Predicting Age-Related Macular Degeneration Progression with Contrastive Attention and Time-Aware LSTM.
Predicting Age-Related Macular Degeneration Progression with Contrastive Attention and Time-Aware LSTM.
复制标题
DOI：
10.1145/3534678.3539163
复制
发表时间：
2022-08
期刊：
影响因子：
--
通讯作者：
中科院分区：
文献类型：
--
作者：
视网膜相关性黄斑变性（AMD）是发达国家不可逆失明的主要原因。识别进展为晚期AMD（威胁视力的阶段）的高风险患者对于临床行动至关重要，包括医疗干预和及时监测。最近，基于深度学习的模型已经开发出来，并在后期AMD预测方面取得了上级性能。然而，大多数现有的方法仅限于最后一次眼科就诊的彩色眼底照相（CFP），并且不包括前几年就诊期间的纵向CFP病史和AMD进展。不同亚表型的AMD患者在AMD疾病的不同阶段可能有不同的进展速度。在前几年的访问中捕获进展信息可能有助于预测AMD进展。在这项工作中，我们提出了一个基于对比注意力的时间感知长短期记忆网络（CAT-LSTM）来预测AMD的进展。首先，我们采用一个卷积神经网络（CNN）模型与对比注意力模块（CA）从CFPs中提取异常特征。然后，我们利用时间感知LSTM（T-LSTM）来对患者的病史进行建模，并考虑AMD进展信息。疾病进展、基因型信息、人口统计学和CFP特征的组合被发送到T-LSTM。此外，我们利用一个自动编码器来表示时间CFP序列作为固定大小的向量，并采用k-均值聚类成亚表型。我们基于真实世界的数据集对所提出的模型进行了评估，结果表明，所提出的模型可以实现5年晚期AMD预测的受试者工作特征下的面积（AUROC）为0.925，并且比最先进的方法高出3%以上，这证明了所提出的CAT-LSTM的有效性。在分析通过自动编码器学习的患者表示后，我们确定了3种具有不同特征和晚期AMD进展率的AMD患者的新亚表型，为改善AMD管理的个性化铺平了道路。CAT-LSTM的代码可以在GitHub 1找到。
Age-related macular degeneration (AMD) is the leading cause of irreversible blindness in developed countries. Identifying patients at high risk of progression to late AMD, the sight-threatening stage, is critical for clinical actions, including medical interventions and timely monitoring. Recently, deep-learning-based models have been developed and achieved superior performance for late AMD prediction. However, most existing methods are limited to the color fundus photography (CFP) from the last ophthalmic visit and do not include the longitudinal CFP history and AMD progression during the previous years’ visits. Patients in different AMD subphenotypes might have various speeds of progression in different stages of AMD disease. Capturing the progression information during the previous years’ visits might be useful for the prediction of AMD progression. In this work, we propose a Contrastive-Attention-based Time-aware Long Short-Term Memory network (CAT-LSTM) to predict AMD progression. First, we adopt a convolutional neural network (CNN) model with a contrastive attention module (CA) to extract abnormal features from CFPs. Then we utilize a time-aware LSTM (T-LSTM) to model the patients’ history and consider the AMD progression information. The combination of disease progression, genotype information, demographics, and CFP features are sent to T-LSTM. Moreover, we leverage an auto-encoder to represent temporal CFP sequences as fixed-size vectors and adopt k-means to cluster them into subphenotypes. We evaluate the proposed model based on real-world datasets, and the results show that the proposed model could achieve 0.925 on area under the receiver operating characteristic (AUROC) for 5-year late-AMD prediction and outperforms the state-of-the-art methods by more than 3%, which demonstrates the effectiveness of the proposed CAT-LSTM. After analyzing patient representation learned by an auto-encoder, we identify 3 novel subphenotypes of AMD patients with different characteristics and progression rates to late AMD, paving the way for improved personalization of AMD management. The code of CAT-LSTM can be found at GitHub1.