Background 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. Methods 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. Results 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. Conclusion 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. Data are available upon reasonable request.

中文翻译：

---

用于识别自动视野检查中同名缺陷的深度学习模型

背景同名视野（VF）缺陷通常是严重颅内病变的指标，但可能很微妙且难以检测。人工智能 (AI) 模型可以在简化这些缺陷的检测方面发挥关键作用。本研究旨在开发一种自动化深度学习人工智能模型，以通过自动化视野检查准确识别同名心室颤动缺陷。方法 收集在 Humphrey 场分析仪（24-2 算法）上执行的 VF，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准备将其用于所提出的 AI 模型。深度学习AI模型Deep Homonymous Classifier是使用PyTorch框架开发的，并使用卷积神经网络提取空间特征进行二元分类。收集的总数据集经过 7 倍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的问题，使用数据增强技术和使用补集交叉熵的最先进的损失函数来训练和增强所提出的人工智能模型。结果 使用 7 倍交叉验证对所提出的模型进行评估，在检测以前未见过的 VF 中的同名 VF 缺陷方面达到了 87% 的平均准确度。召回率是该模型的一个关键值，因为减少假阴性是疾病检测的首要任务，召回率平均为 92%。所提出模型的计算 F2 分数为 0.89，Cohen 的 kappa 值为 0.70。结论 这种新开发的深度学习模型的总体平均准确度达到 87%，使其在自动视野检查中识别同名 VF 缺陷方面非常有效。数据可根据合理要求提供。