npj Digital Medicine ( IF 12.4 ) Pub Date : 2024-08-16 , DOI: 10.1038/s41746-024-01207-4 Gregory Holste 1, 2 , Mingquan Lin 1, 3 , Ruiwen Zhou 4 , Fei Wang 1 , Lei Liu 4 , Qi Yan 5 , Sarah H Van Tassel 6 , Kyle Kovacs 6 , Emily Y Chew 7 , Zhiyong Lu 8 , Zhangyang Wang 2 , Yifan Peng 1
Deep learning has enabled breakthroughs in automated diagnosis from medical imaging, with many successful applications in ophthalmology. However, standard medical image classification approaches only assess disease presence at the time of acquisition, neglecting the common clinical setting of longitudinal imaging. For slow, progressive eye diseases like age-related macular degeneration (AMD) and primary open-angle glaucoma (POAG), patients undergo repeated imaging over time to track disease progression and forecasting the future risk of developing a disease is critical to properly plan treatment. Our proposed Longitudinal Transformer for Survival Analysis (LTSA) enables dynamic disease prognosis from longitudinal medical imaging, modeling the time to disease from sequences of fundus photography images captured over long, irregular time periods. Using longitudinal imaging data from the Age-Related Eye Disease Study (AREDS) and Ocular Hypertension Treatment Study (OHTS), LTSA significantly outperformed a single-image baseline in 19/20 head-to-head comparisons on late AMD prognosis and 18/20 comparisons on POAG prognosis. A temporal attention analysis also suggested that, while the most recent image is typically the most influential, prior imaging still provides additional prognostic value.
中文翻译:
使用基于 Transformer 的序列建模,利用纵向医学成像的力量来预测眼病预后
深度学习在医学成像的自动诊断方面取得了突破,在眼科领域取得了许多成功应用。然而,标准的医学图像分类方法仅评估采集时是否存在疾病,而忽略了纵向成像的常见临床环境。对于年龄相关性黄斑变性 (AMD) 和原发性开角型青光眼 (POAG) 等缓慢、进行性眼病,患者会随着时间的推移进行重复成像以跟踪疾病进展,并预测未来患病的风险对于正确规划治疗至关重要。我们提出的用于生存分析的纵向转换器 (LTSA) 能够从纵向医学成像中动态预测疾病,从在较长、不规则的时间段内捕获的眼底摄影图像序列中模拟患病时间。使用来自年龄相关眼病研究 (AREDS) 和高眼压症治疗研究 (OHTS) 的纵向成像数据,LTSA 在晚期 AMD 预后的 19/20 头对头比较和 POAG 预后的 18/20 比较中显着优于单图像基线。一项时间注意力分析还表明,虽然最近的图像通常是最有影响力的,但先前的影像学检查仍然提供额外的预后价值。