Affiliation:
1. Department of Ophthalmology and Visual Sciences, Rutgers New Jersey Medical School, USA
Abstract
Purpose:
Artificial intelligence (AI) is often trained on images without ocular co-morbidities, limiting its generalizability. This study aims to evaluate the accuracy of a convolutional neural network (CNN) applied to color fundus photos (CFPs) with simulated cataracts (SCs) in detecting diabetic retinopathy (DR).
Methods:
A database of 3662 CFPs (from Asia Pacific Tele-Ophthalmology Society (APTOS) 2019) was used. Using transfer learning, a CNN was trained to classify the training images as either DR or non-DR. The CNN was then applied to classify the testing images after an SC was applied, using varying degrees of Gaussian blur.
Results:
Accuracy without SC was 97.0%, sensitivity (Sn) 95.7%, specificity (Sp) 98.3%. For mild SC, accuracy was 93.1%, Sn 91.8%, Sp 94.3%. For moderate SC, accuracy was 62.8%, Sn 31.4%, Sp 95.2%. For severe SC, accuracy was 53.5%, Sn 11.8%, Sp 96.5%.
Conclusion:
SCs significantly impaired AI accuracy. To prepare AI for clinical use, cataracts and other real-world clinical challenges affecting image quality must be accounted for.
Reference12 articles.
1. Machine learning-based diagnosis of melanoma using macro images;Gautam;Int J Numer Method Biomed Eng,2018
2. Application of artificial intelligence in ophthalmology;Du;Int J Ophthalmol,2018
3. Image quality issues in teledermatology: A comparative analysis of artificial intelligence solutions;Maier;J Am Acad Dermatol,2022
4. Enhanced artificial intelligence system for diagnosing and predicting breast cancer using deep learning;Alfifi;Int J Adv Comput Sci Appl,2020
5. A method to investigate image blurring due to mammography machine compression paddle movement;Ma;Radiography,2015