therapies, chemotherapy, and cell therapies using live tumor tissues.

Deep learning classification of ex vivo human colon tissues using spectroscopic OCT.

Screening programs for colorectal cancer (CRC) have had a profound impact on the morbidity and mortality of this disease by detecting and removing early cancers and precancerous adenomas with colonoscopy. However, CRC continues to be the third leading cause of cancer-related mortality in both men and woman, partly because of limitations in colonoscopy-based screening. Thus, novel strategies to improve the efficiency and effectiveness of screening colonoscopy are urgently needed. Here, we propose to address this need using an optical biopsy technique based on spectroscopic optical coherence tomography (OCT). The depth resolved images obtained with OCT are analyzed as a function of wavelength to measure optical tissue properties. The optical properties can be used as input to machine learning algorithms as a means to classify adenomatous tissue in the colon. In this study, biopsied tissue samples from the colonic epithelium are analyzed ex vivo using spectroscopic OCT and tissue classifications are generated using a novel deep learning architecture, informed by machine learning methods including LSTM and KNN. The overall classification accuracy obtained was 88.9%, 76.0% and 97.9% in discriminating tissue type for these methods. Further, we apply an approach using false coloring of en face OCT images based on SOCT parameters and deep learning predictions to enable visual identification of tissue type. This study advances the spectroscopic OCT towards clinical utility for analyzing colonic epithelium for signs of adenoma.

Biophysical Profiling of Sickle Cell Disease Using Holographic Cytometry and Deep Learning.

Sickle cell disease (SCD) is an inherited hematological disorder associated with high mortality rates, particularly in sub-Saharan Africa. SCD arises due to the polymerization of sickle hemoglobin, which reduces flexibility of red blood cells (RBCs), causing blood vessel occlusion and leading to severe morbidity and early mortality rates if untreated. While sickle solubility tests are available to sub-Saharan African population as a means for detecting sickle hemoglobin (HbS), the test falls short in assessing the severity of the disease and visualizing the degree of cellular deformation. Here, we propose use of holographic cytometry (HC), a high throughput, label-free imaging modality, for comprehensive morphological profiling of RBCs as a means to detect SCD. For this study, more than 2.5 million single-cell holographic images from normal and SCD patient samples were collected using the HC system. We have developed an approach for specially defining training data to improve machine learning classification. Here, we demonstrate the deep learning classifier developed using this approach can produce highly accurate classification, even on unknown patient samples.

Multiscale optical phase fluctuations link disorder strength and fractal dimension of cell structure.

Optical methods for examining cellular structure based on endogenous contrast rely on analysis of refractive index changes to discriminate cell phenotype. These changes can be visualized using techniques such as phase contrast microscopy, detected by light scattering, or analyzed numerically using quantitative phase imaging. The statistical variations of refractive index at the nanoscale can be quantified using disorder strength, a metric seen to increase with neoplastic change. In contrast, the spatial organization of these variations is typically characterized using a fractal dimension, which is also seen to increase with cancer progression. Here, we seek to link these two measurements using multiscale measurements of optical phase to calculate disorder strength and in turn to determine the fractal dimension of the structures. First, quantitative phase images are analyzed to show that the disorder strength metric changes with resolution. The trend of disorder strength with length scales is analyzed to determine the fractal dimension of the cellular structures. Comparison of these metrics is presented for different cell lines with varying phenotypes including MCF10A, MCF7, BT474, HT-29, A431, and A549 cell lines, in addition to three cell populations with modified phenotypes. Our results show that disorder strength and fractal dimension can both be obtained with quantitative phase imaging and that these metrics can independently distinguish between different cell lines. Furthermore, their combined use presents a new approach for better understanding cellular restructuring during different pathways.

Spectroscopic optical coherence tomography for classification of colorectal cancer in a mouse model.

Noninvasive diagnosis of the malignant potential of colon polyps can improve prevention of colorectal cancer without the need for time-consuming and expensive biopsies. This study examines the use of spectroscopic optical coherence tomography (OCT) to classify tissue from genetically engineered mouse models of early-stage adenoma (APC) and advanced adenocarcinoma (AKP) in which tumors are induced in the distal colon. The optical tissue properties of scattering power and scattering attenuation coefficient are evaluated by analyzing the imaging data collected from tissues. Classifications are generated using 2D linear discriminant analysis with high levels of discrimination obtained. The overall classification accuracy obtained was 91.5%, with 100% sensitivity and 96.7% specificity in separating tumors from benign tissue, and 77.8% sensitivity and 99.4% specificity in separating adenocarcinoma from nonmalignant tissue. Thus, this study demonstrates the clinical potential of using spectroscopic OCT for rapid detection of colon adenoma and colorectal cancer.

Esophageal OCT Imaging Using a Paddle Probe Externally Attached to Endoscope.

BACKGROUND AND AIMS: Endoscopic surveillance of Barrett's esophagus (BE) by white light examination is insufficient to diagnose dysplastic change. In this work, we describe an optical imaging method to obtain high-resolution cross-sectional imaging using a paddle-shaped probe affixed to the endoscope tip. METHODS: We integrated Optical Coherence Tomography (OCT), an optical imaging method that produces cross-sectional images, into a paddle probe attached to video endoscope. We acquired images of esophageal epithelium from patients undergoing routine upper GI endoscopy. Images were classified by a reviewer blinded to patient identity and condition, and these results were compared with clinical diagnosis. RESULTS: We successfully captured epithelial OCT images from 30 patients and identified features consistent with both squamous epithelium and Barrett's esophagus. Our blinded image reviewer classified BE versus non-BE with 91.5% accuracy (65/71 image regions), including sensitivity of 84.6% for BE (11/13) and a specificity of 93.1% (54/58). However, in 16 patients, intubation of the probe into the esophagus could not be achieved. CONCLUSIONS: A paddle probe is a feasible imaging format for acquiring cross-sectional OCT images from the esophagus and can provide a structural assessment of BE and non-BE tissue. Probe form factor is the current limiting obstacle, but could be addressed by further miniaturization.

Connectivity-based deep learning approach for segmentation of the epithelium in in vivo human esophageal OCT images.

Optical coherence tomography (OCT) is used for diagnosis of esophageal diseases such as Barrett's esophagus. Given the large volume of OCT data acquired, automated analysis is needed. Here we propose a bilateral connectivity-based neural network for in vivo human esophageal OCT layer segmentation. Our method, connectivity-based CE-Net (Bicon-CE), defines layer segmentation as a combination of pixel connectivity modeling and pixel-wise tissue classification. Bicon-CE outperformed other widely used neural networks and reduced common topological prediction issues in tissues from healthy patients and from patients with Barrett's esophagus. This is the first end-to-end learning method developed for automatic segmentation of the epithelium in in vivo human esophageal OCT images.

Optical coherence tomography of small intestine allograft biopsies using a handheld surgical probe.

SIGNIFICANCE: The current gold standard for monitoring small intestinal transplant (IT) rejection is endoscopic visual assessment and biopsy of suspicious lesions; however, these lesions are only superficially visualized by endoscopy. Invasive biopsies provide a coarse sampling of tissue health without depicting the true presence and extent of any pathology. Optical coherence tomography (OCT) presents a potential alternative approach with significant advantages over traditional white-light endoscopy. AIM: The aim of our investigation was to evaluate OCT performance in distinguishing clinically relevant morphological features associated with IT graft failure. APPROACH: OCT was applied to evaluate the small bowel tissues of two rhesus macaques that had undergone IT of the ileum. The traditional assessment from routine histological observation was compared with OCT captured using a handheld surgical probe during the days post-transplant and subsequently was compared with histophaology. RESULTS: The reported OCT system was capable of identifying major biological landmarks in healthy intestinal tissue. Following IT, one nonhuman primate (NHP) model suffered a severe graft ischemia, and the second NHP graft failed due to acute cellular rejection. OCT images show visual evidence of correspondence with histological signs of IT rejection. CONCLUSIONS: Results suggest that OCT imaging has significant potential to reveal morphological changes associated with IT rejection and to improve patient outcomes overall.

Single Cell Analysis of Stored Red Blood Cells Using Ultra-High Throughput Holographic Cytometry.

Holographic cytometry is introduced as an ultra-high throughput implementation of quantitative phase imaging of single cells flowing through parallel microfluidic channels. Here, the approach was applied for characterizing the morphology of individual red blood cells during storage under regular blood bank conditions. Samples from five blood donors were examined, over 100,000 cells examined for each, at three time points. The approach allows high-throughput phase imaging of a large number of cells, greatly extending our ability to study cellular phenotypes using individual cell images. Holographic cytology images can provide measurements of multiple physical traits of the cells, including optical volume and area, which are observed to consistently change over the storage time. In addition, the large volume of cell imaging data can serve as training data for machine-learning algorithms. For the study here, logistic regression was used to classify the cells according to the storage time points. The analysis showed that at least 5000 cells are needed to ensure accuracy of the classifiers. Overall, results showed the potential of holographic cytometry as a diagnostic tool.

Deep learning classification of cervical dysplasia using depth-resolved angular light scattering profiles.

We present a machine learning method for detecting and staging cervical dysplastic tissue using light scattering data based on a convolutional neural network (CNN) architecture. Depth-resolved angular scattering measurements from two clinical trials were used to generate independent training and validation sets as input of our model. We report 90.3% sensitivity, 85.7% specificity, and 87.5% accuracy in classifying cervical dysplasia, showing the uniformity of classification of a/LCI scans across different instruments. Further, our deep learning approach significantly improved processing speeds over the traditional Mie theory inverse light scattering analysis (ILSA) method, with a hundredfold reduction in processing time, offering a promising approach for a/LCI in the clinic for assessing cervical dysplasia.

Deep imaging with 1.3†µm dual-axis optical coherence tomography and an enhanced depth of focus.

For many clinical applications, such as dermatology, optical coherence tomography (OCT) suffers from limited penetration depth due primarily to the highly scattering nature of biological tissues. Here, we present a novel implementation of dual-axis optical coherence tomography (DA-OCT) that offers improved depth penetration in skin imaging at 1.3 µm compared to conventional OCT. Several unique aspects of DA-OCT are examined here, including the requirements for scattering properties to realize the improvement and the limited depth of focus (DOF) inherent to the technique. To overcome this limitation, our approach uses a tunable lens to coordinate focal plane selection with image acquisition to create an enhanced DOF for DA-OCT. This improvement in penetration depth is quantified experimentally against conventional on-axis OCT using tissue phantoms and mouse skin. The results presented here suggest the potential use of DA-OCT in situations where a high degree of scattering limits depth penetration in OCT imaging.

A review of low-cost and portable optical coherence tomography.

Optical coherence tomography (OCT) is a powerful optical imaging technique capable of visualizing the internal structure of biological tissues at near cellular resolution. For years, OCT has been regarded as the standard of care in ophthalmology, acting as an invaluable tool for the assessment of retinal pathology. However, the costly nature of most current commercial OCT systems has limited its general accessibility, especially in low-resource environments. It is therefore timely to review the development of low-cost OCT systems as a route for applying this technology to population-scale disease screening. Low-cost, portable and easy to use OCT systems will be essential to facilitate widespread use at point of care settings while ensuring that they offer the necessary imaging performances needed for clinical detection of retinal pathology. The development of low-cost OCT also offers the potential to enable application in fields outside ophthalmology by lowering the barrier to entry. In this paper, we review the current development and applications of low-cost, portable and handheld OCT in both translational and research settings. Design and cost-reduction techniques are described for general low-cost OCT systems, including considerations regarding spectrometer-based detection, scanning optics, system control, signal processing, and the role of 3D printing technology. Lastly, a review of clinical applications enabled by low-cost OCT is presented, along with a detailed discussion of current limitations and outlook.

Prospective detection of cervical dysplasia with scanning angle-resolved low coherence interferometry.

We present a prospective clinical study using angle-resolved low-coherence interferometry (a/LCI) to detect cervical dysplasia via depth resolved nuclear morphology measurements. The study, performed at the Jacobi Medical Center, compares 80 a/LCI optical biopsies taken from 20 women with histopathological tissue diagnosis of co-registered physical biopsies. A novel instrument was used for this study that enables 2D scanning across the cervix without repositioning the probe. The main study goal was to compare performance with a previous clinical a/LCI point-probe instrument [Int. J. Cancer140, 1447 (2017)] and use the same diagnostic criteria as in that study. Tissue was classified in two schemes: non-dysplastic vs. dysplastic and low-risk vs. high-risk, with the latter classification aligned with clinically actionable diagnosis. High sensitivity (non-dysplastic vs. dysplastic: 0.903, low-risk vs. high-risk: 1.000) and NPV (0.930 and 1.000 respectively) were obtained when using the previously established decision boundaries, showing the success of the scanning a/LCI instrument and reinforcing the clinical viability of a/LCI in disease detection.

Spatial scanning of a sample with two-dimensional angle-resolved low-coherence interferometry for analysis of anisotropic scatterers.

Angle-resolved low-coherence interferometry (a/LCI) measures depth-resolved angular scattering for cell nuclear morphology analysis. 2D a/LCI, developed to collect across two scattering planes, is currently limited by the lack of spatial scanning. Here we demonstrate 2D a/LCI scanning across a three-dimensional volume using an image rotation scheme and a scanning mirror. Validation using various optical phantoms demonstrated excellent scatterer size determination over a 7.5 mm linear range, for a total accessible area of ∼44 mm2. Measurements from anisotropic scatterers allowed accurate determination of sizes and computation of aspect ratios. This scanning system will facilitate analysis of scatterer structure across wider tissue areas.

Multimodal Coherent Imaging of Retinal Biomarkers of Alzheimer's Disease in a Mouse Model.

We acquired depth-resolved light scattering measurements from the retinas of triple transgenic Alzheimer's Disease (3xTg-AD) mice and wild type (WT) age-matched controls using co-registered angle-resolved low-coherence interferometry (a/LCI) and optical coherence tomography (OCT). Angle-resolved light scattering measurements were acquired from the nerve fiber layer, outer plexiform layer, and retinal pigmented epithelium using image guidance and segmented thicknesses provided by co-registered OCT B-scans. Analysis of the OCT images showed a statistically significant thinning of the nerve fiber layer in AD mouse retinas compared to WT controls. The a/LCI scattering measurements provided complementary information that distinguishes AD mice by quantitatively characterizing tissue heterogeneity. The AD mouse retinas demonstrated higher mean and variance in nerve fiber layer light scattering intensity compared to WT controls. Further, the difference in tissue heterogeneity was observed through short-range spatial correlations that show greater slopes at all layers of interest for AD mouse retinas compared to WT controls. A greater slope indicates a faster loss of spatial correlation, suggesting a loss of tissue self-similarity characteristic of heterogeneity consistent with AD pathology. Use of this combined modality introduces unique tissue texture characterization to complement development of future AD biomarker analysis.

Reconstruction of angle-resolved backscattering through a multimode fiber for cell nuclei and particle size determination.

We demonstrate reconstruction of angle-resolved optical backscattering after transmission through a multimode fiber. Angle-resolved backscattering is an important tool for particle sizing, and has been developed as a diagnostic modality for detecting epithelial precancer. In this work, we fully characterized the transfer function of a multimode fiber using a plane-wave illumination basis across two dimensions. Once characterized, angle-resolved scattering information which has been scrambled by multimodal propagation can be easily and accurately reconstructed. Our technique was validated using a Mie theory-based inverse light scattering analysis (ILSA) algorithm on polystyrene microsphere phantoms of known sizes. To demonstrate the clinical potential of this approach, nuclear morphology was determined from the reconstructed angular backscattering from MCF-10A human mammary epithelial cell samples and validated against quantitative image analysis (QIA) of fluorescence microscopy images.

Quantitative phase imaging of erythrocytes under microfluidic constriction in a high refractive index medium reveals water content changes.

Changes in the deformability of red blood cells can reveal a range of pathologies. For example, cells which have been stored for transfusion are known to exhibit progressively impaired deformability. Thus, this aspect of red blood cells has been characterized previously using a range of techniques. In this paper, we show a novel approach for examining the biophysical response of the cells with quantitative phase imaging. Specifically, optical volume changes are observed as the cells transit restrictive channels of a microfluidic chip in a high refractive index medium. The optical volume changes indicate an increase of cell's internal density, ostensibly due to water displacement. Here, we characterize these changes over time for red blood cells from two subjects. By storage day 29, a significant decrease in the magnitude of optical volume change in response to mechanical stress was witnessed. The exchange of water with the environment due to mechanical stress is seen to modulate with storage time, suggesting a potential means for studying cell storage.