Interpretation Of Optical Coherence Tomography Images Research Articles

OCT Images Diagnosis Based on Deep Learning – A Review

The recent advancements in deep learning technology have significantly transformed the field of medical imaging, namely in the diagnosis of ocular illnesses. The progress made in this field has improved the capacity to extract and evaluate intricate characteristics in images, with Optical Coherence Tomography (OCT) playing a crucial role. OCT has become known for its safe qualities and its high level of detail, rendering it an essential instrument in the diagnosis of eye diseases. The interesting improvement in research is centered around the integration of deep learning with OCT for the purpose of automating the detection of eye diseases. We conducted a comprehensive study that explores several diagnostic methods and the wide-ranging uses of OCT. Additionally, it addresses the accessibility of publicly available datasets that are specifically tailored to optical coherence tomography (OCT). The paper provides a detailed review of the most recent advancements in computer-assisted diagnostic methods for diseases of the eye, such as age-related macular degeneration, glaucoma, and diabetic macular edema, with a particular focus on the effective use of OCT. Moreover, the paper systematically analyzes the primary challenges that deep learning faces in OCT image interpretation, emphasizing the intricate nature and possibilities of this field.

Does artificial intelligence enhance physician interpretation of optical coherence tomography: insights from eye tracking.

The adoption of optical coherence tomography (OCT) in percutaneous coronary intervention (PCI) is limited by need for real-time image interpretation expertise. Artificial intelligence (AI)-assisted Ultreon™ 2.0 software could address this barrier. We used eye tracking to understand how these software changes impact viewing efficiency and accuracy. Eighteen interventional cardiologists and fellows at McMaster University, Canada, were included in the study and categorized as experienced or inexperienced based on lifetime OCT use. They were tasked with reviewing OCT images from both Ultreon™ 2.0 and AptiVue™ software platforms while their eye movements were recorded. Key metrics, such as time to first fixation on the area of interest, total task time, dwell time (time spent on the area of interest as a proportion of total task time), and interpretation accuracy, were evaluated using a mixed multivariate model. Physicians exhibited improved viewing efficiency with Ultreon™ 2.0, characterized by reduced time to first fixation (Ultreon™ 0.9 s vs. AptiVue™ 1.6 s, p = 0.007), reduced total task time (Ultreon™ 10.2 s vs. AptiVue™ 12.6 s, p = 0.006), and increased dwell time in the area of interest (Ultreon™ 58% vs. AptiVue™ 41%, p < 0.001). These effects were similar for experienced and inexperienced physicians. Accuracy of OCT image interpretation was preserved in both groups, with experienced physicians outperforming inexperienced physicians. Our study demonstrated that AI-enabled Ultreon™ 2.0 software can streamline the image interpretation process and improve viewing efficiency for both inexperienced and experienced physicians. Enhanced viewing efficiency implies reduced cognitive load potentially reducing the barriers for OCT adoption in PCI decision-making.

Potential use of optical coherence tomography in oral potentially malignant disorders: in-vivo case series study

BackgroundEvidence confirms that the use of Optical Coherence Tomography (OCT) in oral medicine can be a reliable aid for the diagnosis and management of Oral Potentially Malignant Disorders (OPMDs). Several authors described the ability of this system to detect the structural changes of the epithelia involved by the OPMDs. The purpose of this case series is to provide a suggestion for interpretation of OCT images from different OPMDs, compared to OCT images of healthy tissues.MethodsA sample of 11 OPMDs patients was recruited and analyzed with OCT. The images obtained were then compared with an OCT repertoire image. In this work the reflectance degree was considered, together with the analysis of the increased/decreased thicknesses of the various layers. Keratin Layer (KL), Epithelial Layer (EP), Lamina Propria (LP), Basal Membrane (BM) assessment, for each lesion, was performed.ResultsOCT measurements of KL, EP and LP layers, together with BM assessing, should aid the physicians to recognize and describe different oral lesions, relating them to the corresponding oral pathology.ConclusionMore studies like this, on larger samples, are needed to validate the results and provide, in the future, a kind of manual that could guide clinicians to correctly interpret the OCT images in relation to the causing pathologies.

Non-rigid point cloud registration for middle ear diagnostics with endoscopic optical coherence tomography

PurposeMiddle ear infection is the most prevalent inflammatory disease, especially among the pediatric population. Current diagnostic methods are subjective and depend on visual cues from an otoscope, which is limited for otologists to identify pathology. To address this shortcoming, endoscopic optical coherence tomography (OCT) provides both morphological and functional in vivo measurements of the middle ear. However, due to the shadow of prior structures, interpretation of OCT images is challenging and time-consuming. To facilitate fast diagnosis and measurement, improvement in the readability of OCT data is achieved by merging morphological knowledge from ex vivo middle ear models with OCT volumetric data, so that OCT applications can be further promoted in daily clinical settings.MethodsWe propose C2P-Net: a two-staged non-rigid registration pipeline for complete to partial point clouds, which are sampled from ex vivo and in vivo OCT models, respectively. To overcome the lack of labeled training data, a fast and effective generation pipeline in Blender3D is designed to simulate middle ear shapes and extract in vivo noisy and partial point clouds.ResultsWe evaluate the performance of C2P-Net through experiments on both synthetic and real OCT datasets. The results demonstrate that C2P-Net is generalized to unseen middle ear point clouds and capable of handling realistic noise and incompleteness in synthetic and real OCT data.ConclusionsIn this work, we aim to enable diagnosis of middle ear structures with the assistance of OCT images. We propose C2P-Net: a two-staged non-rigid registration pipeline for point clouds to support the interpretation of in vivo noisy and partial OCT images for the first time. Code is available at: https://gitlab.com/nct_tso_public/c2p-net.

Biomedical Data Annotation: An OCT Imaging Case Study.

In ophthalmology, optical coherence tomography (OCT) is a widely used imaging modality, allowing visualisation of the structures of the eye with objective and quantitative cross-sectional three-dimensional (3D) volumetric scans. Due to the quantity of data generated from OCT scans and the time taken for an ophthalmologist to inspect for various disease pathology features, automated image analysis in the form of deep neural networks has seen success for the classification and segmentation of OCT layers and quantification of features. However, existing high-performance deep learning approaches rely on huge training datasets with high-quality annotations, which are challenging to obtain in many clinical applications. The collection of annotations from less experienced clinicians has the potential to alleviate time constraints from more senior clinicians, allowing faster data collection of medical image annotations; however, with less experience, there is the possibility of reduced annotation quality. In this study, we evaluate the quality of diabetic macular edema (DME) intraretinal fluid (IRF) biomarker image annotations on OCT B-scans from five clinicians with a range of experience. We also assess the effectiveness of annotating across multiple sessions following a training session led by an expert clinician. Our investigation shows a notable variance in annotation performance, with a correlation that depends on the clinician's experience with OCT image interpretation of DME, and that having multiple annotation sessions has a limited effect on the annotation quality.

Abstract 11941: Accuracy of OCT Core Labs in Determining Coronary Artery Plaque Composition

Introduction: Intravascular optical coherence tomography (OCT) provides a high-resolution representation of coronary atherosclerosis. However, the accuracy of OCT image interpretation is unknown. We present a blinded study of histologically identified OCT human plaque composition by leading international OCT core labs. Hypothesis: Human readers are unable to accurately identify all plaque compositions. Methods: Seven recognized OCT core labs (Japan, Netherlands, Switzerland, USA) participated. Each laboratory was provided 51 OCT image clips recorded from ex vivo human coronary arteries within 24 hours of death and had regions of interest processed for H&amp;E stain. Nine plaque components were identified and are listed in Results. Each OCT core lab was asked to blindly read OCT images and complete a questionnaire indicating one of nine possible plaque types. Kappa coefficient ( k ) was used ( k &lt; 0.5 poor agreement, k &gt; 0.5 high agreement) to measure intra-reader agreement; the median k is reported for each plaque component. Results: High agreement was demonstrated in identifying stable plaque including fibrous (0.93), calcium (0.83), layered plaque (1.0), and ThCFA (0.63), in contrast to unstable plaque including calcified nodule (0.50), lipid pool (0.35), macrophages/foam cells (0.35), TCFA (0.39), and necrotic core (0.22). When categories were restricted to Fibrous, Calcium, and Lipids, with Lipids expanded to include lipid pool, TCFA, and necrotic core, similar to an OCT core lab definition, k for Lipids increased to 0.61. Conclusions: Results suggest that participating OCT core labs can accurately identify combined lipid categories (lipid pool, TCFA, and necrotic core), fibrous tissue and calcium. However, accuracy is reduced when reading more sophisticated unstable plaque components. Study results emphasize the need for the development of OCT plaque composition analysis with artificial intelligence.

Diagnosis of coronary layered plaque by deep learning

Abstract Background/Introduction Healed coronary plaques, morphologically characterized by a layered pattern, are signatures of previous plaque disruption and healing. Recent optical coherence tomography (OCT) studies showed that layered plaque is associated with vascular vulnerability and rapid plaque progression. However, the diagnosis of layered plaque requires expertise in OCT image interpretation and is susceptible to interobserver variability. Purpose We aimed to develop a deep learning (DL) model for an accurate diagnosis of layered plaque. Methods We developed a Visual Transformer (ViT)-based DL model emulating the cardiologists who review consecutive OCT frames to make a diagnosis (Figure 1), and compared it to the standard convolutional neural network (CNN) model. We used 302,415 cross-sectional OCT images from 873 patients collected from 9 sites: 237,021 images from 581 patients for training and internal validation from 8 sites, and 65394 images from 292 patients collected from another site for external validation. Results Model performances were evaluated using the area under the receiver operating characteristics (AUC). In the five-fold cross validation, the ViT-based model showed better performance than the standard CNN-based model with AUC of 0.886 (95% confidence interval [CI], 0.882–0.891) compared with 0.797 (95% CI, 0.790–0.804). The ViT-based model also outperformed the standard CNN-based model in the external validation, with an AUC of 0.857 (95% CI, 0.849–0.864) compared to 0.806 (95% CI, 0.797–0.815) (Figure 2). Conclusion(s) The ViT-based DL model will help cardiologists to make an accurate diagnosis of layered plaque, which might help to stratify the risk of future adverse cardiac events. Funding Acknowledgement Type of funding sources: Private grant(s) and/or Sponsorship. Main funding source(s): Mrs. Gillian Gray through the Allan Gray Fellowship Fund in Cardiology

Optical coherence tomography for surgical margin evaluation of excised canine cutaneous and subcutaneous tumours.

Currently, intraoperative tumour margin imaging is not routinely utilized in veterinary medicine. Optical coherence tomography (OCT) allows for real-time assessment of tissue morphology of 1-2 mm depth. The aims of this study were (1) to compare the histologic and OCT features of excised canine skin and subcutaneous specimens, and (2) to determine the diagnostic accuracy of OCT for surgical margin evaluation. The authors hypothesized that OCT imaging would correlate well with histopathology and that OCT would be sensitive for detection of incomplete margins. Eighty dogs were prospectively enrolled. Tumours were excised, and the surgical margins were imaged using a spectral domain OCT system. The tumour type and completeness of excision were determined by histopathology. Nine blinded observers received training in OCT image interpretation and were then given a set of OCT images and videos. The observers assigned each image/video a grade from 1 (no tumour) to 4 (tumour) and the results were compared to histopathology. The overall median sensitivity and specificity of OCT imaging for detection of incomplete margins were 86.7% and 84.6%, respectively. A potential limitation is that observers had varied experience with OCT image interpretation, ranging from no prior experience to participating in a previous OCT project. OCT is sensitive for detection of incomplete margins and could be a promising real-time surgical margin imaging modality. Further study is needed to evaluate intraoperative applications of OCT and its impact on tumour recurrence and long-term outcome.

Optical Coherence Tomography: An Eye Into the Coronary Artery.

Optical coherence tomography (OCT) is slowly but surely gaining a foothold in the hands of interventional cardiologists. Intraluminal and transmural contents of the coronary arteries are no longer elusive to the cardiologist's probing eye. Although the graduation of an interventionalist in imaging techniques right from naked eye angiographies to ultrasound-based coronary sonographies to the modern light-based OCT has been slow, with the increasing regularity of complex coronary cases in practice, such a transition is inevitable. Although intravascular ultrasound (IVUS) due to its robust clinical data has been the preferred imaging modality in recent years, OCT provides a distinct upgrade over it in many imaging and procedural aspects. Better image resolution, accurate estimation of the calcified lesion, and better evaluation of acute and chronic stent failure are the distinct advantages of OCT over IVUS. Despite the obvious imaging advantages of OCT, its clinical impact remains subdued. However, upcoming newer trials and data have been encouraging for expanding the use of OCT to wider indications in clinical utility. During percutaneous coronary intervention (PCI), OCT provides the detailed information (dissection, tissue prolapse, thrombi, and incomplete stent apposition) required for optimal stent deployment, which is the key to successfully reducing the major adverse cardiovascular event (MACE) and stent-related morbidities. The increasing use of OCT in complex bifurcation stenting involving the left main (LM) is being studied. Also, the traditional pitfalls of OCT, such as additional contrast load for image acquisition and stenting involving the ostial and proximal LM, have also been overcome recently. In this review, we discuss the interpretation of OCT images and its clinical impact on the outcome of procedures along with current barriers to its use and newer paradigms in which OCT is starting to become a promising tool for the interventionalist and what can be expected for the immediate future in the imaging world.

Oral Cancer Screening by Artificial Intelligence-Oriented Interpretation of Optical Coherence Tomography Images

Early diagnosis of oral cancer is critical to improve the survival rate of patients. The current strategies for screening of patients for oral premalignant and malignant lesions unfortunately miss a significant number of involved patients. Optical coherence tomography (OCT) is an optical imaging modality that has been widely investigated in the field of oncology for identification of cancerous entities. Since the interpretation of OCT images requires professional training and OCT images contain information that cannot be inferred visually, artificial intelligence (AI) with trained algorithms has the ability to quantify visually undetectable variations, thus overcoming the barriers that have postponed the involvement of OCT in the process of screening of oral neoplastic lesions. This literature review aimed to highlight the features of precancerous and cancerous oral lesions on OCT images and specify how AI can assist in screening and diagnosis of such pathologies.

Intraoperative assessment of canine soft tissue sarcoma by deep learning enhanced optical coherence tomography.

Soft tissue sarcoma (STS) is a locally aggressive and infiltrative tumour in dogs. Surgical resection is the treatment of choice for local tumour control. Currently, post-operative pathology is performed for surgical margin assessment. Spectral-domain optical coherence tomography (OCT) has recently been evaluated for its value for surgical margin assessment in some tumour types in dogs. The purpose of this study was to develop an automatic diagnosis system that can assist clinicians in real-time for OCT image interpretation of tissues at surgical margins. We utilized a ResNet-50 network to classify healthy and cancerous tissues. A patch-based approach was adopted to achieve accurate classification with limited training data (80 cancer images, 80 normal images) and the validation set (20 cancer images, 20 normal images). The proposed method achieved an average accuracy of 97.1% with an excellent sensitivity of 94.3% on the validation set; the quadratic weighted κ was 0.94 for the STS diagnosis. In an independent test data set of 20 OCT images (10 cancer images, 10 normal images), the proposed method correctly differentiated all the STS images. Furthermore, we proposed a diagnostic curve, which could be evaluated in real-time to assist clinicians in detecting the specific location of a lesion. In short, the proposed method is accurate, operates in real-time and is non-invasive, which could be helpful for future surgical guidance.

Intracoronary optical coherence tomography: state of the art and future directions.

Optical coherence tomography (OCT) has been increasingly utilised to guide percutaneous coronary intervention (PCI). Despite the diagnostic utility of OCT, facilitated by its high resolution, the impact of intracoronary OCT on clinical practice has thus far been limited. Difficulty in transitioning from intravascular ultrasound (IVUS), complex image interpretation, lack of a standardised algorithm for PCI guidance, and paucity of data from prospective clinical trials have contributed to the modest adoption. Herein, we provide a comprehensive up-do-date overview on the utility of OCT in coronary artery disease, including technical details, device set-up, simplified OCT image interpretation, recognition of the imaging artefacts, and an algorithmic approach for using OCT in PCI guidance. We discuss the utility of OCT in acute coronary syndromes, provide a summary of the clinical trial data, list the work in progress, and discuss the future directions.

AB016. A standardized approach to correlating OCT images to histopathology using paraffin embedded specimens: clarification of the ellipsoid zone and new opportunities

Background: The aim of this project is to develop a new standardized and cost-efficient method to compare optical coherence tomography (OCT) scans to their corresponding paraffin embedded histopathology sections in post-mortem eyes. This correlation will clarify the interpretation of OCT images, and it will also enable direct immunohistochemical characterization of features observed on OCT.

The basics of intravascular optical coherence tomography.

Optical coherence tomography (OCT) has opened new horizons for intravascular coronary imaging. It utilizes near-infrared light to provide a microscopic insight into the pathology of coronary arteries in vivo. Optical coherence tomography is also capable of identifying the chemical composition of atherosclerotic plaques and detecting traits of their vulnerability. At present it is the only tool to measure the thickness of the fibrous cap covering the lipid core of the atheroma, and thus it is an exceptional modality to detect plaques that are prone to rupture (thin fibrous cap atheromas). Moreover, it facilitates distinguishing between plaque rupture and plaque erosion as a cause of acute intracoronary thrombosis. Optical coherence tomography is applied to guide angioplasties of coronary lesions and to assess outcomes of percutaneous coronary interventions broadly. It identifies stent malapposition, dissections, and thrombosis with unprecedented precision. Furthermore, OCT helps to monitor vessel healing after stenting. It evaluates the coverage of stent struts by the neointima and detects in-stent neoatherosclerosis. With so much potential, new studies are warranted to determine OCT's clinical impact. The following review presents the technical background, basics of OCT image interpretation, and practical tips for adequate OCT imaging, and outlines its established and potential clinical application.

Detection of breast surgical margins with optical coherence tomography imaging: a concept evaluation study.

This study aimed to evaluate the concept of using high-resolution optical coherence tomography (OCT) imaging to rapidly assess surgical specimens and determine if cancer positive margins were left behind in the surgical bed. A mouse model of breast cancer was used in this study. Surgical specimens from 30 animals were investigated with OCT and automated interpretation of the OCT images was performed and tested against histopathology findings. Specimens from 10 animals were used to build a training set of OCT images, while the remaining 20 specimens were used for a validation set of images. The validation study showed that automated interpretation of OCT images can differentiate tissue types and detect cancer positive margins with at least 81% sensitivity and 89% specificity. The findings of this pilot study suggest that OCT imaging of surgical specimens and automated interpretation of OCT data may enable in the future real-time feedback to the surgeon about margin status in patients with breast cancer, and potentially with other types of cancers. Currently, such feedback is not provided and if positive margins are left behind, patients have to undergo another surgical procedure. Therefore, this approach can have a potentially high impact on breast surgery outcome.

Three dimensional optical coherence tomography imaging: Advantages and advances

Three dimensional (3D) ophthalmic imaging using optical coherence tomography (OCT) has revolutionized assessment of the eye, the retina in particular. Recent technological improvements have made the acquisition of 3D-OCT datasets feasible. However, while volumetric data can improve disease diagnosis and follow-up, novel image analysis techniques are now necessary in order to process the dense 3D-OCT dataset. Fundamental software improvements include methods for correcting subject eye motion, segmenting structures or volumes of interest, extracting relevant data post hoc and signal averaging to improve delineation of retinal layers. In addition, innovative methods for image display, such as C-mode sectioning, provide a unique viewing perspective and may improve interpretation of OCT images of pathologic structures. While all of these methods are being developed, most remain in an immature state. This review describes the current status of 3D-OCT scanning and interpretation, and discusses the need for standardization of clinical protocols as well as the potential benefits of 3D-OCT scanning that could come when software methods for fully exploiting these rich datasets are available clinically. The implications of new image analysis approaches include improved reproducibility of measurements garnered from 3D-OCT, which may then help improve disease discrimination and progression detection. In addition, 3D-OCT offers the potential for preoperative surgical planning and intraoperative surgical guidance.

Correlation between optical coherence tomography images and histology of pigskin

Noninvasive imaging techniques such as optical coherence tomography (OCT) are being widely used for early diagnostics of a variety of pathologies. Traditional tissue preparation for histological evaluation alters the dimensions of histological images such that differences between the dimensions of histologic and OCT images can be as great as 2.5-fold. This discrepancy complicates quantitative interpretation of OCT images. Here we used a steel ring sewn to the pigskin to avoid tissue deformation due to excision and fixation and used a surgical suture as a fixed tissue marker. With these techniques, we achieved good correlation between OCT and histological images with differences of less than 10%. The resulting method significantly enhances the diagnostic capabilities of the OCT technique.

Optical coherence tomography: an assessment of current training across all levels of seniority in 8 ophthalmic units in the united kingdom

BackgroundOptical Coherence Tomography (OCT) is becoming an increasingly integral part of ophthalmological clinical practice. The accurate interpretation of OCT images is important both in terms of diagnosis and in directing subsequent management. The aim of this study was to determine the clinical competence in OCT image interpretation of ophthalmologists in different subspecialties and grades.MethodsEight OCT images demonstrating a single macular pathology and two normal scans were selected by case notes review. These ten images were shown to thirty doctors and 10 non-medical staff from eight units. They were asked to identify each lesion, the average thickness of the lesion, and the axis at which the OCT was taken. One point was awarded for each correct answer.ResultsThe mean scores for the correct qualitative identification of the OCT lesion (with a maximum score of 10) for different grades of doctors and non-medical staff were as follows: medical retinal consultants (MRC), 9 (range, 8–10); vitreoretinal consultants (VRC), 7 (range, 6–9); non-retinal consultants (NRC), 4 (range, 2–6); vitreoretinal fellows (VRF), 4 (range, 3–7); specialist registrars (SpR), 3 (range, 2–5); senior house officers (SHO), 4 (range, 3–6); orthoptists, 1 (range, 0–1); ancillary staff, 2 (range, 0–3).ConclusionA wide range in the ability to accurately interpret OCT images has been demonstrated. All doctors would thereby benefit from further training in the interpretation of OCT scans.

In vivo colonoscopic optical coherence tomography for transmural inflammation in inflammatory bowel disease

Transmural inflammation, a distinguishing feature of Crohn's disease (CD), cannot be assessed by conventional colonoscopy with mucosal biopsy. Our previous ex vivo study of histology-correlated optical coherence tomography (OCT) imaging on colectomy specimens of CD and ulcerative colitis (UC) showed that disruption of the layered structure of colon wall on OCT is an accurate marker for transmural inflammation of CD. We performed an in vivo colonoscopic OCT in patients with a clinical diagnosis of CD or UC using the previously established, histology-correlated OCT imaging criterion. OCT was performed in 40 patients with CD (309 images) and 30 patients with UC (292 images). Corresponding endoscopic features of mucosal inflammation were documented. Two gastroenterologists blinded to endoscopic and clinical data scored the OCT images independently to assess the feature of disrupted layered structure. Thirty-six CD patients (90.0%) had disrupted layered structure, whereas 5 UC patients (16.7%) had disrupted layered structure (P < .001). Using the clinical diagnosis of CD or UC as the gold standard, the disrupted layered structure on OCT indicative of transmural inflammation had a diagnostic sensitivity and specificity of 90.0% (95% CI: 78.0%, 96.5%) and 83.3% (95% CI: 67.3%, 93.3%) for CD, respectively. The kappa coefficient in the interpretation of OCT images was 0.80 (95% CI: 0.75, 0.86, P < .001). In vivo colonoscopic OCT is feasible and accurate to detect disrupted layered structure of the colon wall indicative of transmural inflammation, providing a valuable tool to distinguish CD from UC.

Optical coherence tomography for macular edema. Classification, quantitative assessment, and rational usage in the clinical practice

Optical coherence tomography (OCT) allows for morphological assessment of macular edema of various origins by producing two-dimensional images of the retina. In addition, retinal thickness can be measured quantitatively. In diabetic maculopathy, damage of the blood-retinal barrier can be indirectly assessed by locating the intraretinal fluid accumulation and the progress of maculopathy from diffuse to cystoid edema and even rupture of the retinal structure can be described as well as the formation of neurosensory retinal detachment with subretinal fluid. Increase of retinal thickness correlates with decrease in visual acuity. Detailed interpretation of OCT images can replace fluorescein angiography in certain cases, as has been shown for uveitis. In order to obtain correct classification of macular disease in routine clinical use, all images have to be completely assessed and compared to previous investigations and to the measurements of the fellow eye. More accurate normal values of retinal thickness and volume can be expected in the future. The importance of OCT in routine clinical assessment of macular edema will most probably continue to grow.