Department of Computer Science and Media Technology, Linnaeus University, Växjö, Sweden.
Department of Medicine and Optometry, Linnaeus University, Kalmar, Sweden.
Transl Vis Sci Technol. 2023 Nov 1;12(11):29. doi: 10.1167/tvst.12.11.29.
In vivo confocal microscopy (IVCM) of the cornea is a valuable tool for clinical assessment of the cornea but does not provide stand-alone diagnostic support. The aim of this work was to develop an artificial intelligence (AI)-based decision-support system (DSS) for automated diagnosis of Acanthamoeba keratitis (AK) using IVCM images.
The automated workflow for the AI-based DSS was defined and implemented using deep learning models, image processing techniques, rule-based decisions, and valuable input from domain experts. The models were evaluated with 5-fold-cross validation on a dataset of 85 patients (47,734 IVCM images from healthy, AK, and other disease cases) collected at a single eye clinic in Sweden. The developed DSS was validated on an additional 26 patients (21,236 images).
Overall, the DSS uses as input raw unprocessed IVCM image data, successfully separates artefacts from true images (93% accuracy), then classifies the remaining images by their corneal layer (90% accuracy). The DSS subsequently predicts if the cornea is healthy or diseased (95% model accuracy). In disease cases, the DSS detects images with AK signs with 84% accuracy, and further localizes the regions of diagnostic value with 76.5% accuracy.
The proposed AI-based DSS can automatically and accurately preprocess IVCM images (separating artefacts and sorting images into corneal layers) which decreases screening time. The accuracy of AK detection using raw IVCM images must be further explored and improved.
The proposed automated DSS for experienced specialists assists in diagnosing AK using IVCM images.
角膜共焦显微镜（IVCM）是评估角膜的一种有价值的临床工具，但不能提供独立的诊断支持。本研究旨在开发一种基于人工智能（AI）的决策支持系统（DSS），用于使用 IVCM 图像自动诊断棘阿米巴角膜炎（AK）。
使用深度学习模型、图像处理技术、基于规则的决策以及领域专家的宝贵输入，定义并实现了基于 AI 的 DSS 的自动化工作流程。在瑞典一家单一眼科诊所收集的 85 名患者（47734 张来自健康、AK 和其他疾病病例的 IVCM 图像）的数据集上，采用 5 折交叉验证对模型进行了评估。对另外 26 名患者（21236 张图像）进行了开发的 DSS 验证。
总体而言，DSS 作为输入使用原始未处理的 IVCM 图像数据，成功地将伪影与真实图像区分开来（准确率为 93%），然后根据角膜层对剩余的图像进行分类（准确率为 90%）。DSS 随后预测角膜是否健康或患病（模型准确率为 95%）。在疾病病例中，DSS 以 84%的准确率检测到具有 AK 迹象的图像，并以 76.5%的准确率进一步定位具有诊断价值的区域。
所提出的基于 AI 的 DSS 可以自动且准确地预处理 IVCM 图像（分离伪影并将图像分类到角膜层），从而减少筛选时间。使用原始 IVCM 图像检测 AK 的准确性需要进一步探索和改进。
本研究提出的用于有经验专家的自动化 DSS 可协助使用 IVCM 图像诊断 AK。
