Glaucoma Progression Prediction Using Retinal Thickness via Latent Space Linear Regression
Glaucoma Progression Prediction Using Retinal Thickness via Latent Space Linear Regression
复制标题
DOI：
10.1145/3292500.3330757
复制
发表时间：
2019-07
期刊：
影响因子：
--
通讯作者：
Yuhui Zheng;Linchuan Xu;Taichi Kiwaki;Jing Wang;Hiroshi Murata;R. Asaoka;K. Yamanishi
中科院分区：
文献类型：
--
作者：
Yuhui Zheng;Linchuan Xu;Taichi Kiwaki;Jing Wang;Hiroshi Murata;R. Asaoka;K. Yamanishi
预测青光眼视野缺损具有显着的临床益处，因为它有助于早期发现青光眼以及制定治疗决策。青光眼性视力丧失传统上是通过视野敏感度（VF）测量来捕获的，这是昂贵且耗时的。因此，现有方法主要利用过去收集的有限 VF 数据来预测未来的 VF。最近，光学相干断层扫描（OCT）已被用来测量视网膜层厚度（RT），以显着降低治疗成本。那么在眼科背景下出现了一个重要问题：RT 测量是否有利于 VF 预测？在本文中，我们提出了一种新方法来展示 RT 测量带来的好处。挑战在于管理 VF 数据和 RT 数据的两种异质性，因为 RT 数据是根据不同的临床时间表收集的，并且与 VF 数据位于不同的空间。为了解决这些异质性，我们提出了潜在进展模式（LPP），这是一种新型的青光眼进展表征。除了 LPP 之外，我们还提出了一种基于矩阵分解将 VF 系列转换为 LPP 的方法以及一种基于深度神经网络将 RT 系列转换为 LPP 的方法。部分 VF 和 RT 信息集成在 LPP 中以提供准确的预测。所提出的框架被命名为深度正则化潜在空间线性回归（\em DLLR）。我们凭经验证明，就真实数据集上的均方根误差的平均值而言，我们提出的方法在最佳情况下比最先进的技术高出 12%。
Prediction of glaucomatous visual field loss has significant clinical benefits because it can help with early detection of glaucoma as well as decision-making for treatments. Glaucomatous visual loss is conventionally captured through visual field sensitivity (VF ) measurement, which is costly and time-consuming. Thus, existing approaches mainly predict future VF utilizing limited VF data collected in the past. Recently, optical coherence tomography (OCT) has been adopted to measure retinal layers thickness (RT ) for considerably more low-cost treatment assistance. There then arises an important question in the context of ophthalmology: are RT measurements beneficial for VF prediction? In this paper, we propose a novel method to demonstrate the benefits provided by RT measurements. The challenge is management of the two heterogeneities of VF data and RT data as RT data are collected according to different clinical schedules and lie in a different space to VF data. To tackle these heterogeneities, we propose latent progression patterns (LPPs), a novel type of representations for glaucoma progression. Along with LPPs, we propose a method to transform VF series to an LPP based on matrix factorization and a method to transform RT series to an LPP based on deep neural networks. Partial VF and RT information is integrated in LPPs to provide accurate prediction. The proposed framework is named deeply-regularized latent-space linear regression (\em DLLR). We empirically demonstrate that our proposed method outperforms the state-of-the-art technique by 12% for the best case in terms of the mean of the root mean square error on a real dataset.