Automatic detection of retinopathy with optical coherence tomography images via a semi-supervised deep learning method.

Microaneurysms (MAs) are pathognomonic signs that help clinicians to detect diabetic retinopathy (DR) in the early stages. Automatic detection of MA in retinal images is an active area of research due to its application in screening processes for DR which is one of the main reasons of blindness amongst the working-age population. The focus of these works is on the automatic detection of MAs in en face retinal images like fundus color and Fluorescein Angiography (FA). On the other hand, detection of MAs from Optical Coherence Tomography (OCT) images has 2 main advantages: first, OCT is a non-invasive imaging technique that does not require injection, therefore is safer. Secondly, because of the proven application of OCT in detection of Age-Related Macular Degeneration, Diabetic Macular Edema, and normal cases, thanks to detecting MAs in OCT, extensive information is obtained by using this imaging technique. In this research, the concentration is on the diagnosis of MAs using deep learning in the OCT images which represent in-depth structure of retinal layers. To this end, OCT B-scans should be divided into strips and MA patterns should be searched in the resulted strips. Since we need a dataset comprising OCT image strips with suitable labels and such large labelled datasets are not yet available, we have created it. For this purpose, an exact registration method is utilized to align OCT images with FA photographs. Then, with the help of corresponding FA images, OCT image strips are created from OCT B-scans in four labels, namely MA, normal, abnormal, and vessel. Once the dataset of image strips is prepared, a stacked generalization (stacking) ensemble of four fine-tuned, pre-trained convolutional neural networks is trained to classify the strips of OCT images into the mentioned classes. FA images are used once to create OCT strips for training process and they are no longer needed for subsequent steps. Once the stacking ensemble model is obtained, it will be used to classify the OCT strips in the test process. The results demonstrate that the proposed framework classifies overall OCT image strips and OCT strips containing MAs with accuracy scores of 0.982 and 0.987, respectively.

Previous studies have demonstrated that optical coherence tomography (OCT) could be used to delineate alterations in the microstructure of cartilage, and have suggested that changes in the polarization state of light as detected by OCT could provide information on the birefringence properties of articular cartilage as influenced by disease. In this study we have used both OCT and polarization sensitive optical coherence tomography (PS-OCT) technologies to evaluate normal and abnormal bovine articular cartilage according to established structural, organizational, and birefringent characteristics of degenerative joint disease (DJD) in order to determine if this technology can be used to differentiate various stages of DJD as a minimally invasive imaging tool. Fresh bovine femoral-tibial joints were obtained from an abattoir, and 45 cartilage specimens were harvested from 8 tibial plateaus. Whole ex vivo specimens of normal and degenerative articular cartilage were imaged by both OCT and PS-OCT, then fixed and processed for histological evaluation. OCT/PS-OCT images and corresponding histology sections of each specimen were scored according to a modified Mankin structural grading scale and compared. OCT and PS-OCT imaging allowed structural evaluation of intact articular cartilage along a 6 mm surface length to a depth of 2 mm with a transverse resolution of 12 microm and an axial resolution of 10 microm. The OCT and PS-OCT images demonstrated characteristic alterations in the structure of articular cartilage with a high correlation to histological evaluation (kappa = 0.776). The OCT images were able to demonstrate early to advanced structural changes of articular cartilage while the optical phase retardation images obtained by PS-OCT imaging were able to discriminate areas where disorganization of the cartilage matrix was present, however, these characteristics are much different than those reported where OCT images alone were used to characterize tissue birefringence. No evidence of differences in OCT or PS-OCT images were detected between specimens of similar structural characteristics where proteoglycan was judged present or absent by safranin-O Fast Green staining. The combined use of OCT and PS-OCT technologies to obtain images from a single system is able to demonstrate and discriminate between characteristics of very early stages of surface irregularities not previously reported for OCT imaging, to deep clefts and collagen matrix disorganization for tissue at depths of up to 2 mm with good correlation to histology. PS-OCT and accumulated optical phase retardation images of articular cartilage as constructed from alterations in Stokes vector parameters appear to give a valuable but different assessment of alterations in tissue birefringence and organization than have been reported for OCT images obtained with the use of polarized or non-polarized light sources. This is the first time that alterations in the polarization state of light reflected from within the tissue have been demonstrated to be consistent with changes observed in the orientation and organization of the collagen matrix in advanced stages of DJD. The degree of phase transformation of light reflected from within the tissue as determined by PS-OCT imaging does not appear to be altered by the presence or absence of proteoglycan.

Aim To develop an optimal method for automated segmentation of atherosclerotic plaque structural components in optical coherence tomography (OCT) images using an ensemble of deep learning neural network models based on a comparison of nine artificial neural network architectures.Material and methods This study utilized a multidisciplinary OCT dataset obtained from examinations of 103 patients. Each OCT session was annotated as a set of two-dimensional binary masks corresponding to the pixel boundaries of four key morphological features of plaques: vascular lumen, fibrous cap, lipid core, and microvessels. Nine deep learning models, including U-Net, DeepLabV3, and others, were used to segment the anatomical structures. Model hyperparameters were tuned using Bayesian optimization, and the performance was assessed using the Dice Similarity Coefficient (DSC) metric.Results The models demonstrated high segmentation accuracy for the vascular lumen (DSC: 0.987) and moderate accuracy for the fibrous cap (DSC: 0.736) and lipid core (DSC: 0.751). Microvessel segmentation proved more challenging, with a final DSC accuracy of 61%. A weighted ensemble of models, accounting for the uneven representation of different morphological structures and model confidence, achieved an average DSC of 88.2%, which significantly improved the overall accuracy compared to individual models. This accuracy value exceeds those of all individual models, including the highest DSC values of 0.784 (for microvessels) and 0.751 (for lipid core), indicating a consistent improvement in the segmentation accuracy by integrating the models.Conclusion The study confirms the effectiveness of the proposed strategy for segmentation of atherosclerotic plaques in OCT images. This strategy is based on using specialized models for various morphological features and a weighted ensemble adapted to the uneven representation of different morphological structures and morphological complexity. This approach provided a high segmentation accuracy despite the pronounced inequality in the representation of classes. The study results can contribute to the development of decision support methods in cardiology aimed at improving diagnostic accuracy and treatment of cardiovascular diseases.

Aims/Purpose: The detection of subretinal fluid (SRF) and intraretinal fluid (IRF) in optical coherence tomography (OCT) images plays a crucial role in the diagnosis and treatment of certain eye diseases. In this study, we investigated the performance of a Transfer Learning artificial intelligence (AI) technique, which we used to perform the model adaptation from the domain of Heidelberg OCT images to Optopol devices.Methods: A data set of 133 Optopol OCT images. 69 images indicating subretinal or intraretinal fluid and 64 fluid‐free images, were analysed. The AI algorithm that was initially trained on OCT images from Heidelberg device was fine‐tuned to perform the biomarker segmentation in Optopol (Revo NX, SOCT Copernicus REVO, REVO FC) OCT images. Manual assessments by the medical experts were used to evaluate the algorithm's performance.Results: Our findings demonstrate the promising performance of the domain‐adapted model. in detecting SRF and IRF, when initially trained on OCT images from a different device. The algorithm achieved an accuracy of 80% while classifying the presence versus absence of the fluids on the balanced test data set.Conclusions: The study demonstrates a successful application of a transfer learning technique for detection of subretinal and intraretinal fluids in OCT images acquired with the Optopol devices, indicating its potential for enhancing eye diagnostics. Further studies utilizing larger data sets, further biomarkers and diverse OCT devices are warranted to validate the algorithm's robustness and generalizability.

Accurate plaque cap thickness quantification and cap stress/strain calculations are of fundamental importance for vulnerable plaque research. To overcome uncertainties due to intravascular ultrasound (IVUS) resolution limitation, IVUS and optical coherence tomography (OCT) coronary plaque image data were combined together to obtain accurate and reliable cap thickness data, stress/strain calculations, and reliable plaque progression predictions. IVUS, OCT, and angiography baseline and follow-up data were collected from nine patients (mean age: 69; m: 5) at Cardiovascular Research Foundation with informed consent obtained. IVUS and OCT slices were coregistered and merged to form IVUS + OCT (IO) slices. A total of 114 matched slices (IVUS and OCT, baseline and follow-up) were obtained, and 3D thin-layer models were constructed to obtain stress and strain values. A generalized linear mixed model (GLMM) and least squares support vector machine (LSSVM) method were used to predict cap thickness change using nine morphological and mechanical risk factors. Prediction accuracies by all combinations (511) of those predictors with both IVUS and IO data were compared to identify optimal predictor(s) with their best accuracies. For the nine patients, the average of minimum cap thickness from IVUS was 0.17 mm, which was 26.08% lower than that from IO data (average = 0.23 mm). Patient variations of the individual errors ranged from ‒58.11 to 20.37%. For maximum cap stress between IO and IVUS, patient variations of the individual errors ranged from ‒30.40 to 46.17%. Patient variations of the individual errors of maximum cap strain values ranged from ‒19.90 to 17.65%. For the GLMM method, the optimal combination predictor using IO data had AUC (area under the ROC curve) = 0.926 and highest accuracy = 90.8%, vs. AUC = 0.783 and accuracy = 74.6% using IVUS data. For the LSSVM method, the best combination predictor using IO data had AUC = 0.838 and accuracy = 75.7%, vs. AUC = 0.780 and accuracy = 69.6% using IVUS data. This preliminary study demonstrated improved plaque cap progression prediction accuracy using accurate cap thickness data from IO slices and the differences in cap thickness, stress/strain values, and prediction results between IVUS and IO data. Large-scale studies are needed to verify our findings.

Aim: To investigate and compare the presentation of granulomatous lesions in optical coherence tomography (OCT) images and compare this to previous studies of nonmelanoma skin tumors. Methods: Two patients with granulomas, tophi and granuloma annulare (GA), respectively, were photographed digitally, OCT-scanned and biopsied in the said order. Normal skin was OCT-scanned for comparison, but not biopsied. The OCT images from each lesion were compared with their histologic images as well as with OCT images with similar characteristics obtained from nonmelanoma skin tumors. Results: The OCT images of the tophi showed hyperreflective, rounded cloud-like structures in dermis, their upper part sharply delineated by a hyporeflective fringe. The deeper areas appeared blurred. The crystalline structures were delineated by a hyporeflective fringe. OCT images of GA showed two different structures in dermis: a hyporeflective rounded one, and one that was lobulated and wing-like. Conclusion: Granulomatous tissue surrounding urate deposits appeared as a clear hyporeflective fringe surrounding a light, hyperreflective area. The urate crystals appeared as hyperreflective areas, shielding the deeper part of dermis, meaning OCT could only visualize the upper part of the lesions. The lobulated, wing-like structure in GA may resemble diffuse GA or a dense lymphocytic infiltrate as seen on histology. The rounded structure in GA may represent an actual granuloma or either diffuse GA or a dense lymphocytic infiltrate as described above. This case suggests that OCT images granulomatous tissue as absorbent, hyporeflective areas, and urate crystals appear as reflective areas, obscuring the underlying tissue. In GA a new image shape looking like a wing has been found. The frequency, specificity and sensitivity of this new pattern in OCT imaging will require further studies.

Purpose: To evaluate the performance of deep learning (DL) in diagnosing glaucoma and predicting its progression using fundus photography and retinal optical coherence tomography (OCT) images. Materials and Methods: Relevant studies published up to 30 October 2024 were retrieved from PubMed, Medline, EMBASE, Cochrane Library, Web of Science, and ClinicalKey. A bivariate random-effects model was employed to calculate pooled sensitivity, specificity, positive and negative likelihood ratios, and area under the receiver operating characteristic curve (AUROC). Results: A total of 48 studies were included in the meta-analysis. DL algorithms demonstrated high diagnostic performance in glaucoma detection using fundus photography and OCT images. For fundus photography, the pooled sensitivity and specificity were 0.92 (95% CI: 0.89-0.94) and 0.93 (95% CI: 0.90-0.95), respectively, with an AUROC of 0.90 (95% CI: 0.88-0.92). For the OCT imaging, the pooled sensitivity and specificity were 0.90 (95% CI: 0.84-0.94) and 0.87 (95% CI: 0.81-0.91), respectively, with an AUROC of 0.86 (95% CI: 0.83-0.90). In predicting glaucoma progression, DL models generally showed less robust performance, with pooled sensitivities and specificities ranging lower than in diagnostic tasks. Internal validation datasets showed higher accuracy than external validation datasets. Conclusions: DL algorithms achieve excellent performance in diagnosing glaucoma using fundus photography and OCT imaging. To enhance the prediction of glaucoma progression, future DL models should integrate multimodal data, including functional assessments, such as visual field measurements, and undergo extensive validation in real-world clinical settings.

Computer aided diagnosis of diabetic macular edema in retinal fundus and OCT images: A review

To train generative adversarial network (GAN) models to generate predictive optical coherence tomography (OCT) images of central serous chorioretinopathy (CSC) at 3months after observation using multi-modal OCT images. Four hundred forty CSC eyes of 440 patients who underwent Cirrus OCT imaging were included. Baseline OCT B-scan images through the foveal center, en face choroid, and en face ellipsoid zone were collected from each patient. The datasets were divided into training and validation (n = 390) and test (n = 50) sets. The input images for each model comprised either baseline B-scan alone or a combination of en face choroid and ellipsoid zones. Predictive post-treatment OCT B-scan images were generated using GAN models and compared with real 3-month images. Of 50 generated OCT images, there were 48, 47, and 48 acceptable images for UNIT, CycleGAN, and RegGAN, respectively. In comparison with real 3-month images, the generated images showed sensitivity, specificity, and positive predictive values (PPV) for residual fluid in the ranges of 0.762-1.000, 0.483-0.724, and 0.583-0.704; for pigment epithelial detachment (PED) of 0.917-1.000, 0.974-1.000, and 0.917-1.000; and for subretinal hyperreflective material (SHRM) of 0.667-0.778, 0.925-0.950 and 0.700-0.750, respectively. RegGAN exhibited the highest values except for sensitivity. GAN models could generate prognostic OCT images with good performance for prediction of residual fluid, PED, and SHRM presence in CSC. Implementation of the models may help predict disease activity in CSC, facilitating the establishment of a proper treatment plan.

The purpose of this study was to develop and evaluate the performance of a convolutional neural network (CNN) that uses a novel A-line based classification approach to detect cancer in OCT images of breast specimens. Deep learning algorithms have been developed for OCT ophthalmology applications using pixel-based classification approaches. In this study, a novel deep learning approach was developed that classifies OCT A-lines of breast tissue. De-identified human breast tissues from mastectomy and breast reduction specimens were excised from patients at Columbia University Medical Center. A total of 82 specimens from 49 patients were imaged with OCT, including both normal tissues and non-neoplastic tissues. The proposed algorithm utilized a hybrid 2D/1D convolutional neural network (CNN) to map each single B-scan to a 1D label vector, which were derived from manual annotation. Each A-line was labelled as one of the following tissue types: ductal carcinoma in situ (DCIS), invasive ductal carcinoma (IDC), adipose, and stroma. Five-fold cross-validation Dice scores across tissue types were: 0.82-0.95 for IDC, 0.54-0.75 for DCIS, 0.67-0.91 for adipose, and 0.61-0.86 for stroma. In a second experiment, IDC and DCIS were combined as a single tissue class (malignancy) while stroma and adipose were combined as a second tissue class (non-malignancy). In this setup, the experiment yielded five-fold cross-validation Dice scores between 0.89-0.93, respectively. Future work includes acquiring more patient samples and to compare the algorithm to previous works, including both deep learning and traditional automatic image processing methods for classification of breast tissue in OCT images.

We compared the performance of deep learning (DL) in the classification of optical coherence tomography (OCT) images of macular diseases between automated classification alone and in combination with automated segmentation. OCT images were collected from patients with neovascular age-related macular degeneration, polypoidal choroidal vasculopathy, diabetic macular edema, retinal vein occlusion, cystoid macular edema in Irvine-Gass syndrome, and other macular diseases, along with the normal fellow eyes. A total of 14,327 OCT images were used to train DL models. Three experiments were conducted: classification alone (CA), use of automated segmentation of the OCT images by RelayNet, and the graph-cut technique before the classification (combination method 1 (CM1) and 2 (CM2), respectively). For validation of classification of the macular diseases, the sensitivity, specificity, and accuracy of CA were found at 62.55%, 95.16%, and 93.14%, respectively, whereas the sensitivity, specificity, and accuracy of CM1 were found at 72.90%, 96.20%, and 93.92%, respectively, and of CM2 at 71.36%, 96.42%, and 94.80%, respectively. The accuracy of CM2 was statistically higher than that of CA (p = 0.05878). All three methods achieved AUC at 97%. Applying DL for segmentation of OCT images prior to classification of the images by another DL model may improve the performance of the classification.

BackgroundRecent research on macular diseases has prompted investigations into the condition of the intersection between the photoreceptor inner and outer segments (IS/OS) and the relationship with retinal photoreceptor abnormalities. Although the origin of the IS/OS in optical coherence tomography (OCT) images is unclear, it may be related to either the cellular activity of the photoreceptors or the structure of the OS disks. To address this question, we compared the IS/OS status in OCT images of rat retinas before and after euthanasia.MethodsOCT images were taken before and after euthanasia in four eyes of two Brown Norway rats. After the OCT images were taken, the rats were used for histopathological studies to confirm that retinal structures were intact.ResultsBefore euthanasia, the IS/OS and external limiting membrane (ELM) line were clearly identifiable on the OCT images. However, after euthanasia, neither the IS/OS nor the ELM line was evident in three out of four eyes, and a faint IS/OS and an ELM line were identified in one eye. Histopathological analysis did not show any abnormalities in the retina in any of the four eyes.ConclusionThe origin of the IS/OS identified in OCT images is likely related to the biological activities of the photoreceptor cells.

Optical coherence tomography (OCT) is becoming one of the most important detection modalities for fast and noninvasive assessment of ophthalmological diseases. Diabetic macular edema (DME) is one of the important reasons leads to blindness. Its pathological features are mainly manifested in the accumulation of fluid in the retina. An automated method is proposed to identify and quantify the volume of cystoid macular edema in Spectral Domain OCT (SD-OCT) images. In the first stage of preprocessing, we balance the apparent signal-to-noise of each retinal OCT image. Because the signal-to-noise of OCT images is variable from patient to patient, and balance of the signal-to-noise ensures consistent segmentation of cystoid fluid. Speckle noise is the main reason leads to quality degrading in OCT images. The denoising method should be efficient for the noise suppression, and the edge information can be preserved at the same time. Then we used the anisotropic diffusion filter to suppress shot noise. The intensity inhomogeneity in OCT images may lead to false detection in the further segmentation work. Then we used the gamma transformation to change the brightness, which eliminates the effect availably. In the second stage of segmentation, we solve the problem of segmentation effectively by the improved level set method and calculated the area of edema area, which provides quantitative analytic tools for clinical diagnosis and therapy. Finally, the proposed method was evaluated on 15 SD-OCT retinal images from DME adults. Leave-one-out evaluation resulted in a precision, sensitivity and dice similarity coefficient (DSC) of 81.12%, 86.90% and 80.05%, respectively.

In preclinical vision research, cell grading in small animal models is essential for the quantitative evaluation of intraocular inflammation. Here, we present a new and practical optical coherence tomography (OCT) image analysis method for the automated detection and counting of aqueous cells in the anterior chamber (AC) of a rodent model of uveitis. Anterior segment OCT images are acquired with a 100 kHz swept-source OCT system. The proposed method consists of 2 steps. In the first step, we first despeckle and binarize each OCT image. After removing AS structures in the binary image, we then apply area thresholding to isolate cell-like objects. Potential cell candidates are selected based on their best fit to roundness. The second step performs the cell counting within the whole AC, in which additional cell tracking analysis is conducted on the successive OCT images to eliminate redundancy in cell counting. Finally, 3D cell grading using the proposed method is demonstrated in longitudinal OCT imaging of a mouse model of anterior uveitis in vivo. Rendering of anterior segment (orange) of mouse eye and automatically counted anterior chamber cells (green). Inset is a top view of the rendering, showing the cell distribution across the anterior chamber.

Extracting optical properties of tissue [e.g., the attenuation coefficient () and the backscattering fraction] from the optical coherence tomography (OCT) images is a valuable tool for parametric imaging and related diagnostic applications. Previous attenuation estimation models depend on the assumption of the uniformity of the backscattering fraction () within layers or whole samples, which does not accurately represent real-world conditions. Our aim is to develop a robust and accurate model that calculates depth-wise values of attenuation and backscattering fractions simultaneously from OCT signals. Furthermore, we aim to develop an attenuation compensation model for OCT images that utilizes the optical properties we obtained to improve the visual representation of tissues. Using the stationary iteration method under suitable constraint conditions, we derived the approximated solutions of and on a single scattering model. During the iteration, the estimated value of can be rectified by introducing the large variations of , whereas the small ones were automatically ignored. Based on the calculation of the structure information, the OCT intensity with attenuation compensation was deduced and compared with the original OCT profiles. The preliminary validation was performed in the OCT A-line simulation and Monte Carlo modeling, and the subsequent experiment was conducted on multi-layer silicone-dye- phantoms and ex vivo cow eyes. Our method achieved robust and precise estimation of and for both simulated and experimental data. Moreover, corresponding OCT images with attenuation compensation provided an improved resolution over the entire imaging range. Our proposed method was able to correct the estimation bias induced by the variations of and provided accurate depth-resolved measurements of both and simultaneously. The method does not require prior knowledge of the morphological information of tissue and represents more real-life tissues. Thus, it has the potential to help OCT imaging based disease diagnosis of complex and multi-layer biological tissue.