TY - JOUR
T1 - Development and Evaluation of a Deep Learning Algorithm to Differentiate Between Membranes Attached to the Optic Disc on Ultrasonography
AU - Bhatt, Vaidehi D.
AU - Shah, Nikhil
AU - Bhatt, Deepak C.
AU - Dabir, Supriya
AU - Sheth, Jay
AU - Berendschot, Tos T. J. M.
AU - Erckens, Roel J.
AU - Webers, Carroll A. B.
PY - 2025/3/18
Y1 - 2025/3/18
N2 - Purpose: The purpose of this study was to create and test a deep learning algorithm that could identify and distinguish between membranes attached to optic disc [OD; retinal detachment (RD)/posterior vitreous detachment (PVD)] based on ocular ultrasonography (USG). Patients and Methods: We obtained a database of B-scan ultrasonography from a high-volume imaging center. A transformer-based Vision Transformer (ViT) model was employed, pre-trained on ImageNet21K, to classify ultrasound B-scan images into healthy, RD, and PVD. Images were pre-processed using Hugging Face's AutoImage Processor for standardization. Labels were mapped to numerical values, and the dataset was split into training and validation (505 samples), and testing (212 samples) subsets to evaluate model performance. Alternate methods, such as ensemble strategies and object detection pipelines, were explored but showed limited improvement in classification accuracy. Results: The AI model demonstrated high classification performance, achieving an accuracy of 98.21% for PVD, 97.22% for RD, and 95.83% for normal cases. Sensitivity was 98.21% for PVD, 96.55% for RD, and 92.86% for normal cases, while specificity reached 95.16%, 100%, and 95.42%, respectively. Despite the overall strong performance, some misclassification occurred, with seven instances of RD being incorrectly labeled as PVD. Conclusion: We developed a transformer-based deep learning algorithm for ocular ultrasonography that accurately identifies membranes attached to the optic disc, distinguishing between RD (97.22% accuracy) and PVD (98.21% accuracy). Despite seven misclassifications, our model demonstrates robust performance and enhances diagnostic efficiency in high-volume imaging settings, thereby facilitating timely referrals and ultimately improving patient outcomes in urgent care scenarios. Overall, this promising innovation shows potential for clinical adoption.
AB - Purpose: The purpose of this study was to create and test a deep learning algorithm that could identify and distinguish between membranes attached to optic disc [OD; retinal detachment (RD)/posterior vitreous detachment (PVD)] based on ocular ultrasonography (USG). Patients and Methods: We obtained a database of B-scan ultrasonography from a high-volume imaging center. A transformer-based Vision Transformer (ViT) model was employed, pre-trained on ImageNet21K, to classify ultrasound B-scan images into healthy, RD, and PVD. Images were pre-processed using Hugging Face's AutoImage Processor for standardization. Labels were mapped to numerical values, and the dataset was split into training and validation (505 samples), and testing (212 samples) subsets to evaluate model performance. Alternate methods, such as ensemble strategies and object detection pipelines, were explored but showed limited improvement in classification accuracy. Results: The AI model demonstrated high classification performance, achieving an accuracy of 98.21% for PVD, 97.22% for RD, and 95.83% for normal cases. Sensitivity was 98.21% for PVD, 96.55% for RD, and 92.86% for normal cases, while specificity reached 95.16%, 100%, and 95.42%, respectively. Despite the overall strong performance, some misclassification occurred, with seven instances of RD being incorrectly labeled as PVD. Conclusion: We developed a transformer-based deep learning algorithm for ocular ultrasonography that accurately identifies membranes attached to the optic disc, distinguishing between RD (97.22% accuracy) and PVD (98.21% accuracy). Despite seven misclassifications, our model demonstrates robust performance and enhances diagnostic efficiency in high-volume imaging settings, thereby facilitating timely referrals and ultimately improving patient outcomes in urgent care scenarios. Overall, this promising innovation shows potential for clinical adoption.
KW - POSTERIOR VITREOUS DETACHMENT
KW - artificial intelligence
KW - deep learning algorithm
KW - posterior vitreous detachment
KW - retinal detachment
KW - ultrasonography
U2 - 10.2147/OPTH.S501316
DO - 10.2147/OPTH.S501316
M3 - Article
SN - 1177-5467
VL - 19
SP - 939
EP - 947
JO - Clinical Ophthalmology
JF - Clinical Ophthalmology
ER -