Hu Wenxing, Li Kejie, Gagnon Jake, Wang Ye, Raney Talia, Chen Jeron, Chen Yirui, Okunuki Yoko, Chen Will, Zhang Baohong
Research Department, Biogen, Inc., 225 Binney St., Cambridge, MA 02142, USA.
Bioengineering (Basel). 2025 Jan 13;12(1):57. doi: 10.3390/bioengineering12010057.
Early-stage detection of neurodegenerative diseases is crucial for effective clinical treatment. However, current diagnostic methods are expensive and time-consuming. In this study, we present FundusNet, a deep-learning model trained on fundus images, for rapid and cost-effective diagnosis of neurodegenerative diseases. FundusNet achieved superior performance in age prediction (MAE 2.55 year), gender classification (AUC 0.98), and neurodegenerative disease diagnosis-Parkinson's disease AUC 0.75 ± 0.03, multiple sclerosis AUC 0.77 ± 0.02. Grad-CAM was used to identify which part of the image contributes to diagnosis. Imaging biomarker interpretation demonstrated that FundusNet effectively identifies clinical retina structures associated with diseases. Additionally, the model's high accuracy in predicting genetic risk suggests that its performance could be further enhanced with larger training datasets.
神经退行性疾病的早期检测对于有效的临床治疗至关重要。然而，目前的诊断方法既昂贵又耗时。在本研究中，我们提出了FundusNet，这是一种基于眼底图像训练的深度学习模型，用于快速且经济高效地诊断神经退行性疾病。FundusNet在年龄预测（平均绝对误差2.55岁）、性别分类（曲线下面积0.98）以及神经退行性疾病诊断方面表现出色——帕金森病曲线下面积0.75±0.03，多发性硬化症曲线下面积0.77±0.02。使用Grad-CAM来确定图像的哪一部分有助于诊断。成像生物标志物解释表明FundusNet能够有效地识别与疾病相关的临床视网膜结构。此外，该模型在预测遗传风险方面的高准确率表明，通过更大的训练数据集，其性能可能会进一步提高。
