Medical Center for Dementia, Osaka City Kosaiin Hospital, 6-2-1, Furuedai, Suita-shi, Osaka Prefecture, 565-0874, Japan.
Department of Neuropsychiatry, Osaka Metropolitan University Graduate School of Medicine, Osaka, Japan.
Sci Rep. 2022 Jun 14;12(1):9881. doi: 10.1038/s41598-022-13984-7.
This study aims to investigate the accuracy of a fine-tuned deep convolutional neural network (CNN) for evaluating responses to the pentagon copying test (PCT). To develop a CNN that could classify PCT images, we fine-tuned and compared the pre-trained CNNs (GoogLeNet, VGG-16, ResNet-50, Inception-v3). To collate our training dataset, we collected 1006 correct PCT images and 758 incorrect PCT images drawn on a test sheet by dementia suspected patients at the Osaka City Kosaiin Hospital between April 2009 and December 2012. For a validation dataset, we collected PCT images from consecutive patients treated at the facility in April 2020. We examined the ability of the CNN to detect correct PCT images using a validation dataset. For a validation dataset, we collected PCT images (correct, 41; incorrect, 16) from 57 patients. In the validation testing for an ability to detect correct PCT images, the fine-tuned GoogLeNet CNN achieved an area under the receiver operating characteristic curve of 0.931 (95% confidence interval 0.853-1.000). These findings indicate that our fine-tuned CNN is a useful method for automatically evaluating PCT images. The use of CNN-based automatic scoring of PCT can potentially reduce the burden on assessors in screening for dementia.
本研究旨在探讨经微调的深度卷积神经网络（CNN）评估五边形复制测验（PCT）反应的准确性。为开发可对 PCT 图像进行分类的 CNN，我们对预训练的 CNN（GoogLeNet、VGG-16、ResNet-50、Inception-v3）进行了微调并进行了比较。为了整理我们的训练数据集，我们收集了 2009 年 4 月至 2012 年 12 月期间在大阪市 Kosaiin 医院由疑似痴呆患者在测试纸上绘制的 1006 个正确的 PCT 图像和 758 个错误的 PCT 图像。作为验证数据集，我们收集了该机构 2020 年 4 月连续治疗的患者的 PCT 图像。我们使用验证数据集检查了 CNN 检测正确 PCT 图像的能力。作为验证数据集，我们从 57 名患者中收集了 PCT 图像（正确，41 个；错误，16 个）。在验证测试中，经过微调的 GoogLeNet CNN 在接受者操作特征曲线下的面积为 0.931（95%置信区间 0.853-1.000）。这些发现表明，我们经微调的 CNN 是一种自动评估 PCT 图像的有用方法。基于 CNN 的 PCT 自动评分的使用有可能减轻评估者在痴呆筛查中的负担。
