预测未来Humphrey视野的深度学习数据集

数据集获取（Figshare）

• 源站标题：Forecasting future Humphrey Visual Fields using deep learning
• DOI：10.1371/journal.pone.0214875
• 发布日期：2019-04-05
• 文件数：3 个
• 文件总体积：192.30 KB
• 源站页面：https://plos.figshare.com/articles/dataset/Forecasting_future_Humphrey_Visual_Fields_using_deep_learning/7960142

命令行下载

curl -L -o "pone.0214875.s001.pdf" "https://ndownloader.figshare.com/files/14815778"
curl -L -o "pone.0214875.s002.pdf" "https://ndownloader.figshare.com/files/14815781"
curl -L -o "pone.0214875.s003.pdf" "https://ndownloader.figshare.com/files/14815784"

文件清单

• pone.0214875.s001.pdf（32.09 KB）
• pone.0214875.s002.pdf（25.56 KB）
• pone.0214875.s003.pdf（134.66 KB）

文件总体积 192.30 KB（源站 API 实测）。

数据说明

Purpose
To determine if deep learning networks could be trained to forecast future 24–2 Humphrey Visual Fields (HVFs).
Methods
All data points from consecutive 24–2 HVFs from 1998 to 2018 were extracted from a university database. Ten-fold cross validation with a held out test set was used to develop the three main phases of model development: model architecture selection, dataset combination selection, and time-interval model training with transfer learning, to train a deep learning artificial neural network capable of generating a point-wise visual field prediction. The point-wise mean absolute error (PMAE) and difference in Mean Deviation (MD) between predicted and actual future HVF were calculated.
Results
More than 1.7 million perimetry points were extracted to the hundredth decibel from 32,443 24–2 HVFs. The best performing model with 20 million trainable parameters, CascadeNet-5, was selected. The overall point-wise PMAE for the test set was 2.47 dB (95% CI: 2.45 dB to 2.48 dB), and deep learning showed a statistically significant improvement over linear models. The 100 fully trained models successfully predicted future HVFs in glaucomatous eyes up to 5.5 years in the future with a correlation of 0.92 between the MD of predicted and actual future HVF and an average difference of 0.41 dB.
Conclusions
Using unfiltered real-world datasets, deep learning networks show the ability to not only learn spatio-temporal HVF changes but also to generate predictions for future HVFs up to 5.5 years, given only a single HVF.

许可

CC BY 4.0

引用

学术使用请引用 DOI 10.1371/journal.pone.0214875（source: https://plos.figshare.com/articles/dataset/Forecasting_future_Humphrey_Visual_Fields_using_deep_learning/7960142）。