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.

Many different parameters exist for the investigation of tear film dynamics. We present a new tear meniscus segmentation algorithm which automatically extracts tear meniscus area (TMA), height (TMH), depth (TMD) and radius (TMR) from UHR-OCT measurements and apply it to a data set including repeated measurements from ten healthy subjects. Mean values and standard deviations are 0.0174 ± 0.007 mm², 0.272 ± 0.069 mm, 0.191 ± 0.049 mm and 0.309 ± 0.123 mm for TMA, TMH, TMD and TMR, respectively. A significant correlation was found between all respective tear meniscus parameter pairs (all p < 0.001, all Pearson’s r ≥ 0.657). Challenges, limitations and potential improvements related to the data acquisition and the algorithm itself are discussed. The automatic segmentation of tear meniscus measurements acquired with UHR-OCT might help in a clinical setting to further understand the tear film and related medical conditions like dry eye disease.

Purpose: To determine the association between tear film thickness (TFT) as measured with ultra-high resolution optical coherence tomography (UHR-OCT) and signs and symptoms of dry eye disease (DED). Methods: A total of 450 eyes from 225 patients with DED from six different randomized clinical trials were included in this pooled analysis. In all subjects, TFT was measured with a custom-built UHR-OCT system. Symptoms of DED were quantified using a standardized Ocular Surface Disease Index (OSD)I questionnaire and clinical signs including tear film break up time (TFBUT) and Schirmer I test were assessed. Associations of the average TFT with OSDI, TFBUT, and Schirmer I test were calculated using a linear regression analysis. Results: The average TFT of the included sample (mean age, 45.0 ± 13.3 years; 65% female) was 4.2 ± 0.5 µm and the OSDI 36.2 ± 10.4. A significant negative correlation was found between TFT and OSDI (r = −0.36 to −0.31; p < 0.001). Tear break up time and Schirmer I test were not correlated with OSDI. Significant albeit weak correlations were found between TFT and TFBUT (r = 0.17 to 0.25; p < 0.01) as well as Schirmer I (r = 0.36 to 0.37; p < 0.001). Subgroup analysis revealed that the correlation was stronger in the subjects with abnormal Schirmer I (<15 mm; r = 0.50 to 0.54; p < 0.001). Conclusions: The present study demonstrates an objective measurement of TFT using a novel OCT approach for DED that correlates with symptoms and signs of DED. Our data are consistent with the idea that TFT represents the aqueous-deficient component of DED.

A custom-built ultrahigh-resolution optical coherence tomography (UHR-OCT) system and fluorescein staining were employed for investigation of a scopolamine induced dry eye mouse model. Acquired data was used to evaluate common and complementary findings of the two modalities. Central corneal thickness as measured by UHR-OCT increased significantly over the study period of 24 hours, from 89.0 ± 3.57 µm to 92.2 ± 4.07 µm. Both techniques were able to show corneal lesions with a large range of severity. Localized fluorescein staining was detected in 5% and diffuse staining in 45% of cases where no epithelial damage was visible with OCT. However, OCT revealed stromal defects in 6% and endothelial defects in 18% of the cases, which could not be visualized via fluorescein staining. Thus, while fluorescein staining widely detected defects of the corneal surface in a mouse model of dry eye disease, OCT non-invasively revealed additional information about defect depth and involvement of particular layers.

During wound healing, the rapid re-establishment of a functional microcirculation in the wounded tissue is of utmost importance. We applied optical coherence tomography (OCT) angiography to evaluate vascular remodeling in an excisional wound model in the pinnae of C57BL/6 and db/db mice receiving different proangiogenic topical treatments. Analysis of the high-resolution OCT angiograms, including the four quantitative parameters vessel density, vessel length, number of bifurcations, and vessel tortuosity, revealed changes of the microvasculature and allowed identification of the overlapping wound healing phases hemostasis, inflammation, proliferation, and remodeling. Angiograms acquired in the inflammatory phase in the first days showed a dilation of vessels and recruitment of pre-existing capillaries. In the proliferative phase, angiogenesis with the sprouting of new capillaries into the wound tissue led to an increase of the OCT angiography parameters vessel density, normalized vessel length, number of bifurcations, and vessel tortuosity by 28–47%, 39–52%, 33–48%, and 3–8% versus baseline, respectively. After the peak observed on study days four to seven, the parameters slowly decreased but remained still elevated 18 days after wounding, indicating a continuing remodeling phase. Our study suggests that OCT angiography has the potential to serve as a valuable preclinical research tool in studies investigating impaired vascular remodeling during wound healing and potential new treatment strategies.