IEEE J Biomed Health Inform. 2021 Oct;25(10):3898-3910. doi: 10.1109/JBHI.2021.3079430. Epub 2021 Oct 6.
Keratoconus is one of the most severe corneal diseases, which is difficult to detect at the early stage (i.e., sub-clinical keratoconus) and possibly results in vision loss. In this paper, we propose a novel end-to-end deep learning approach, called KerNet, which processes the raw data of the Pentacam HR system (consisting of five numerical matrices) to detect keratoconus and sub-clinical keratoconus. Specifically, we propose a novel convolutional neural network, called KerNet, containing five branches as the backbone with a multi-level fusion architecture. The five branches receive five matrices separately and capture effectively the features of different matrices by several cascaded residual blocks. The multi-level fusion architecture (i.e., low-level fusion and high-level fusion) moderately takes into account the correlation among five slices and fuses the extracted features for better prediction. Experimental results show that: (1) our novel approach outperforms state-of-the-art methods on an in-house dataset, by ~1% for keratoconus detection accuracy and ~4 for sub-clinical keratoconus detection accuracy; (2) the attention maps visualized by Grad-CAM show that our KerNet places more attention on the inferior temporal part for sub-clinical keratoconus, which has been proved as the identifying regions for ophthalmologists to detect sub-clinical keratoconus in previous clinical studies. To our best knowledge, we are the first to propose an end-to-end deep learning approach utilizing raw data obtained by the Pentacam HR system for keratoconus and subclinical keratoconus detection. Further, the prediction performance and the clinical significance of our KerNet are well evaluated and proved by two clinical experts. Our code is available at https://github.com/upzheng/Keratoconus.
圆锥角膜是最严重的角膜疾病之一，在早期（即亚临床圆锥角膜）很难发现，并且可能导致视力丧失。在本文中，我们提出了一种新颖的端到端深度学习方法，称为 KerNet，它可以处理 Pentacam HR 系统的原始数据（由五个数值矩阵组成），以检测圆锥角膜和亚临床圆锥角膜。具体来说，我们提出了一种新颖的卷积神经网络，称为 KerNet，它包含五个分支作为骨干，具有多层次融合架构。五个分支分别接收五个矩阵，并通过几个级联残差块有效地捕获不同矩阵的特征。多层次融合架构（即低水平融合和高水平融合）适度考虑了五个切片之间的相关性，并融合提取的特征以进行更好的预测。实验结果表明：（1）在内部数据集上，我们的新方法优于最先进的方法，在圆锥角膜检测准确性方面提高了约 1%，在亚临床圆锥角膜检测准确性方面提高了约 4%；（2）Grad-CAM 可视化的注意力图表明，我们的 KerNet 对亚临床圆锥角膜的下颞部分更加关注，这已被证明是眼科医生在以前的临床研究中检测亚临床圆锥角膜的识别区域。据我们所知，我们是第一个提出利用 Pentacam HR 系统获得的原始数据进行圆锥角膜和亚临床圆锥角膜检测的端到端深度学习方法。此外，两位临床专家对我们的 KerNet 的预测性能和临床意义进行了很好的评估和验证。我们的代码可在 https://github.com/upzheng/Keratoconus 上获得。
