Artificial intelligence derived grading of mustard gas induced corneal injury and opacity

Abstract 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 m...

Full description

Saved in:
Bibliographic Details
Main Authors: Rajnish Kumar, Devansh M. Sinha, Nishant R. Sinha, Ratnakar Tripathi, Nathan Hesemann, Suneel Gupta, Anil Tiwari, Rajiv R. Mohan
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-08042-x
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849402641847681024
author Rajnish Kumar
Devansh M. Sinha
Nishant R. Sinha
Ratnakar Tripathi
Nathan Hesemann
Suneel Gupta
Anil Tiwari
Rajiv R. Mohan
author_facet Rajnish Kumar
Devansh M. Sinha
Nishant R. Sinha
Ratnakar Tripathi
Nathan Hesemann
Suneel Gupta
Anil Tiwari
Rajiv R. Mohan
author_sort Rajnish Kumar
collection DOAJ
description Abstract 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.
format Article
id doaj-art-3fd032f933cd418aafbfdad1ae2c587d
institution Kabale University
issn 2045-2322
language English
publishDate 2025-07-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-3fd032f933cd418aafbfdad1ae2c587d2025-08-20T03:37:30ZengNature PortfolioScientific Reports2045-23222025-07-0115111310.1038/s41598-025-08042-xArtificial intelligence derived grading of mustard gas induced corneal injury and opacityRajnish Kumar0Devansh M. Sinha1Nishant R. Sinha2Ratnakar Tripathi3Nathan Hesemann4Suneel Gupta5Anil Tiwari6Rajiv R. Mohan7Harry S. Truman Memorial Veterans’ HospitalDepartment of Veterinary Medicine & Surgery, College of Veterinary Medicine, University of MissouriHarry S. Truman Memorial Veterans’ HospitalHarry S. Truman Memorial Veterans’ HospitalHarry S. Truman Memorial Veterans’ HospitalHarry S. Truman Memorial Veterans’ HospitalDepartment of Veterinary Medicine & Surgery, College of Veterinary Medicine, University of MissouriHarry S. Truman Memorial Veterans’ HospitalAbstract 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.https://doi.org/10.1038/s41598-025-08042-xArtificial intelligenceCorneaFibrosisSulfur mustardPathology
spellingShingle Rajnish Kumar
Devansh M. Sinha
Nishant R. Sinha
Ratnakar Tripathi
Nathan Hesemann
Suneel Gupta
Anil Tiwari
Rajiv R. Mohan
Artificial intelligence derived grading of mustard gas induced corneal injury and opacity
Scientific Reports
Artificial intelligence
Cornea
Fibrosis
Sulfur mustard
Pathology
title Artificial intelligence derived grading of mustard gas induced corneal injury and opacity
title_full Artificial intelligence derived grading of mustard gas induced corneal injury and opacity
title_fullStr Artificial intelligence derived grading of mustard gas induced corneal injury and opacity
title_full_unstemmed Artificial intelligence derived grading of mustard gas induced corneal injury and opacity
title_short Artificial intelligence derived grading of mustard gas induced corneal injury and opacity
title_sort artificial intelligence derived grading of mustard gas induced corneal injury and opacity
topic Artificial intelligence
Cornea
Fibrosis
Sulfur mustard
Pathology
url https://doi.org/10.1038/s41598-025-08042-x
work_keys_str_mv AT rajnishkumar artificialintelligencederivedgradingofmustardgasinducedcornealinjuryandopacity
AT devanshmsinha artificialintelligencederivedgradingofmustardgasinducedcornealinjuryandopacity
AT nishantrsinha artificialintelligencederivedgradingofmustardgasinducedcornealinjuryandopacity
AT ratnakartripathi artificialintelligencederivedgradingofmustardgasinducedcornealinjuryandopacity
AT nathanhesemann artificialintelligencederivedgradingofmustardgasinducedcornealinjuryandopacity
AT suneelgupta artificialintelligencederivedgradingofmustardgasinducedcornealinjuryandopacity
AT aniltiwari artificialintelligencederivedgradingofmustardgasinducedcornealinjuryandopacity
AT rajivrmohan artificialintelligencederivedgradingofmustardgasinducedcornealinjuryandopacity