Assaf Jad F, Yazbeck Hady, Venkatesh Prajna N, Prajna Lalitha, Gunasekaran Rameshkumar, Rajarathinam Karpagam, Lietman Thomas M, Keenan Jeremy D, Campbell J Peter, Song Xubo, Redd Travis K
Casey Eye Institute, Oregon Health & Science University, Portland, Oregon.
Faculty of Medicine, American University of Beirut, Beirut, Lebanon.
Ophthalmol Sci. 2024 Nov 12;5(2):100653. doi: 10.1016/j.xops.2024.100653. eCollection 2025 Mar-Apr.
The diagnosis of fungal keratitis using potassium hydroxide (KOH) smears of corneal scrapings enables initiation of the correct antimicrobial therapy at the point-of-care but requires time-consuming manual examination and expertise. This study evaluates the efficacy of a deep learning framework, dual stream multiple instance learning (DSMIL), in automating the analysis of whole slide imaging (WSI) of KOH smears for rapid and accurate detection of fungal infections.
Retrospective observational study.
Corneal scrapings from 568 patients with suspected fungal keratitis; 51% contained filamentous fungi according to human expert interpretation.
Dual stream multiple instance learning was employed to analyze WSI of KOH smears. Due to the extensive size of these images, often exceeding 100 000 pixels, conventional computer vision methods (e.g., convolutional neural networks) are not feasible. Dual stream multiple instance learning segments the WSI into patches for analysis, extracting relevant features from each patch and aggregating these to make a comprehensive slide-level diagnosis while generating heat maps to visualize areas contributing most to the prediction. Fivefold cross-validation was used for training and validation, with a hold-out test set comprising 15% of the total samples.
Accuracy, sensitivity, specificity, area under the receiver operating characteristic curve (AUC), F1 score, positive predictive value (PPV), and negative predictive value (NPV) in distinguishing fungal from nonfungal slides.
Dual stream multiple instance learning demonstrated an overall AUC of 0.88 with an accuracy of 79% and an F1 score of 0.79 in distinguishing fungal from nonfungal slides, with sensitivity of 85%, specificity of 71%, PPV of 80%, and NPV of 79%. For "consensus cases," where 2 human graders agreed on the slide interpretation, the model achieved an accuracy of 85% and an F1 score of 0.85. For "discrepant cases," the accuracy was 71% with an F1 score of 0.71. The generated heatmaps highlighted regions corresponding to fungal elements. Code and models are open-sourced and available at https://github.com/Redd-Cornea-AI/KOH-Smear-DSMIL.
The DSMIL framework shows significant promise in automating interpretation of KOH smears. Its capability to handle large, high-resolution WSI data and accurately detect fungal infections, while providing visual explanations through heatmaps, could enhance the scalability of KOH smear interpretation, ultimately reducing the global burden of blindness from infectious keratitis.
Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.
使用角膜刮片的氢氧化钾（KOH）涂片诊断真菌性角膜炎，能够在即时护理时启动正确的抗菌治疗，但需要耗时的人工检查和专业知识。本研究评估深度学习框架双流多实例学习（DSMIL）在自动分析KOH涂片的全玻片成像（WSI）以快速准确检测真菌感染方面的效果。
回顾性观察研究。
568例疑似真菌性角膜炎患者的角膜刮片；根据人类专家解读，51%含有丝状真菌。
采用双流多实例学习分析KOH涂片的WSI。由于这些图像尺寸巨大，常常超过100000像素，传统的计算机视觉方法（如卷积神经网络）不可行。双流多实例学习将WSI分割成小块进行分析，从每个小块中提取相关特征并汇总这些特征以进行全面的玻片水平诊断，同时生成热图以可视化对预测贡献最大的区域。采用五折交叉验证进行训练和验证，留出测试集包含总样本的15%。
区分真菌涂片和非真菌涂片的准确性、敏感性、特异性、受试者操作特征曲线下面积（AUC）、F1分数、阳性预测值（PPV）和阴性预测值（NPV）。
双流多实例学习在区分真菌涂片和非真菌涂片方面显示出总体AUC为0.88，准确性为79%，F1分数为0.79，敏感性为85%，特异性为71%，PPV为80%，NPV为79%。对于两名人类分级员对玻片解读达成一致的“共识病例”，该模型的准确率为85%，F1分数为0.85。对于“有差异的病例”，准确率为71%，F1分数为0.71。生成的热图突出显示了与真菌成分相对应的区域。代码和模型已开源，可在https://github.com/Redd-Cornea-AI/KOH-Smear-DSMIL获取。
DSMIL框架在自动解读KOH涂片方面显示出巨大潜力。它处理大型高分辨率WSI数据并准确检测真菌感染的能力，同时通过热图提供视觉解释，可提高KOH涂片解读的可扩展性，最终减轻感染性角膜炎导致的全球失明负担。
本文末尾的脚注和披露中可能会找到专有或商业披露信息。
