Cho Bum-Joo, Lee Minwoo, Han Jiyong, Kwon Soonil, Oh Mi Sun, Yu Kyung-Ho, Lee Byung-Chul, Kim Ju Han, Kim Chulho
Department of Ophthalmology, Hallym University Sacred Heart Hospital, Anyang 14068, Korea.
Medical Artificial Intelligence Center, Hallym University Medical Center, Anyang 14068, Korea.
J Clin Med. 2022 Jun 9;11(12):3309. doi: 10.3390/jcm11123309.
We investigated whether a deep learning algorithm applied to retinal fundoscopic images could predict cerebral white matter hyperintensity (WMH), as represented by a modified Fazekas scale (FS), on brain magnetic resonance imaging (MRI).
Participants who had undergone brain MRI and health-screening fundus photography at Hallym University Sacred Heart Hospital between 2010 and 2020 were consecutively included. The subjects were divided based on the presence of WMH, then classified into three groups according to the FS grade (0 vs. 1 vs. 2+) using age matching. Two pre-trained convolutional neural networks were fine-tuned and evaluated for prediction performance using 10-fold cross-validation.
A total of 3726 fundus photographs from 1892 subjects were included, of which 905 fundus photographs from 462 subjects were included in the age-matched balanced dataset. In predicting the presence of WMH, the mean area under the receiver operating characteristic curve was 0.736 ± 0.030 for DenseNet-201 and 0.724 ± 0.026 for EfficientNet-B7. For the prediction of FS grade, the mean accuracies reached 41.4 ± 5.7% with DenseNet-201 and 39.6 ± 5.6% with EfficientNet-B7. The deep learning models focused on the macula and retinal vasculature to detect an FS of 2+.
Cerebral WMH might be partially predicted by non-invasive fundus photography via deep learning, which may suggest an eye-brain association.
我们研究了应用于视网膜眼底图像的深度学习算法能否预测脑磁共振成像（MRI）上以改良Fazekas量表（FS）表示的脑白质高信号（WMH）。
连续纳入2010年至2020年期间在韩林大学圣心医院接受过脑MRI和健康筛查眼底摄影的参与者。根据WMH的存在情况对受试者进行分组，然后使用年龄匹配根据FS分级（0级与1级与2+级）分为三组。对两个预训练的卷积神经网络进行微调，并使用10折交叉验证评估预测性能。
共纳入1892名受试者的3726张眼底照片，其中462名受试者的905张眼底照片纳入年龄匹配的平衡数据集。在预测WMH的存在时，DenseNet-201的受试者操作特征曲线下平均面积为0.736±0.030，EfficientNet-B7为0.724±0.026。对于FS分级的预测，DenseNet-201的平均准确率达到41.4±5.7%，EfficientNet-B7为39.6±5.6%。深度学习模型聚焦于黄斑和视网膜血管系统以检测2+级的FS。
通过深度学习，无创眼底摄影可能部分预测脑WMH，这可能提示眼脑关联。
