Search

IntroductionLimbal Stem Cell Deficiency (LSCD) is a blinding corneal disease characterized by the loss of function or deficiency in adult stem cells located at the junction between the cornea and the sclera (i.e., the limbus), namely the limbal stem cells (LSCs). Recent advances in in vivo imaging technology have improved disease diagnosis and staging to quantify several biomarkers of in vivo LSC function including epithelial thickness measured by anterior segment optical coherence tomography, and basal epithelial cell density and subbasal nerve plexus by in vivo confocal microscopy. A decrease in central corneal sub-basal nerve density and nerve fiber and branching number has been shown to correlate with the severity of the disease in parallel with increased nerve tortuosity. Yet, image acquisition and manual quantification require a high level of expertise and are time-consuming. Manual quantification presents inevitable interobserver variability.MethodsThe current study employs a novel deep learning approach to classify neuron morphology in various LSCD stages and healthy controls, by integrating images created through latent diffusion augmentation. The proposed model, a residual U-Net, is based in part on the InceptionResNetV2 transfer learning model.ResultsDeep learning was able to determine fiber number, branching, and fiber length with high accuracy (R2 of 0.63, 0.63, and 0.80, respectively). The model trained on images generated through latent diffusion on average outperformed the same model when trained on solely original images. The model was also able to detect LSCD with an AUC of 0.867, which showed slightly higher performance compared to classification using manually assessed metrics.DiscussionThe results suggest that utilizing latent diffusion to supplement training data may be effective in bolstering model performance. The results of the model emphasize the ability as well as the shortcomings of this novel deep learning approach to predict various nerve morphology metrics as well as LSCD disease severity.

BackgroundFasting is usually recommended in patients undergoing cataract surgery under topical anesthesia. However, starving before surgery may increase preoperative anxiety and affect surgical outcomes. It is not known which fasting or non-fasting strategy is best for cataract surgery. The aim of this study was to compare non-fasting and fasting strategy in patients undergoing cataract surgery under topical anesthesia with regard to surgical outcomes, anxiety and pain.MethodsThis randomized, crossover, controlled trial enrolled patients undergoing surgery for bilateral cataract under topical anesthesia at Cochin Hospital (Paris, France), from February to May 2021. Patients were randomly assigned to the non-fasting or fasting group for the first eye surgery and were switched to the other group for the second eye surgery. The primary endpoint was to compare the rate of anesthetist's interventions during surgery. The secondary endpoints included intra-operative complications, duration of surgery, surgeon perception of surgical difficulty, anesthesia-related complications and anxiety and pain level.Resultsone hundred and nine consecutive patients were included, with 60 of them being fasted first and non-fasted for the second eye surgery, while the other 59 were non-fasted first and fasted for the next surgery. The number of patients requiring sedation was significantly lower in the non-fasting group compared with the fasting group [1%; 95%IC (0-3.2) vs. 6%; 95%IC (2.9-8.9), P = 0.04]. No anesthesia-related complications were observed. There was no difference in the number of intra-operative complications between the non-fasting and the fasting groups (,respectively, 0 and 1; P = 1). Anxiety level and surgical pain were significantly lower in the non-fasting group compared to the fasting group (,respectively, 2.3 ± 2.0 vs. 4.1 ± 2.4, P = 0.01 and 0.6 ± 0.6 vs. 2.6 ± 3.4, P = 0.003). The mean duration of surgery was significantly shorter in the non-fasting group compared with the fasting group (,respectively, 16.0 ± 5.9 vs. 22.3 ± 6.1 min; P = 0.03).ConclusionIn conclusion pre-operatory non-fasting strategy provides a better patient experience with regards to preoperative anxiety and surgical pain. It allows to reduce operating times and is safe and well-tolerated as regards the anesthetic intervention.