Epivascular microstructures, a potential biomarker for retinal diseases, are investigated in the living human retina using adaptive optics optical coherence tomography (AO-OCT). The AO correction is driven by a four-sided pyramid wavefront sensor with a loop bandwidth of 30 Hz. In order to achieve a stable placement of the focus of the imaging beam in the desired retinal layer, a new concept for focus shifting is introduced which uses an in vivo calibration routine that is performed pre-imaging in each subject. The capability of the instrument is demonstrated by visualizing hyporeflective microstructures situated along the retinal vasculature with single volume AO-OCT images recorded at an extended 4° x 4° field of view.
Optical coherence tomography can provide visualizations of the eye both in diagnostic and surgical settings. However, noise limits the achievable image quality, especially in scenarios in which multi-frame averaging is not available. In this work, we present high-quality OCT image denoising using deep learning, only requiring unpaired volumetric capture scans for training. It is shown that, by exploiting neighboring B-scans, an artificial neural network for denoising OCT images can be trained based on a state-of-the-art approach which usually requires repeated scans from the exact same location. The effect of denoising is demonstrated for B-scans and volumetric renderings during and after mock cataract surgery on ex-vivo porcine eyes.
Four-dimensional microscope integrated optical coherence tomography (4D-miOCT) has been proposed as an alternative to conventional white-light microscopy during ophthalmic surgical interventions. Its real-time visualization capability of 3D data constitutes one of the most promising visualization techniques for many surgical use cases in ophthalmology. In this work, we conducted a comprehensive user study for optimal visualization with the highest performance use of the 4D-miOCT data, comparing an autostereoscopic light field tablet to a 3D TV. With the feedback collected as part of a user study, we are able to further optimize how we display 4D-miOCT data to surgeons.
Diabetic retinopathy is the leading cause of vision loss. Optical coherence tomography-angiography is emerging as the potentially most promising technique for diagnosing DR. We circumvent the necessity for strong labels in these data with our multiple instance learning (MIL)-based network, MIL-ResNet14. MIL-ResNet14 is evaluated against two other proven capable classifiers, Res-Net14 and VGG16. All networks were assessed quantitatively by numerical classification values. MIL-ResNet14 showcased superior numerical classification abilities and turned to identify lesions more reliably. We conclude that MIL has a regularizing effect on inexactly labeled data and is a more reliable classifier than previously proposed methods.
Previously introduced deep learning classifiers were able to support diabetic biomarker detection in OCTA en face images, but require pixel-by-pixel expert labeling, which is a labor-intensive and expensive process. We present a multiple-instance learning-based network, MIL-ResNet,14 that detects clinically relevant diabetic retinopathy biomarkers in a wide-angle (65°) OCTA dataset with high accuracy without annotation. We evaluated our proposed architecture against two well-established machine learning classifiers, ResNet14 and VGG16. The dataset we used for this study was acquired with a MHz A-scan rate swept source OCT device. We used a total of 352 en face images representing the retinal vasculature over an 18 mm x 18 mm field of view. MIL-ResNet14 outperformed the other two networks with an F-score of 0.95, a precision of 0.909 and an area under the curve of 0.973. In addition, we were able to demonstrate that MIL-ResNet14 paid special attention to relevant biomarkers such as ischemic areas and retinal vascular abnormalities by saliency overlay of gradient-weighted class activation maps on top of the en face images. Thus, OCTA could be used as a powerful diagnostic decision support tool for clinical ophthalmic screening in combination with our MIL approach.
In this work, we propose to utilize an end-to-end deep learning approach for the reconstruction of structural OCT images based on the rich information contained in raw OCT data alone instead of performing signal processing with manual tuning of the associated system parameters.
The proposed deep learning approach already yields promising results on a small training data set of widefield OCT images. Qualitative results suggest that the neural network is able to implicitly learn the full signal processing pipeline and its inherent system parameters but is strongly impacted by the data variability seen during training.
We present a multiple instance learning-based network, MIL-ResNet14, detecting biomarkers for diabetic retinopathy in a widefield optical coherence tomography angiography dataset with high accuracy, without the necessity of annotations other than the information of whether a scan stems from a diabetic patient or not. Previously introduced deep learning-based classifiers were able to support the detection of diabetic biomarkers in OCTA images, however, require expert labeling on a pixel-level, a labor-intensive and expensive process. We evaluated our proposed architecture against two proven-capable classifiers, ResNet14 and VGG16. The dataset we applied for this study was acquired with a MHz A-Scan rate widefield Swept Source-OCT device. We utilized a total of 352 en face images, displaying retinal vasculature over a field of view of 18 mm x 18 mm. MIL-ResNet14 outperformed both other networks with an F-score of 0.95, a precision of 0.909 and an Area Under the Curve of 0.973. In addition, we could show via saliency overlays of gradient-weighted class activation mappings onto the en face images, that MIL-ResNet14 pays special attention to clinically relevant biomarkers like ischemic areas and retinal vessel anomalies. This could therefore function as a vigorous diagnostic decision support tool for clinical ophthalmologic screenings.
Diabetes is a chronic metabolic disease characterized by elevated levels of blood glucose. Over time, it can lead to serious damages in the body. In the eyes, diabetic retinopathy (DR), the most common microvascular complication of diabetes, is a major cause of blindness. OCT can be used to provide high resolution images of the damages in the retina and follow their evolution over time. It is however still unclear which of the vascular or neurologic changes happen first in the development of the disease. In this work, we investigate the birefringence of the retinal nerve fiber layer (RNFL) of diabetic patients (with different stage of DR or no DR) and compare these results to healthy subject’s data. We use a PS-OCT system with an integrated retinal tracker for imaging (center wavelength of 860 nm, A-scan rate of 70 kHz). For each eye imaged, a raster scan centered on the optic nerve head (ONH) and a circular scan around the ONH (radius: 1.5mm) are taken. Considering only areas with a RNFL thickness >100 μm, birefringence values are calculated from an averaged circular tomogram for each eye. We observe a statistically significant reduced birefringence of the RNFL in the diabetic patients compared to the healthy volunteers.
Adaptive optics optical coherence tomography (AO-OCT) provides depth resolved images of the retina with cellular resolution [1, 2]. So far, various cell types have been visualized with this technique including rod photoreceptors [3], retinal pigment epithelium cells [3, 4] or Ganglion cells [5, 6]. However, a translation of this technology into clinical settings remains challenging as AOOCT systems are quite bulky and complex to operate. In addition, the clinical benefit of AO-OCT imaging has not yet been demonstrated as especially elderly patients are difficult to image. This presentation gives an overview over the performance of AO-OCT technology in a clinical setting.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.