KerNet: A Novel Deep Learning Approach for Keratoconus and Sub-Clinical Keratoconus Detection Based on Raw Data of the Pentacam HR System
KerNet: A Novel Deep Learning Approach for Keratoconus and Sub-Clinical Keratoconus Detection Based on Raw Data of the Pentacam HR System
复制标题
KerNet：基于 Pentacam HR 系统原始数据的圆锥角膜和亚临床圆锥角膜检测的新型深度学习方法
DOI：
10.1109/jbhi.2021.3079430
复制
发表时间：
2021-10-01
影响因子：
7.7
通讯作者：
Wu, Jian
中科院分区：
文献类型：
--
作者：
Feng, Ruiwei;Xu, Zhe;Wu, Jian
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，并可能导致视力丧失。在本文中，我们提出了一种新的端到端深度学习方法，称为KerNet，它处理由五个数字矩阵组成的Pentacam HR系统的原始数据，以检测圆锥角膜和亚临床圆锥角膜。具体地说，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主干，具有多级融合结构。这五个分支分别接收五个矩阵，并通过多个级联残差块有效地捕捉不同矩阵的特征。多层融合结构(即低层融合和高层融合)适度地考虑了五个切片之间的相关性，并对提取的特征进行融合以获得更好的预测。实验结果表明：(1)在内部数据集上，我们的新方法比最先进的方法提高了~1%的圆锥角膜检测准确率和~4%的亚临床圆锥角膜检测精度；(2)Grad-CAM可视化的注意图显示，我们的KerNet更关注亚临床圆锥角膜的颞下部分，这在以往的临床研究中已经被证明是眼科医生检测亚临床圆锥角膜的识别区域。据我们所知，我们首次提出了一种端到端的深度学习方法，利用Pentacam HR系统获得的原始数据来检测圆锥角膜和亚临床圆锥角膜。此外，我们的KerNet的预测性能和临床意义得到了两位临床专家的良好评估和验证。我们的代码可以在https://github.com/upzheng/Keratoconus.上找到
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.