Department of Mechanical and Industrial Engineering, University of Toronto, Toronto, Ontario, Canada.
Ophthalmology and Vision Science, University of Toronto, Toronto, Ontario, Canada.
Br J Ophthalmol. 2023 Oct;107(10):1516-1521. doi: 10.1136/bjo-2021-320996. Epub 2022 Aug 3.
Homonymous visual field (VF) defects are usually an indicator of serious intracranial pathology but may be subtle and difficult to detect. Artificial intelligence (AI) models could play a key role in simplifying the detection of these defects. This study aimed to develop an automated deep learning AI model to accurately identify homonymous VF defects from automated perimetry.
VFs performed on Humphrey field analyser (24-2 algorithm) were collected and run through an in-house optical character recognition program that extracted mean deviation data and prepared it for use in the proposed AI model. The deep learning AI model, Deep Homonymous Classifier, was developed using PyTorch framework and used convolutional neural networks to extract spatial features for binary classification. Total collected dataset underwent 7-fold cross validation for model training and evaluation. To address dataset class imbalance, data augmentation techniques and state-of-the-art loss function that uses complement cross entropy were used to train and enhance the proposed AI model.
The proposed model was evaluated using 7-fold cross validation and achieved an average accuracy of 87% for detecting homonymous VF defects in previously unseen VFs. Recall, which is a critical value for this model as reducing false negatives is a priority in disease detection, was found to be on average 92%. The calculated F2 score for the proposed model was 0.89 with a Cohen's kappa value of 0.70.
This newly developed deep learning model achieved an overall average accuracy of 87%, making it highly effective in identifying homonymous VF defects on automated perimetry.
同视性视野（VF）缺损通常是严重颅内病变的指标，但可能较为细微且难以察觉。人工智能（AI）模型在简化这些缺损的检测方面可能发挥关键作用。本研究旨在开发一种自动化深度学习 AI 模型，以从自动视野计中准确识别同视性 VF 缺损。
收集 Humphrey 视野分析仪（24-2 算法）进行的 VFs，并通过内部光学字符识别程序运行，该程序提取平均偏差数据并为拟议的 AI 模型的使用做好准备。深度学习 AI 模型 Deep Homonymous Classifier 使用 PyTorch 框架开发，使用卷积神经网络提取用于二进制分类的空间特征。对总采集数据集进行 7 折交叉验证以进行模型训练和评估。为了解决数据集类别不平衡问题，使用数据扩充技术和使用互补交叉熵的最新损失函数来训练和增强所提出的 AI 模型。
该模型使用 7 折交叉验证进行评估，在以前未见的 VFs 中检测同视性 VF 缺损的平均准确率为 87%。召回率是该模型的关键值，因为减少假阴性是疾病检测的优先事项，平均为 92%。所提出模型的计算 F2 分数为 0.89，Cohen's kappa 值为 0.70。
新开发的深度学习模型的总体平均准确率为 87%，在自动视野计上识别同视性 VF 缺损非常有效。
