Deep learning has dramatically improved object recognition, speech recognition, medical image analysis and many other fields. Optical coherence tomography (OCT) has become a standard of care imaging modality for ophthalmology. We asked whether deep learning could be used to segment cornea OCT images. Using a custom-built ultrahigh-resolution OCT system, we scanned 72 healthy eyes and 70 keratoconic eyes. In total, 20,160 images were labeled and used for the training in a supervised learning approach. A custom neural network architecture called CorneaNet was designed and trained. Our results show that CorneaNet is able to segment both healthy and keratoconus images with high accuracy (validation accuracy: 99.56%). Thickness maps of the three main corneal layers (epithelium, Bowman’s layer and stroma) were generated both in healthy subjects and subjects suffering from keratoconus. CorneaNet is more than 50 times faster than our previous algorithm. Our results show that deep learning algorithm scan be used for OCT image segmentation and could be applied in various clinical settings. In particular, CorneaNet could be used for early detection of keratoconus and more generally to study other diseases altering corneal morphology.

The tear meniscus contains most of the tear fluid and therefore is a good indicator for the state of the tear film. Previously, we used a custom-built optical coherence tomography (OCT) system to study the lower tear meniscus by automatically segmenting the image data with a thresholding-based segmentation algorithm (TBSA). In this report, we investigate whether the results of this image segmentation algorithm are suitable to train a neural network in order to obtain similar or better segmentation results with shorter processing times. Considering the class imbalance problem, we compare two approaches, one directly segmenting the tear meniscus (DSA), the other first localizing the region of interest and then segmenting within the higher resolution image section (LSA). A total of 6658 images labeled by the TBSA were used to train deep convolutional neural networks with supervised learning. Five-fold cross-validation reveals a sensitivity of 96.36% and 96.43%, a specificity of 99.98% and 99.86% and a Jaccard index of 93.24% and 93.16% for the DSA and LSA, respectively. Average segmentation times are up to 228 times faster than the TBSA. Additionally, we report the behavior of the DSA and LSA in cases challenging for the TBSA and further test the applicability to measurements acquired with a commercially available OCT system. The application of deep learning for the segmentation of the tear meniscus provides a powerful tool for the assessment of the tear film, supporting studies for the investigation of the pathophysiology of dry eye-related diseases.

We present vessel density alterations in response to flicker stimulation using optical coherence tomography angiography and identified the superficial capillary plexus as the layer with the most pronounced effect. This points out the physiological importance of the microvasculature in mediating functional hyperemia and suggests a fine-tuned plexus-specific mechanism to meet cellular metabolic demands.

Optical coherence tomography (OCT) and high-frequency ultrasound (HFUS), two established imaging modalities in the field of dermatology, were evaluated and compared regarding their applicability for visualization of skin tissue morphology and quantification of murine intradermal structures. The accuracy and reproducibility of both methods were assessed ex vivo and in vivo using a standardized model for intradermal volumes based on injected soft tissue fillers. OCT revealed greater detail in skin morphology, allowing for detection of single layers due to the superior resolution. Volumetric data measured by OCT (7.9 ± 0.3 μl) and HFUS (7.7 ± 0.5 μl) were in good agreement and revealed a high accuracy when compared to the injected volume of 7.98 ± 0.8 µl. In vivo, OCT provided a higher precision (relative SD: 26% OCT vs. 42% HFUS) for the quantification of intradermal structures, whereas HFUS offered increased penetration depth enabling the visualization of deeper structures. A combination of both imaging technologies might be valuable for tumor assessments or other dermal pathologies in clinical settings.

We present a system for automatic determination of the intradermal volume of hydrogels based on optical coherence tomography (OCT) and deep learning. Volumetric image data was acquired using a custom-built OCT prototype that employs an akinetic swept laser at ~1310 nm with a bandwidth of 87 nm, providing an axial resolution of ~6.5 μm in tissue. Three-dimensional data sets of a 10×10 mm skin patch comprising the intradermal filler and the surrounding tissue were acquired. A convolutional neural network using a u-net-like architecture was trained from slices of 100 OCT volume data sets where the dermal filler volume was manually annotated. Using six-fold cross-validation, a mean accuracy of 0.9938 and a Jaccard similarity coefficient of 0.879 were achieved.

Purpose: To employ ultrahigh‐resolution (UHR) optical coherence tomography (OCT) for investigation of the early wound healing process in corneal epithelium.Methods: A custom‐built UHR‐OCT system assessed epithelial healing in human keratoconic cornea after epi‐off crosslinking (CXL) procedure and a wound healing model in rabbits with iatrogenic corneal injury. 3D OCT data sets enhanced obtaining epithelial thickness maps and evaluation of reepithelization stage. Accompanying changes in deeper corneal microarchitecture were analysed.Results: The mean central corneal thickness in 40 eyes with keratoconus at baseline was 482.7 ± 38.2 μm, while mean central epithelial thickness (CET) was 43.8 ± 6.4 μm. At the final visit 20 ± 5 days post‐CXL procedure, CET was 35.0 ± 5.8 μm, significantly thinner after reepithelization (p < 0.001). Surgical success was assessed at the final visit through the demarcation line (DL), identified at 43.7 ± 13.5% stromal depth. In rabbits, the mean CET in 20 eyes at baseline was 35.9 ± 2.6 μm. In rabbits that revealed complete wound closure (10/20 eyes) at the last study day at 72 hr, CET was significantly thinner compared to baseline (30.4 ± 2.8 μm versus 35.4 ± 2.9 μm, p = 0.005). An intra‐stromal landmark indicating early keratocyte apoptosis was measured at 30.0 ± 5.1% stromal depth. Epithelial thickness maps showed the time–course of corneal healing.Conclusion: Ultrahigh‐resolution (UHR)‐OCT provided precise assessment of epithelial wound and its healing by 3D‐mapping. In addition, microarchitectural changes in the cornea in early phases of epithelial healing were revealed.