Automated algorithm for breast tissue differentiation in optical coherence tomography

Large Area Kidney Imaging for Pre-transplant Evaluation using Real-Time Robotic Optical Coherence Tomography

Optical coherence tomography (OCT) is a high-resolution imaging modality that can be used to image microstructures of human kidneys. These images can be analyzed to evaluate the viability of the organ for transplantation. However, current OCT devices suffer from insufficient field-of-view, leading to biased examination outcomes when only small portions of the kidney can be assessed. Here we present a robotic OCT system where an OCT probe is integrated with a robotic manipulator, enabling wider area spatially-resolved imaging. With the proposed system, it becomes possible to comprehensively scan the kidney surface and provide large area parameterization of the microstructures. We verified the probe tracking accuracy with a phantom as 0.0762±0.0727 mm and demonstrated its clinical feasibility by scanning ex vivo kidneys. The parametric map exhibits fine vasculatures beneath the kidney surface. Quantitative analysis on the proximal convoluted tubule from the ex vivo human kidney yields highly clinical-relevant information.

Advancements in Intraoperative Near-Infrared Fluorescence Imaging for Accurate Tumor Resection: A Promising Technique for Improved Surgical Outcomes and Patient Survival

Clear surgical margins for solid tumor resection are essential for preventing cancer recurrence and improving overall patient survival. Complete resection of tumors is often limited by a surgeon's ability to accurately locate malignant tissues and differentiate them from healthy tissue. Therefore, techniques or imaging modalities are required that would ease the identification and resection of tumors by real-time intraoperative visualization of tumors. Although conventional imaging techniques such as positron emission tomography (PET), computed tomography (CT), magnetic resonance imaging (MRI), or radiography play an essential role in preoperative diagnostics, these cannot be utilized in intraoperative tumor detection due to their large size, high cost, long imaging time, and lack of cancer specificity. The inception of several imaging techniques has paved the way to intraoperative tumor margin detection with a high degree of sensitivity and specificity. Particularly, molecular imaging using near-infrared fluorescence (NIRF) based nanoprobes provides superior imaging quality due to high signal-to-noise ratio, deep penetration to tissues, and low autofluorescence, enabling accurate tumor resection and improved survival rates. In this review, we discuss the recent developments in imaging technologies, specifically focusing on NIRF nanoprobes that aid in highly specific intraoperative surgeries with real-time recognition of tumor margins.

Multi-class classification of breast tissue using optical coherence tomography and attenuation imaging combined via deep learning

We demonstrate a convolutional neural network (CNN) for multi-class breast tissue classification as adipose tissue, benign dense tissue, or malignant tissue, using multi-channel optical coherence tomography (OCT) and attenuation images, and a novel Matthews correlation coefficient (MCC)-based loss function that correlates more strongly with performance metrics than the commonly used cross-entropy loss. We hypothesized that using multi-channel images would increase tumor detection performance compared to using OCT alone. 5,804 images from 29 patients were used to fine-tune a pre-trained ResNet-18 network. Adding attenuation images to OCT images yields statistically significant improvements in several performance metrics, including benign dense tissue sensitivity (68.0% versus 59.6%), malignant tissue positive predictive value (PPV) (79.4% versus 75.5%), and total accuracy (85.4% versus 83.3%), indicating that the additional contrast from attenuation imaging is most beneficial for distinguishing between benign dense tissue and malignant tissue.

Three-dimensional mapping of the attenuation coefficient in optical coherence tomography to enhance breast tissue microarchitecture contrast

Effective intraoperative tumor margin assessment is needed to reduce re-excision rates in breast-conserving surgery (BCS). Mapping the attenuation coefficient in optical coherence tomography (OCT) throughout a sample to create an image (attenuation imaging) is one promising approach. For the first time, three-dimensional OCT attenuation imaging of human breast tissue microarchitecture using a wide-field (up to ~45 × 45 × 3.5 mm) imaging system is demonstrated. Representative results from three mastectomy and one BCS specimen (from 31 specimens) are presented with co-registered postoperative histology. Attenuation imaging is shown to provide substantially improved contrast over OCT, delineating nuanced features within tumors (including necrosis and variations in tumor cell density and growth patterns) and benign features (such as sclerosing adenosis). Additionally, quantitative micro-elastography (QME) images presented alongside OCT and attenuation images show that these techniques provide complementary contrast, suggesting that multimodal imaging could increase tissue identification accuracy and potentially improve tumor margin assessment.

Intraoperative margin assessment of human breast tissue in optical coherence tomography images using deep neural networks

Assessing the surgical margin during breast lumpectomy operations can avoid the need for additional surgery. Optical coherence tomography (OCT) is an imaging technique that has been proven to be efficient for this purpose. However, to avoid overloading the surgeon during the operation, automatic cancer detection at the surface of the removed tissue is needed. This work explores automated margin assessment on a sample of patient data collected at the Pathology Department, Severance Hospital (Seoul, South Korea). Some methods based on the spatial statistics of the images have been developed, but the obtained results are still far from human performance. In this work, we investigate the possibility to use deep neural networks (DNNs) for real time margin assessment, demonstrating performance significantly better than the reported literature and close to the level of a human expert. Since the goal is to detect the presence of cancer, a patch-based classification method is proposed, as it is sufficient for detection, and requires training data that is easier and cheaper to collect than for other approaches such as segmentation. For that purpose, we train a DNN architecture that was proved to be efficient for small images on patches extracted from images containing only cancer or only normal tissue as determined by pathologists in a university hospital. As the number of available images in all such studies is by necessity small relative to other deep network applications such as ImageNet, a good regularization method is needed. In this work, we propose to use a recently introduced function norm regularization that attempts to directly control the function complexity, in contrast to classical approaches such as weight decay and DropOut. As neither the code nor the data of previous results are publicly available, the obtained results are compared with reported results in the literature for a conservative comparison. Moreover, our method is applied to locally collected data on several data configurations. The reported results are the average over the different trials. The experimental results show that the use of DNNs yields significantly better results than other techniques when evaluated in terms of sensitivity, specificity, F1 score, G-mean and Matthews correlation coefficient. Function norm regularization yielded higher and more robust results than competing regularization methods. We have demonstrated a system that shows high promise for (partially) automated margin assessment of human breast tissue, Equal error rate (EER) is reduced from approximately 12% (the lowest reported in the literature) to 5% - a 58% reduction. The method is computationally feasible for intraoperative application (less than 2 s per image) at the only cost of a longer offline training time.

Investigation of tissue cellularity at the tip of the core biopsy needle with optical coherence tomography

We report the development and the pre-clinical testing of a new technology based on optical coherence tomography (OCT) for investigating tissue composition at the tip of the core biopsy needle. While ultrasound, computed tomography, and magnetic resonance imaging are routinely used to guide needle placement within a tumor, they still do not provide the resolution needed to investigate tissue cellularity (ratio between viable tumor and benign stroma) at the needle tip prior to taking a biopsy core. High resolution OCT imaging, however, can be used to investigate tissue morphology at the micron scale, and thus to determine if the biopsy core would likely have the expected composition. Therefore, we implemented this capability within a custom-made biopsy gun and evaluated its capability for a correct estimation of tumor tissue cellularity. A pilot study on a rabbit model of soft tissue cancer has shown the capability of this technique to provide correct evaluation of tumor tissue cellularity in over 85% of the cases. These initial results indicate the potential benefit of the OCT-based approach for improving the success of the core biopsy procedures.

Review of optical coherence tomography in oncology

The application of optical coherence tomography (OCT) in the field of oncology has been prospering over the past decade. OCT imaging has been used to image a broad spectrum of malignancies, including those arising in the breast, brain, bladder, the gastrointestinal, respiratory, and reproductive tracts, the skin, and oral cavity, among others. OCT imaging has initially been applied for guiding biopsies, for intraoperatively evaluating tumor margins and lymph nodes, and for the early detection of small lesions that would often not be visible on gross examination, tasks that align well with the clinical emphasis on early detection and intervention. Recently, OCT imaging has been explored for imaging tumor cells and their dynamics, and for the monitoring of tumor responses to treatments. This paper reviews the evolution of OCT technologies for the clinical application of OCT in surgical and noninvasive interventional oncology procedures and concludes with a discussion of the future directions for OCT technologies, with particular emphasis on their applications in oncology.

Tissue characterization with depth-resolved attenuation coefficient and backscatter term in intravascular optical coherence tomography images

An important application of intravascular optical coherence tomography (IVOCT) for atherosclerotic tissue analysis is using it to estimate attenuation and backscatter coefficients. This work aims at exploring the potential of the attenuation coefficient, a proposed backscatter term, and image intensities in distinguishing different atherosclerotic tissue types with a robust implementation of depth-resolved (DR) approach. Therefore, the DR model is introduced to estimate the attenuation coefficient and further extended to estimate the backscatter-related term in IVOCT images, such that values can be estimated per pixel without predefining any delineation for the estimation. In order to exclude noisy regions with a weak signal, an automated algorithm is implemented to determine the cut-off border in IVOCT images. The attenuation coefficient, backscatter term, and the image intensity are further analyzed in regions of interest, which have been delineated referring to their pathology counterparts. Local statistical values were reported and their distributions were further compared with a two-sample t-test to evaluate the potential for distinguishing six types of tissues. Results show that the IVOCT intensity, DR attenuation coefficient, and backscatter term extracted with the reported implementation are complementary to each other on characterizing six tissue types: mixed, calcification, fibrous, lipid-rich, macrophages, and necrotic core.

Visualization and tissue classification of human breast cancer images using ultrahigh-resolution OCT

BACKGROUND AND OBJECTIVE

Breast cancer is one of the most common cancers, and recognized as the third leading cause of mortality in women. Optical coherence tomography (OCT) enables three dimensional visualization of biological tissue with micrometer level resolution at high speed, and can play an important role in early diagnosis and treatment guidance of breast cancer. In particular, ultra-high resolution (UHR) OCT provides images with better histological correlation. This paper compared UHR OCT performance with standard OCT in breast cancer imaging qualitatively and quantitatively. Automatic tissue classification algorithms were used to automatically detect invasive ductal carcinoma in ex vivo human breast tissue.

STUDY DESIGN/MATERIALS AND METHODS

Human breast tissues, including non-neoplastic/normal tissues from breast reduction and tumor samples from mastectomy specimens, were excised from patients at Columbia University Medical Center. The tissue specimens were imaged by two spectral domain OCT systems at different wavelengths: a home-built ultra-high resolution (UHR) OCT system at 800 nm (measured as 2.72 μm axial and 5.52 μm lateral) and a commercial OCT system at 1,300 nm with standard resolution (measured as 6.5 μm axial and 15 μm lateral), and their imaging performances were analyzed qualitatively. Using regional features derived from OCT images produced by the two systems, we developed an automated classification algorithm based on relevance vector machine (RVM) to differentiate hollow-structured adipose tissue against solid tissue. We further developed B-scan based features for RVM to classify invasive ductal carcinoma (IDC) against normal fibrous stroma tissue among OCT datasets produced by the two systems. For adipose classification, 32 UHR OCT B-scans from 9 normal specimens, and 28 standard OCT B-scans from 6 normal and 4 IDC specimens were employed. For IDC classification, 152 UHR OCT B-scans from 6 normal and 13 IDC specimens, and 104 standard OCT B-scans from 5 normal and 8 IDC specimens were employed.

RESULTS

We have demonstrated that UHR OCT images can produce images with better feature delineation compared with images produced by 1,300 nm OCT system. UHR OCT images of a variety of tissue types found in human breast tissue were presented. With a limited number of datasets, we showed that both OCT systems can achieve a good accuracy in identifying adipose tissue. Classification in UHR OCT images achieved higher sensitivity (94%) and specificity (93%) of adipose tissue than the sensitivity (91%) and specificity (76%) in 1,300 nm OCT images. In IDC classification, similarly, we achieved better results with UHR OCT images, featured an overall accuracy of 84%, sensitivity of 89% and specificity of 71% in this preliminary study.

CONCLUSION

In this study, we provided UHR OCT images of different normal and malignant breast tissue types, and qualitatively and quantitatively studied the texture and optical features from OCT images of human breast tissue at different resolutions. We developed an automated approach to differentiate adipose tissue, fibrous stroma, and IDC within human breast tissues. Our work may open the door toward automatic intraoperative OCT evaluation of early-stage breast cancer. Lasers Surg. Med. 49:258-269, 2017. © 2017 Wiley Periodicals, Inc.

Depth-resolved imaging of colon tumor using optical coherence tomography and fluorescence laminar optical tomography

Early detection of neoplastic changes remains a critical challenge in clinical cancer diagnosis and treatment. Many cancers arise from epithelial layers such as those of the gastrointestinal (GI) tract. Current standard endoscopic technology is difficult to detect the subsurface lesions. In this research, we investigated the feasibility of a novel multi-modal optical imaging approach including high-resolution optical coherence tomography (OCT) and high-sensitivity fluorescence laminar optical tomography (FLOT) for structural and molecular imaging. The C57BL/6J-Apc^Min/J mice were imaged using OCT and FLOT, and the correlated histopathological diagnosis was obtained. Quantitative structural (scattering coefficient) and molecular (relative enzyme activity) parameters were obtained from OCT and FLOT images for multi-parametric analysis. This multi-modal imaging method has demonstrated the feasibility for more accurate diagnosis with 88.23% (82.35%) for sensitivity (specificity) compared to either modality alone. This study suggested that combining OCT and FLOT is promising for subsurface cancer detection, diagnosis, and characterization.

Automated classification of optical coherence tomography images of human atrial tissue

Tissue composition of the atria plays a critical role in the pathology of cardiovascular disease, tissue remodeling, and arrhythmogenic substrates. Optical coherence tomography (OCT) has the ability to capture the tissue composition information of the human atria. In this study, we developed a region-based automated method to classify tissue compositions within human atria samples within OCT images. We segmented regional information without prior information about the tissue architecture and subsequently extracted features within each segmented region. A relevance vector machine model was used to perform automated classification. Segmentation of human atrial ex vivo datasets was correlated with trichrome histology and our classification algorithm had an average accuracy of 80.41% for identifying adipose, myocardium, fibrotic myocardium, and collagen tissue compositions.

Innovations in Intraoperative Tumor Visualization

In the surgical management of solid tumors, adequacy of tumor resection has implications for local recurrence and survival. The standard method of intraoperative identification of tumor margin is frozen section pathologic analysis, which is time-consuming with potential for sampling error. Intraoperative tumor visualization has the potential to significantly improve surgical cancer care across disciplines, by guiding accuracy of biopsies, increasing adequacy of resections, directing adjuvant therapy, and even providing diagnostic information. We provide an outline of various methods of intraoperative tumor visualization developed to aid in the real-time assessment of tumor extent and adequacy of resection.

An overview of optical coherence tomography for ovarian tissue imaging and characterization

Ovarian cancer has the lowest survival rate among all the gynecologic cancers because it is predominantly diagnosed at late stages due to the lack of reliable symptoms and efficacious screening techniques. Optical coherence tomography (OCT) is an emerging technique that provides high-resolution images of biological tissue in real time, and demonstrates great potential for imaging of ovarian tissue. In this article, we review OCT studies for visualization and diagnosis of human ovaries as well as quantitative extraction of ovarian tissue optical properties for classifying normal and malignant ovaries. OCT combined with other imaging modalities to further improve ovarian tissue diagnosis is also reviewed.

Low coherence interferometry approach for aiding fine needle aspiration biopsies

We present portable preclinical low-coherence interference (LCI) instrumentation for aiding fine needle aspiration biopsies featuring the second-generation LCI-based biopsy probe and an improved scoring algorithm for tissue differentiation. Our instrument and algorithm were tested on 38 mice with cultured tumor mass and we show the specificity, sensitivity, and positive predictive value of tumor detection of over 0.89, 0.88, and 0.96, respectively.

Real-time three-dimensional optical coherence tomography image-guided core-needle biopsy system

Advances in optical imaging modalities, such as optical coherence tomography (OCT), enable us to observe tissue microstructure at high resolution and in real time. Currently, core-needle biopsies are guided by external imaging modalities such as ultrasound imaging and x-ray computed tomography (CT) for breast and lung masses, respectively. These image-guided procedures are frequently limited by spatial resolution when using ultrasound imaging, or by temporal resolution (rapid real-time feedback capabilities) when using x-ray CT. One feasible approach is to perform OCT within small gauge needles to optically image tissue microstructure. However, to date, no system or core-needle device has been developed that incorporates both three-dimensional OCT imaging and tissue biopsy within the same needle for true OCT-guided core-needle biopsy. We have developed and demonstrate an integrated core-needle biopsy system that utilizes catheter-based 3-D OCT for real-time image-guidance for target tissue localization, imaging of tissue immediately prior to physical biopsy, and subsequent OCT imaging of the biopsied specimen for immediate assessment at the point-of-care. OCT images of biopsied ex vivo tumor specimens acquired during core-needle placement are correlated with corresponding histology, and computational visualization of arbitrary planes within the 3-D OCT volumes enables feedback on specimen tissue type and biopsy quality. These results demonstrate the potential for using real-time 3-D OCT for needle biopsy guidance by imaging within the needle and tissue during biopsy procedures.

Parametric imaging of the local attenuation coefficient in human axillary lymph nodes assessed using optical coherence tomography

We report the use of optical coherence tomography (OCT) to determine spatially localized optical attenuation coefficients of human axillary lymph nodes and their use to generate parametric images of lymphoid tissue. 3D-OCT images were obtained from excised lymph nodes and optical attenuation coefficients were extracted assuming a single scattering model of OCT. We present the measured attenuation coefficients for several tissue regions in benign and reactive lymph nodes, as identified by histopathology. We show parametric images of the measured attenuation coefficients as well as segmented images of tissue type based on thresholding of the attenuation coefficient values. Comparison to histology demonstrates the enhancement of contrast in parametric images relative to OCT images. This enhancement is a step towards the use of OCT for in situ assessment of lymph nodes.

Preliminary evaluation of a nanotechnology-based approach for the more effective diagnosis of colon cancers

AIM

The goal of this research was to develop and preliminarily test a novel technology and instrumentation that could help to significantly increase the diagnostic yield of current colon cancer screening procedures. This technology is based on a combined fluorescence-optical coherence tomography (OCT) imaging, and topical delivery of a cancer-targeting agent.

MATERIALS & METHODS

Gold colloid-adsorbed poly(ε-caprolactone) microparticles were labeled with a near-infrared dye, and functionalized with argentine-glycine-aspartic acid (RGD peptide) to effectively target cancer tissue, and enhance fluorescence-imaging contrast. The RGD peptide recognizes the α(v)β(3)-integrin receptor, which is overexpressed by epithelial cancer cells. OCT was used under fluorescence guidance to visualize tissue morphology and, thus, to serve as a confirmatory tool for cancer presence.

RESULTS

A preliminary testing of this technology on human colon cancer cell lines, a mouse model of colon cancer, as well as human colon tissue specimens, was performed. Strong binding of microparticles to cancer cells and no binding to cells that do not significantly express integrins, such as mouse fibroblasts, was observed. Preferential binding to cancer tissue was also observed. Strong fluorescence signals were obtained from cancer tissue, owing to the efficient binding of the contrast agent. OCT imaging was capable of revealing clear differences between normal and cancer tissue.

CONCLUSION

A dual-modality imaging approach combined with topical delivery of a cancer-targeting contrast agent has been preliminarily tested for colon cancer diagnosis. Preferential binding of the contrast agent to cancer tissue allowed the cancer-suspicious locations to be highlighted and, thus, guided OCT imaging to visualize tissue morphology and determine tissue type. If successful, this multimodal approach might help to increase the sensitivity and the specificity of current colon cancer-screening procedures in the future.

Parametric imaging of cancer with optical coherence tomography

We present a parametric optical coherence tomography (OCT) technique to improve contrast between malignant and healthy non-neoplastic tissue. The technique incorporates a fully automated method to extract tissue attenuation characteristics. Results are represented visually as a parametric en face image, where the parameter used for contrast is indicative of the relative optical attenuation coefficient of the tissue. We present the first parametric OCT images of human lymph nodes containing malignant cells, and demonstrate improved tissue contrast over en face OCT images.

Tissue discrimination in anterior eye using three optical parameters obtained by polarization sensitive optical coherence tomography

We developed a tissue discrimination algorithm of polarization sensitive optical coherence tomography (PS-OCT) based on the optical properties of tissues. We calculated the three-dimensional (3D) feature vector from the parameters intensity, extinction coefficient, birefringence, which were obtained by PS-OCT. The tissue type of each pixel was determined according to the position of the feature vector in the 3D feature space. The algorithm was applied for discriminating tissues of the human anterior eye segment. The conjunctiva, sclera, trabecular meshwork (TM), cornea, and uvea were well separated in the 3D feature space, and we observed them with good contrast. The TM line can be observed in the 3D discriminated volume, as observed by gonioscopy.We validated our method by applying our algorithm and histological data to porcine eyes. A marker was injected into sub-Tenon's space and the tissues that were anterior to the marker and posterior to the marker were successfully segmented by our algorithm.