This study aims to investigate how infectious keratitis depicted on slit-lamp and smartphone photographs can be reliably assessed using deep learning. We retrospectively collected a dataset consisting of 5,673 slit-lamp photographs and 400 smartphone photographs acquired on different subjects. Based on multiple clinical tests (e.g., cornea scraping), these photographs were diagnosed and classified into four categories, including normal (i.e., no keratitis), bacterial keratitis (BK), fungal keratitis (FK), and herpes simplex virus stromal keratitis (HSK). We preprocessed these slit-lamp images into two separate subgroups: (1) global images and (2) regional images. The cases in each group were randomly split into training, internal validation, and independent testing sets. Then, we implemented a deep learning network based on the InceptionV3 by fine-tuning its architecture and used the developed network to classify these slit-lamp images. Additionally, we investigated the performance of the InceptionV3 model in classifying infectious keratitis depicted on smartphone images. We, in particular, clarified whether the computer model trained on the global images outperformed the one trained on the regional images. The quadratic weighted kappa (QWK) and the receiver operating characteristic (ROC) analysis were used to assess the performance of the developed models. Our experiments on the independent testing sets showed that the developed models achieved the QWK of 0.9130 (95% CI: 88.99-93.61%) and 0.8872 (95% CI: 86.13-91.31%), and 0.5379 (95% CI, 48.89-58.69%) for the global images, the regional images, and the smartphone images, respectively. The area under the ROC curves (AUCs) were 0.9588 (95% CI: 94.28-97.48%), 0.9425 (95% CI: 92.35-96.15%), and 0.8529 (95% CI: 81.79-88.79%) for the same test sets, respectively. The deep learning solution demonstrated very promising performance in assessing infectious keratitis depicted on slit-lamp photographs and the images acquired by smartphones. In particular, the model trained on the global images outperformed that trained on the regional images.

BACKGROUND Herpes simplex virus (HSV) stromal keratitis with ulceration is one of the most serious forms of herpes corneal infection and is one of the most difficult conditions in terms of clinical management. We assessed the efficacy of intravenous acyclovir in the treatment of this condition. CASE REPORT Two cases of HSV stromal keratitis with ulceration were reported in terms of clinical presentation, investigation, treatment, and outcome.Diagnosis was confirmed by polymerase chain reaction (PCR) analysis. PCR testing of corneal scraping samples identified HSV-1 in the first patient and HSV-2 in the second patient. The first patient initially presented with herpes geographic epithelial keratitis and progressed to HSV stromal keratitis with ulceration during treatment with a prophylactic dose of oral acyclovir. Despite oral acyclovir therapy, the cornea lesion continued to worsen. The treatment was switched to intravenous acyclovir. The stromal infiltration gradually improved, and the epithelial defect closed. The second patient, who had undergone penetrating keratoplasty for 13 years, presented with extensive corneal infiltration and corneal melting. The laboratory work-up was positive for HSV-2, and intravenous acyclovir was prescribed. The patient's corneal infiltration improved, but a persistent epithelial defect was present. Then, 100% autologous serum was used until the epithelial defect closed. Prophylactic treatment with oral acyclovir was prescribed to both patients to prevent disease recurrence. CONCLUSIONS Intravenous acyclovir might be considered as an alternative treatment for patients with HSV stromal keratitis with ulceration who do not respond to oral acyclovir or those with an extensive infection on a corneal graft.