Optical Coherence Tomography In Diagnosis Research Articles

Role of optical coherence tomography in diagnosis of acute syphilitic chorioretinitis

Role of optical coherence tomography in diagnosis of acute syphilitic chorioretinitis

Noninvasive carotid ultrasound for predicting vulnerable plaques of the coronary artery based on optical coherence tomography images.

The risk factors for coronary and carotid plaque development are consistent. Coronary plaque rupture is a major cause of adverse cardiovascular events. Ultrasound can evaluate vulnerable carotid plaques and provide information for predicting vulnerable coronary plaques identified by optical coherence tomography (OCT). This study aimed to investigate the predictive role of non-invasive carotid ultrasound in OCT diagnosis of atherosclerotic vulnerable plaque. A total of 70 participants, including 35 patients with and 35 without vulnerable coronary plaque, were enrolled in this case-control study at Beijing Anzhen Hospital from 2016 to 2021. The data of 70 patients with suspected coronary heart disease who had undergone OCT examination during percutaneous coronary intervention (PCI) surgery and completed carotid ultrasound examination within 3 days before PCI were analyzed retrospectively. According to the OCT diagnostic criteria for vulnerable plaques, the patients were divided into the vulnerable-plaque group and the stable-plaque group. Univariate and binary logistic regression analyses assessed risk factors for vulnerable coronary plaque. Receiver operating characteristic (ROC) curve analysis was used to determine the predictive power of carotid plaque features. The univariate analysis demonstrated that the differences in high-sensitivity C-reactive protein levels and carotid plaque characteristics (irregular fibrous cap, heterogeneous plaque, hypoechoic plaque, plaque calcification, and a plaque thickness of greater than 3 mm) between the two groups were statistically significant. The logistic multivariate regression analysis revealed that an irregular fibrous cap of a carotid plaque [odds ratio (OR) =4.819; 95% confidence interval (CI): 1.106-22.867; P=0.048] and a hypoechoic plaque (OR =9.632; 95% CI: 2.138-43.384; P<0.05) were independent risk factors for predicting vulnerable plaques of the coronary artery. Noninvasive carotid ultrasound is feasible and clinically valuable for predicting vulnerable and asymptomatic coronary plaques defined by OCT. With this method, adverse events can be diagnosed and treated in advance.

Low rates of optical coherence tomography utilization in the diagnosis and management of retinovascular diseases in a lower middle-income economy.

Optical coherence tomography (OCT) is widely used as the standard of care in evaluating macular and retinovascular diseases. However, the degree of OCT utilization is yet to be researched in a resource-limited country where wide gaps exist in access to healthcare. To determine the rate of utilization of the OCT in diagnosis, pre-treatment, and post-treatment evaluation of macular and retinovascular diseases treated with intravitreal anti-vascular endothelial growth factor injection (IVI). Retrospective, consecutive, and non-comparative case series of eyes diagnosed and treated from Jan 2017 to Jan 2022 for seven macular and retinovascular diseases in five eye clinics in Nigeria. Data extracted include demographics, indication for IVI, eye treated, use or non-use of OCT at the diagnosis (pre-treatment) and after the last IVI (post-treatment), and central macular thickness (CMT) of pre-treatment OCT scans. Seven hundred and forty two eyes were diagnosed with retinovascular and macular diseases (389 right eyes and 353 left eyes).The male to female ratio was 430: 312 eyes. The mean age was, 63.89 years (SD 12.58). Four hundred and fifty two eyes (60.9%) had a pre-treatment OCT, 235 eyes (31.7%) had a post-treatment OCT, and 190 eyes (25.6%) had both pre- and post-treatment OCTs. The rate of pre-treatment OCT varied with the diagnosis (P = 0.000); DME had the highest rate, 74.4%, and HRVO had the lowest, 40%. Post-treatment OCT rate varied with the diagnosis (P = 0.009); non-AMD CNVM had the highest rate, 49.1%, and PCV had the lowest, 24.6%. Pre-treatment OCT rate was influenced by clinic location (P = 0.000); higher in clinics having an OCT. Post-treatment OCT was not influenced by clinic location (P = 0.37). A CRVO eye had the highest maximum CMT (1031 microns) of all the pre treatment eyes and the lowest minimum CMT of all the pre treatment eyes was in a BRVO eye (138 microns). Mean CMT was highest in HRVO (475.33 microns) and lowest in CNVM (307.62 microns). Though OCT is the standard of care for managing retinovascular and macular diseases, this research quantifies the extent of its use in Nigeria and finds it to be low. A post-treatment OCT rate of 32% suggests that urgent steps are required to improve access to OCT for IVI patients.

Changes in retinal nerve fiber layer, ganglion cell complex, and ganglion cell layer thickness in thyroid eye disease: A systematic review.

Thyroid eye disease (TED) is characterized by progressive orbital inflammation. In severe cases, it can lead to dysthyroid optic neuropathy (DON), involving death of retinal ganglion cells and permanent vision loss. Imaging with optical coherence tomography (OCT) has enabled noninvasive examination of the structural impact of the disease, including of the retinal nerve fiber layer (RNFL), the ganglion cell layer (GCL), and the inner plexiform layer (IPL). In this study, we systematically review 20 studies (897 patients, 1430 eyes) to evaluate changes in retinal thickness in patients with TED, stratified by severity. Most studies found a decrease in thickness in peripapillary RNFL (pRNFL), non-pRNFL, combined RNFL/GCL/IPL, or combined GCL/IPL when comparing patients with DON to healthy controls or to patients without DON. However, results were equivocal regarding differences between non-DON TED patients and controls. In addition, several studies reported a postoperative decrease in pRNFL thickness after orbital decompression surgery. Future studies examining OCT changes of retinal thickness along with disease progression are needed to assess the potential of OCT in diagnosis and management of patients with TED.

Role of optical coherence tomography in diagnosis of Alzheimer's disease

AbstractPurpose: To evaluate changes in visual function and anatomical structures in the neuroretina of patients diagnosed with Alzheimer's disease (AD) in comparison with healthy controls.Methods: A total of 25 eyes of 13 AD patients and 80 eyes of 40 healthy subjects were analysed. Best corrected visual acuity (BCVA) was assessed in different contrast situations (100%, 2.5%, 1.25%) with ETDRS chart (Early Treatment Diabetic Retinopathy Study). Also, retinal nerve fibre layer (RNFL) and ganglion cell layer (GCL) thickness were analysed using Spectralis and Triton optical coherence tomography (OCT), globally and by sectors, both in peripapillary and macular area.Results: A statistically significant decrease was found in BCVA in AD patients in comparison with controls (p &lt; 0.001), specifically in 100% and 1.25% contrast charts. Regarding structural analysis, a significant reduction in retinal thickness was found in AD patients in comparison with controls. Global thickness was found to be significantly thinner in peripapillary retina in Triton OCT (p &lt; 0.001). In a similar way, macular GCL, both in Triton and Spectralis OCT, showed a significant thinning (p &lt; 0.001) in global and sectorial analysis. RNFL showed a significant tendency towards thinning, but specifically in infero‐temporal sector of macular area in Spectralis OCT (p &lt; 0.001).Conclusions: The neurodegeneration that AD produces to the brain affects the retina in a parallel way, and that can be objectified by measuring BCVA parameters and thickness measurements in OCT. Compared to healthy controls, AD has a significant thinning in several neuroretinal layers, which can be considered a potential diagnostic tool considering that OCT is a quick, reproducible, non‐invasive test.

Identification of coronary plaque rupture or erosion by preprocedural computed tomography angiography in patients with non-st-segment elevation acute coronary syndrome

Abstract Background The frequent pathological cause of acute coronary thrombosis is plaque rupture or erosion. A previous CT angiographic study failed to discriminate OCT-defined intact fibrous cap culprit lesions (IFC lesions) from those with ruptured fibrous cap (RFC group) in patients with acute coronary syndrome (ACS) and chronic coronary syndrome. Objectives This study aimed to evaluate the diagnostic efficacy of preprocedural coronary CT imaging to identify optical coherence tomography (OCT)-defined plaque rupture or erosion at culprit lesions in patients with non-ST-segment elevation acute coronary syndrome (NSTE-ACS). Methods Consecutive patients with suspected NSTE-ACS who underwent preprocedural non-contrast CT and CT angiography (CCTA) were studied. Patients with at least one lesion with more than 50% stenosis at the proximal segment on CCTA were subsequently assessed by invasive coronary angiography and OCT. ALL CT and OCT examination were performed within 24 hours from presentation. The diagnosis of intact fibrous cap or ruptured fibrous cap was made by OCT for the angiographically most severely stenosed lesion. Cases of ambiguous OCT diagnosis such as massive thrombosis or calcified nodule precluding the fibrous cap assessment were excluded from the final analysis. Results In the final analysis of 176 patients, OCT identified 87 RFC plaques and 89 IFC plaques for the culprit lesions, respectively. In IFC group, lower prevalence of diabetes mellitus (24.7% vs. 41.4%, P=0.025) and lower peak cardiac marker elevation (CPK, 159 vs. 272 U/L, P&amp;lt;0.001) were observed. On CT, the prevalence of low attenuation plaque, positive remodeling, napkin ring sign, spotty calcification, calcium score (CAC), and culprit vessel pericoronary adipose tissue attenuation (FAI) were all significantly low in IFC group. Multivariate regression analysis to predict IFC at culprit lesions revealed that the absence of low attenuation plaque, the absence of napkin ring sign, zero CAC, and low FAI were independent predictors of IFC. When stratified by the number of these 4 CT factors, the presence of IFC were stratified as 0%, 23.6%, 50%, 77.8%, and 100% (P&amp;lt;0.001), respectively. Adding non-contrast CT factor of zero CAC to the reference model including age, sex, DM, EF, low attenuation plaque, napkin ring sign, and FAI, can increase the incremental discriminatory and reclassification performance for the prediction of IFC (C-statistic 0.828 NRI: 0.37, 95% CI: 0.095–0.646, P=0.008 and IDI: 0.042, 95% CI: 0.012–0.071, P=0.005). Conclusions Preprocedural comprehensive CT imaging including CAC and pericoronary adipose tissue inflammation could identify IFC or RFC culprit lesions defined by OCT. Further studies are needed to confirm our preliminary results and if CT imaging in NSTE-ACS provides prognostic information or specific therapeutic approach such as conservative therapy or non-stenting strategy before invasive angiography. Funding Acknowledgement Type of funding sources: None.

Riehl's Melanosis: A Multimodality, In Vivo, Real-Time Skin Imaging Study with Cellular Resolution Optical Coherence Tomography and Advanced Skin Diagnosis System in a Tertiary Medical Center.

Background: Riehl’s melanosis is a psychologically devastating hyperpigmentary disorder that typically occurs on the face and neck. The study of Riehl’s melanosis is limited due to its rarity, variable morphology, and lack of noninvasive diagnostic tools. Recent advances in skin imaging analysis and diagnostic systems improve diagnostic accuracy and enable the noninvasive, real-time evaluation of pigmentary disease. A comprehensive study of Riehl’s melanosis clinical morphology with multimodality and in vivo skin imaging systems has yet to be reported. Objectives: To investigate the clinical features and in vivo advanced skin imaging findings of Riehl’s melanosis. Methods: We retrospectively investigated the clinical characteristics, dermoscopic, and histopathological features of Riehl’s melanosis. We further utilized multimodality skin imaging analysis systems, including a cellular resolution optical coherence tomography (OCT) and new skin diagnosis system, to investigate the features of Riehl’s melanosis. In addition, we compared OCT findings with histopathological features and clinical assessment. Results: We evaluated 30 patients with Riehl’s melanosis at a tertiary medical center from 2010 to 2022. The average age was 47.7 ± 12.3 (mean ± SD) years, predominantly female patients (female: n = 23; male: n = 7). Cellular resolution OCT imaging from lesion skin shows increased melanocyte capping, disrupted basement membrane, telangiectatic blood vessels, and melanophages in the dermis. The advanced skin diagnosis system captured subclinical erythema of the skin, highlighting the inflammatory nature of the disease. The results correlated well with histopathological findings. Limitations: This is a single-center, cross-sectional study. Conclusions: We highlight the features of Riehl’s melanosis through a novel cellular resolution OCT and photographic skin diagnosis system. A multimodality skin diagnosis system can serve as a real-time, in vivo, noninvasive method for evaluating pigmentary disorders.

Automated diagnosis of optical coherence tomography imaging on plaque vulnerability and its relation to clinical outcomes in coronary artery disease

This study sought to develop a deep learning-based diagnostic algorithm for plaque vulnerability by analyzing intravascular optical coherence tomography (OCT) images and to investigate the relation between AI-plaque vulnerability and clinical outcomes in patients with coronary artery disease (CAD). A total of 1791 study patients who underwent OCT examinations were recruited from a multicenter clinical database, and the OCT images were first labeled as either normal, a stable plaque, or a vulnerable plaque by expert cardiologists. A DenseNet-121-based deep learning algorithm for plaque characterization was developed by training with 44,947 prelabeled OCT images, and demonstrated excellent differentiation among normal, stable plaques, and vulnerable plaques. Patients who were diagnosed with vulnerable plaques by the algorithm had a significantly higher rate of both events from the OCT-observed segments and clinical events than the patients with normal and stable plaque (log-rank p < 0.001). On the multivariate logistic regression analyses, the OCT diagnosis of a vulnerable plaque by the algorithm was independently associated with both types of events (p = 0.047 and p < 0.001, respectively). The AI analysis of intracoronary OCT imaging can assist cardiologists in diagnosing plaque vulnerability and identifying CAD patients with a high probability of occurrence of future clinical events.

FN-OCT: Disease Detection Algorithm for Retinal Optical Coherence Tomography Based on a Fusion Network.

Optical coherence tomography (OCT) is a new type of tomography that has experienced rapid development and potential in recent years. It is playing an increasingly important role in retinopathy diagnoses. At present, due to the uneven distributions of medical resources in various regions, the uneven proficiency levels of doctors in grassroots and remote areas, and the development needs of rare disease diagnosis and precision medicine, artificial intelligence technology based on deep learning can provide fast, accurate, and effective solutions for the recognition and diagnosis of retinal OCT images. To prevent vision damage and blindness caused by the delayed discovery of retinopathy, a fusion network (FN)-based retinal OCT classification algorithm (FN-OCT) is proposed in this paper to improve upon the adaptability and accuracy of traditional classification algorithms. The InceptionV3, Inception-ResNet, and Xception deep learning algorithms are used as base classifiers, a convolutional block attention mechanism (CBAM) is added after each base classifier, and three different fusion strategies are used to merge the prediction results of the base classifiers to output the final prediction results (choroidal neovascularization (CNV), diabetic macular oedema (DME), drusen, normal). The results show that in a classification problem involving the UCSD common retinal OCT dataset (108,312 OCT images from 4,686 patients), compared with that of the InceptionV3 network model, the prediction accuracy of FN-OCT is improved by 5.3% (accuracy = 98.7%, area under the curve (AUC) = 99.1%). The predictive accuracy and AUC achieved on an external dataset for the classification of retinal OCT diseases are 92 and 94.5%, respectively, and gradient-weighted class activation mapping (Grad-CAM) is used as a visualization tool to verify the effectiveness of the proposed FNs. This finding indicates that the developed fusion algorithm can significantly improve the performance of classifiers while providing a powerful tool and theoretical support for assisting with the diagnosis of retinal OCT.

"Inverted Snowing-Cloud" Sign in Endogenous Candida Endophthalmitis.

Candida spp. is the most common cause of endogenous fungal endophthalmitis. The diagnosis of this rare disease is based on clinical findings supported by positive blood culture. Recently, it has been shown that optical coherence tomography (OCT) characteristic findings are beneficial in making a correct diagnosis of fungal infection in cases with endogenous endophthalmitis. The current photo-essay aims to highlight the role of OCT in diagnosis of Candida endogenous endophthalmitis where OCT imaging of one of the retinal lesions disclosed a pre-retinal hyper reflective lesion with overlying punctate vitreous opacities. We propose “inverted snowing-cloud” sign for this OCT pattern considering the resemblance of the vitreous opacities to snowflakes.

Use of optical coherence tomography in diagnosis of retinal lymphomas

Evaluation of the characteristic features of retinal lymphomas using OCT. The study included 6 patients (10 eyes) with retinal lymphomas associated with brain lesions of diffuse large B-cell lymphoma (DLBCL) who were treated at the N.N. Burdenko National Medical Research Center of Neurosurgery from 2017 to 2020; they were examined with OCT. All patients with retinal lymphomas showed typical OCT signs in the form of hyperreflective subretinal infiltrates. OCT is a modern non-invasive method that allows diagnosing retinal lymphomas based on clinical and instrumental signs with a high degree of reliability.

The role of optical coherence tomography in the diagnosis of the leukemic infiltration of the optic nerve and retina

Even though there are multiple diseases of the optic nerve and the retina in patients with hemoblastosis, their ophthalmoscopic picture is similar in many respects. The purpose of this study is to determine the role of optical coherence tomography (OCT) in the differential diagnosis of various manifestations of hemoblastosis in the fundus. Material and methods. From Jan. 2015 to Jan. 2019, 9 patients (5 men and 4 women aged 29 to 72) with hemoblastosis and lesions of the optic nerve and retina were examined. Results. 5 patients were diagnosed with leukemic infiltration of the optic nerve. The remaining 4 patients had, congestive optic discs (1), occlusion of the central retinal vein (1), anterior ischemic optic neuropathy (1), and bilateral occlusion of the central retinal artery with leukemic infiltration of eye membranes (1). The article describes the ophthalmoscopic pictures and OCT data for the specific diseases. Unlike other diseases of the optic nerve and retina, leukemic infiltration is characterized by a pronounced dense edema in the inner layers of the retina with shielding of the underlying outer layers of the retina. Conclusion. OCT is an important additional method for differential diagnosis of leukemic infiltration and other diseases of the optic nerve and retina in patients with hemoblastosis.

Optical Coherence Tomography for Diagnosis and Treatment of Corneal Diseases

Optical coherence tomography (OCT) is a modern non-contact real-time imaging of anterior and posterior eye’s segments. Based on the principle of low-coherence interferometry, it provides the analysis of tissue structures. In this review, we discuss technical aspects of two different OCT platforms: Time-Domain OCT (TD-OCT), and Spectral-Domain (SD-OCT) with the use of Fourier transformation — Fourier-Domain (FD-OCT). Over the last several years, the development of OCT has increased the resolution of images by different ways of optical filtering. The usage of tunable swept laser instead of superluminescent diode in modern Swept-Source OCT (SS-OCT) provides the sufficient quality of image. Anterior segment OCT can detect the pathological changes in different ocular structures and may be a key tool for monitoring of their progression. In pterygium OCT shows the true extent of fibrovascular granulation tissue in stromal layers, whereas in keratitis it provides imaging of corneal infiltration. Frequently, OCT-pachymetry can be advantageous in the detection of subclinical keratectasias. In patients with bullous keratopathy OCT can help to distinguish corneal edema and fibrosis. The new era of OCT is characterized by application of this method in keratorefractive surgery. Microscope-mounted (portable) and microscopeintegrated OCT systems have been developed. During LASIK surgery intraoperative OCT (iOCT) helps to assess flap interface, measure flap and residual bed thickness. It is a useful tool to reveal the structural changes during corneal collagen crosslinking. At the beginning of keratoplasty, iOCT helps to determine the corneal thickness, extent and depth of opacity, Descemet membrane perforation. iOCT guides decision-making regarding keratoplasty modification, depth and diameter of trephination. Furthermore, a real-time visualization of ocular structures during keratoplasty decreases the frequency of intra- and postsurgical complications.

Влияние толщины и сосудистой плотности сетчатки на ее светочувствительность при диабетическом макулярном отеке

Purpose: to study the effect of the thickness and vascular density of the retina on its photosensitivity in diabetic macular edema. Material and methods. 9 patients (13 eyes) aged from 26 to 79 years (average age 62.1 ± 16 years) with a diagnosis of diabetic retinopathy (DR), diabetic macular edema (DME) were examined. In addition to the standard ophthalmological examination, a complex of specialized research methods was performed, including microperimetry, optical coherence tomography (OCT) and OCT with angiography (OCT-angio) of the posterior segment of the eye. At the same time, the influence of morphometric parameters on functional changes in the retina in the corresponding segments with a diameter of 6 mm was analyzed. Results. The study was a high inverse correlation relationship in the majority of cases between the parameters of the relevant sectors according microperimetry and OCT and OCT-angio in central zone of diameter 1, 3 and 6 mm and a direct correlation between central retinal thickness by OCT diagnosis and the so-called parameter K, denoting the number of points with sensitivity below 24 dB according microperimetry with a high degree of confidence (p&lt;0.01, p&lt;0.05). Conclusion. According to the results of our study, a direct correlation was found between the vascular density of the superficial and deep capillary plexuses and the parameters of photosensitivity in patients with DME. At the same time, the relationship between the thickness and light sensitivity of the retina is inverse. Key words: diabetic retinopathy, diabetic macular edema, optical coherence tomography, microperimetry, angiography.

Multi-center clinical study using optical coherence tomography for evaluation of cervical lesions in-vivo

In this prospective study of an in-vivo cervical examination using optical coherence tomography (OCT), we evaluated the diagnostic value of non-invasive and real-time OCT in cervical precancerous lesions and cancer diagnosis, and determined the characteristics of OCT images. 733 patients from 5 Chinese hospitals were inspected with OCT and colposcopy-directed biopsy. The OCT images were compared with the histological sections to find out the characteristics of various categories of lesions. The OCT images were also interpreted by 3 investigators to make a 2-class classification, and the results were compared against the pathological results. Various structures of the cervical tissue were clearly observed in OCT images, which matched well with the corresponding histological sections. The OCT diagnosis results delivered a sensitivity of 87.0% (95% confidence interval, CI 82.2–90.7%), a specificity of 84.1% (95% CI 80.3–87.2%), and an overall accuracy of 85.1%. Both good consistency of OCT images and histological images and satisfactory diagnosis results were provided by OCT. Due to its features of non-invasion, real-time, and accuracy, OCT is valuable for the in-vivo evaluation of cervical lesions and has the potential to be one of the routine cervical diagnosis methods.

Autofluorescence combined with spectral domain optical coherence tomography for diagnosis and follow-up of acute Vogt-Koyanagi-Harada disease

To evaluate the value of fundus autofluorescence (FAF) imaging combined with spectral domain optical coherence tomography (SD-OCT) in diagnosis, prognostic assessment and follow-up observation of acute Vogt-KoyanagiHarada (VKH) disease. Clinical data were collected from 12 patients (23 eyes) with acute VKH disease treated in our hospital from May, 2018 to November, 2019, including detailed medical history, best corrected visual acuity (BCVA), and results of slit lamp biomicroscopy, fundus photography, SD-OCT, fundus fluorescein angiography (FFA) and FAF imaging.SDOCT and FAF imaging were repeated after a course of treatment and in follow-up examination, and the results were compared with those at the time of admission. VKH disease involved both eyes in 11 patients (91.7%).Fundus photography showed optic disc edema in 16 eyes (69.6%), and multiple retinal neuroepithelial detachment was detected by SD-OCT in all the involved eyes (100%).IN all the eyes, FFA revealed small and dense fluorescein leakage in the early stage and fluorescein accumulation in advanced stages of VHK disease to form multiple dye pooling in the areas of serous detachment.Hyperauto fluorescence was a common finding in FAF imaging (100%), and the area involved was consistent with that of fluorescein accumulation shown by FAF imaging.Ten eyes (43.5%) showed patches of relative hypoautofluorescence in the hyperauto fl uorescence areas, and granular hyperauto fl uorescence was found in the lesions in 4 eyes (17.4%).During the remission period of VKH disease, FAF imaging showed normal finding in 8 eyes (34.8%) and reduced areas (by 55.2%) and intensity (by 46.5%) of hyperautofluorescence in 9 eyes (39.1%).In 6 eyes (26.1%), only a few hyperautofluorescent spots scattered in the macula were observed.SD-OCT demonstrated significantly reduced (by 69.5% on average) or even disappearance of subretinal fluid in the eyes.The fluorescence intensity in FAF imaging showed a significant positive correlation with the volume of subretinal fluid detected by SD-OCT (r=0.626, P < 0.05). The combination of fluorescein angiography, FAF imaging and SD-OCT can significantly improve the diagnostic accuracy of VKH disease.FAF imaging combined with SD-OCT provides an effective and noninvasive modality for evaluation of remission and monitoring the changes in VKH disease.

Feasibility study to improve deep learning in OCT diagnosis of rare retinal diseases with few-shot classification.

Deep learning (DL) has been successfully applied to the diagnosis of ophthalmic diseases. However, rare diseases are commonly neglected due to insufficient data. Here, we demonstrate that few-shot learning (FSL) using a generative adversarial network (GAN) can improve the applicability of DL in the optical coherence tomography (OCT) diagnosis of rare diseases. Four major classes with a large number of datasets and five rare disease classes with a few-shot dataset are included in this study. Before training the classifier, we constructed GAN models to generate pathological OCT images of each rare disease from normal OCT images. The Inception-v3 architecture was trained using an augmented training dataset, and the final model was validated using an independent test dataset. The synthetic images helped in the extraction of the characteristic features of each rare disease. The proposed DL model demonstrated a significant improvement in the accuracy of the OCT diagnosis of rare retinal diseases and outperformed the traditional DL models, Siamese network, and prototypical network. By increasing the accuracy of diagnosing rare retinal diseases through FSL, clinicians can avoid neglecting rare diseases with DL assistance, thereby reducing diagnosis delay and patient burden.Graphical abstract Supplementary InformationThe online version contains supplementary material available at 10.1007/s11517-021-02321-1.

Diagnostic accuracy of optical coherence tomography for the identification of in-stent fibroatheroma following stent implantation: an ex vivo histological validation study.

The accurate identification of in-stent fibroatheroma by in vivo imaging is clinically important to preventing the late catch-up phenomenon after stent deployment. This study investigated the diagnostic accuracy of optical coherence tomography (OCT) for the detection of "in-stent fibroatheroma" following stent implantation.Fifty stented coronary arteries from the 31 autopsy hearts were examined to compare OCT and histological image findings. A histological in-stent fibroatheroma was defined as a neointima containing an acellular necrotic core generated by macrophage infiltration. OCT-derived in-stent fibroatheroma comprised a heterogeneous pattern with an invisible stent strut behind the low-signal-intensity region.A total of 122 matched OCT and histology cross-sections were evaluated. Using histological findings as the gold standard, the sensitivity, specificity, positive predictive value, and negative predictive value for OCT-derived in-stent fibroatheroma were 100%, 99%, 80%, and 100%, respectively. The only histological finding underlying the false-positive diagnosis of OCT-derived in-stent fibroatheroma was foam cell accumulation without a necrotic core on the neointimal surface. No false-negative diagnosis of OCT for in-stent fibroatheroma was apparent in this analysis.This study demonstrated the potential capability of OCT based on stent strut visualization behind low-signal-intensity regions to discriminate in-stent fibroatheroma from other neointimal tissues.

Topical Application of Glycerol Increases Penetration Depth of Optical Coherence Tomography in Diagnosis of Basal Cell Carcinoma.

Optical coherence tomography is a non-invasive imaging technique that enables high-resolution in vivo imaging of skin. Although optical coherence tomography is promising for diagnosing basal cell carcinoma, its limited penetration depth may impede basal cell carcinoma subtyping. This study evaluated whether topical application of glycerol can increase penetration depth and improve the image quality and visibility of characteristic features of basal cell carcinoma. A total of 61 patients with a total of 72 basal cell carcinomas were included. Optical coherence tomography scans were obtained before and after application of an 85% glycerol solution. The mean penetration depth of each optical coherence tomography scan was acquired by automatically tracing both skin surface and the point of signal loss using a custom-made MATLAB program. Mean±standard deviation penetration depth increased from 883 ± 108 to 904 ± 88 μm before and after glycerol application, respectively (p = 0.005). Topical application of glycerol leads to a significant 2.4% increase in penetration depth. However, no significant differences in image quality and visibility of basal cell carcinoma features were found.

The use of optical coherence tomography in diagnosis of HIV-associated atherosclerosis: Case report

Background and Aims: Patients with human immunodeficiency virus (HIV) are at higher risk for coronary artery disease, due to accelerated atherosclerosis resulting from chronic inflammation, the prevalence of cardiovascular risk factors and the side effects of highly active antiretroviral therapy (HAART). The atherosclerosis associated with HIV differs in important ways from atherosclerosis in the non-HIV setting. The present article aimed to report an unusual case of atherosclerosis in HIV-infected young women without any traditional cardiovascular risk factors on OCT.