Kumar Rajnish, Sinha Devansh M, Sinha Nishant R, Tripathi Ratnakar, Hesemann Nathan, Gupta Suneel, Tiwari Anil, Mohan Rajiv R
Harry S. Truman Memorial Veterans' Hospital, Columbia, MO, USA.
Department of Veterinary Medicine & Surgery, College of Veterinary Medicine, University of Missouri, Columbia, MO, USA.
Sci Rep. 2025 Jul 1;15(1):20359. doi: 10.1038/s41598-025-08042-x.
Artificial intelligence (AI) has emerged as a transformative tool in ophthalmology for disease diagnosis and prognosis. However, use of AI for assessing corneal damage due to chemical injury in live rabbits remains lacking. This study aimed to develop an AI-derived clinical classification model for an objective grading of corneal injury and opacity levels in live rabbits following ocular exposure of sulfur mustard (SM). An automated method to grade corneal injury minimizes diagnostic errors and enhances translational application of preclinical research in better human eyecare. SM induced corneal injury and opacity from 401 in-house rabbit corneal images captured with a clinical stereomicroscope were used. Three independent subject matter specialists classified corneal images into four health grades: healthy, mild, moderate, and severe. Mask-RCNN was employed for precise corneal segmentation and extraction, followed by classification using baseline convolutional neural network and transfer learning algorithms, including VGG16, ResNet101, DenseNet121, InceptionV3, and ResNet50. The ResNet50-based model demonstrated the best performance, achieving 87% training accuracy, and 85% and 83% prediction accuracies on two independent test sets. This deep learning framework, combining Mask-RCNN with ResNet50 allows reliable and uniform grading of SM-induced corneal injury and opacity levels in affected eyes.
人工智能（AI）已成为眼科疾病诊断和预后的一种变革性工具。然而，在活体兔中使用AI评估化学伤所致角膜损伤的研究仍较为缺乏。本研究旨在开发一种基于AI的临床分类模型，用于客观分级活体兔眼部暴露于芥子气（SM）后角膜损伤和混浊程度。一种用于角膜损伤分级的自动化方法可最大限度地减少诊断误差，并增强临床前研究在改善人类眼保健方面的转化应用。研究使用了通过临床体视显微镜拍摄的401张实验室内兔角膜图像，这些图像显示了SM诱导的角膜损伤和混浊。三名独立的主题专家将角膜图像分为四个健康等级：健康、轻度、中度和重度。采用Mask-RCNN进行精确的角膜分割和提取，随后使用基线卷积神经网络和迁移学习算法（包括VGG16、ResNet101、DenseNet121、InceptionV3和ResNet50）进行分类。基于ResNet50的模型表现最佳，在训练集上的准确率达到87%，在两个独立测试集上的预测准确率分别为85%和83%。这种将Mask-RCNN与ResNet50相结合的深度学习框架能够可靠且统一地分级受影响眼中SM诱导的角膜损伤和混浊程度。
