Department of Ophthalmology, The First Affiliated Hospital of Guangxi Medical University, 22 Shuangyong Road, Nanning, Guangxi Zhuang Autonomous Region, China.
Qi Dian Fu Liu Technology Co.Ltd, Beijing, China.
Sci Rep. 2024 Jul 12;14(1):16154. doi: 10.1038/s41598-024-66608-7.
Corneal infection is a major public health concern worldwide and the most common cause of unilateral corneal blindness. Toxic effects of different microorganisms, such as bacteria and fungi, worsen keratitis leading to corneal perforation even with optimal drug treatment. The cornea forms the main refractive surface of the eye. Diseases affecting the cornea can cause severe visual impairment. Therefore, it is crucial to analyze the risk of corneal perforation and visual impairment in corneal ulcer patients for making early treatment strategies. The modeling of a fully automated prognostic model system was performed in two parts. In the first part, the dataset contained 4973 slit lamp images of corneal ulcer patients in three centers. A deep learning model was developed and tested for segmenting and classifying five lesions (corneal ulcer, corneal scar, hypopyon, corneal descementocele, and corneal neovascularization) in the eyes of corneal ulcer patients. Further, hierarchical quantification was carried out based on policy rules. In the second part, the dataset included clinical data (name, gender, age, best corrected visual acuity, and type of corneal ulcer) of 240 patients with corneal ulcers and respective 1010 slit lamp images under two light sources (natural light and cobalt blue light). The slit lamp images were then quantified hierarchically according to the policy rules developed in the first part of the modeling. Combining the above clinical data, the features were used to build the final prognostic model system for corneal ulcer perforation outcome and visual impairment using machine learning algorithms such as XGBoost, LightGBM. The ROC curve area (AUC value) evaluated the model's performance. For segmentation of the five lesions, the accuracy rates of hypopyon, descemetocele, corneal ulcer under blue light, and corneal neovascularization were 96.86, 91.64, 90.51, and 93.97, respectively. For the corneal scar lesion classification, the accuracy rate of the final model was 69.76. The XGBoost model performed the best in predicting the 1-month prognosis of patients, with an AUC of 0.81 (95% CI 0.63-1.00) for ulcer perforation and an AUC of 0.77 (95% CI 0.63-0.91) for visual impairment. In predicting the 3-month prognosis of patients, the XGBoost model received the best AUC of 0.97 (95% CI 0.92-1.00) for ulcer perforation, while the LightGBM model achieved the best performance with an AUC of 0.98 (95% CI 0.94-1.00) for visual impairment.
角膜感染是全球范围内一个主要的公共卫生问题，也是导致单侧角膜盲的最常见原因。不同微生物（如细菌和真菌）的毒性作用会加重角膜炎，即使进行了最佳的药物治疗，也会导致角膜穿孔。角膜是眼睛的主要屈光表面。影响角膜的疾病会导致严重的视力损害。因此，分析角膜溃疡患者发生角膜穿孔和视力损害的风险对于制定早期治疗策略至关重要。该全自动预后模型系统的建模分为两部分完成。在第一部分中，数据集包含了三个中心的 4973 例角膜溃疡患者的裂隙灯图像。开发了一个深度学习模型，用于分割和分类角膜溃疡患者眼睛中的五种病变（角膜溃疡、角膜瘢痕、前房积脓、角膜内皮下水肿和角膜新生血管）。此外，还根据策略规则进行了分层量化。在第二部分中，数据集包含了 240 例角膜溃疡患者的临床数据（姓名、性别、年龄、最佳矫正视力和角膜溃疡类型）和 240 例相应的 1010 例裂隙灯图像，这些图像是在两种光源（自然光和钴蓝光）下拍摄的。然后，根据建模第一部分中制定的策略规则对裂隙灯图像进行分层量化。结合上述临床数据，使用机器学习算法（如 XGBoost、LightGBM）构建最终的角膜溃疡穿孔和视力损害预后模型系统。使用受试者工作特征曲线（AUC 值）评估模型性能。对于五种病变的分割，前房积脓、内皮下水肿、蓝光下的角膜溃疡和角膜新生血管的准确率分别为 96.86%、91.64%、90.51%和 93.97%。对于角膜瘢痕病变的分类，最终模型的准确率为 69.76%。XGBoost 模型在预测患者 1 个月的预后方面表现最佳，其对于溃疡穿孔的 AUC 值为 0.81（95%CI 0.63-1.00），对于视力损害的 AUC 值为 0.77（95%CI 0.63-0.91）。在预测患者 3 个月的预后方面，XGBoost 模型的 AUC 值最佳，为 0.97（95%CI 0.92-1.00），用于溃疡穿孔，而 LightGBM 模型的 AUC 值最佳，为 0.98（95%CI 0.94-1.00），用于视力损害。
