To develop an artificial intelligence (AI) model to diagnose keratitis (AK) based on confocal microscopy (IVCM) images extracted from the Heidelberg Retinal Tomograph 3 (HRT 3). This retrospective cohort study utilized HRT 3 IVCM images from patients who had received a culture-confirmed diagnosis of AK between 2013 and 2021 at Massachusetts Eye and Ear. Two cornea specialists independently labeled the images as AK or nonspecific finding (NSF) in a blind manner. Deep learning tasks were then conducted through Python and TensorFlow. Distinguishing between AK and NSF was designed as the task and completed through a devised convolutional neural network. A dataset of 3312 confocal images from 17 patients with a culture-confirmed diagnosis of AK was used in this study. The inter-rater agreement for identifying the presence or absence of AK in IVCM images was 84 %, corresponding to a total of 2782 images on which both observers agreed and which were included in the model. 1242 and 1265 images of AK and NSF, respectively, were utilized in the training and validation sets, and 173 and 102 images of AK and NSF, respectively, were utilized in the evaluation set. Our model had an accuracy, sensitivity, and specificity of 76 % each, and a precision of 78 %. We developed an HRT-based IVCM AI model for AK diagnosis utilizing culture-confirmed cases of AK. We achieved good accuracy in diagnosing AK and our model holds significant promise in the clinical application of AI in improving early AK diagnosis.

中文翻译：

---

通过共焦显微镜诊断棘阿米巴角膜炎的新型人工智能模型


开发人工智能 (AI) 模型，根据从海德堡视网膜断层扫描仪 3 (HRT 3) 提取的共焦显微镜 (IVCM) 图像来诊断角膜炎 (AK)。这项回顾性队列研究利用了 2013 年至 2021 年间在马萨诸塞州眼耳医院接受培养确诊 AK 的患者的 HRT 3 IVCM 图像。两位角膜专家以盲法独立地将图像标记为 AK 或非特异性发现 (NSF)。然后通过 Python 和 TensorFlow 执行深度学习任务。区分 AK 和 NSF 被设计为任务，并通过设计的卷积神经网络完成。本研究使用了 17 名经培养确诊为 AK 的患者的 3312 张共聚焦图像数据集。鉴定 IVCM 图像中是否存在 AK 的评估者间一致性为 84%，相当于两个观察者都同意并包含在模型中的总共 2782 个图像。训练集和验证集中分别使用了 1242 张和 NSF 的图像，评估集中分别使用了 173 张和 NSF 的图像。我们的模型的准确度、灵敏度和特异性均为 76%，精确度为 78%。我们利用培养确诊的 AK 病例开发了一种基于 HRT 的 IVCM AI 模型，用于 AK 诊断。我们在诊断 AK 方面取得了良好的准确性，并且我们的模型在 AI 临床应用中改善早期 AK 诊断方面具有重大前景。