Annu Int Conf IEEE Eng Med Biol Soc. 2021 Nov;2021:2790-2793. doi: 10.1109/EMBC46164.2021.9631043.
In this paper, we proposed and validated a multi-task based deep learning method for simultaneously segmenting the foveal avascular zone (FAZ) and classifying three ocular disease related states (normal, diabetic, and myopia) utilizing optical coherence tomography angiography (OCTA) images. The essential motivation of this work is that reliable predictions on disease states may be made based on features extracted from a segmentation network, by sharing a same encoder between the classification network and the segmentation network. In this study, a cotraining network structure was designed for simultaneous ocular disease discrimination and FAZ segmentation. Specifically, we made use of a classification head following a segmentation network's encoder, so that the classification branch used the feature information extracted in the segmentation branch to improve the classification results. The performance of our proposed network structure has been tested and validated on the FAZID dataset, with the best Dice and Jaccard being 0.9031±0.0772 and 0.8302 ±0.0990 for FAZ segmentation, and the best Accuracy and Kappa being 0.7533 and 0.6282 for classifying three ocular disease related states.Clinical Relevance- This work provides a useful tool for segmenting FAZ and discriminating three ocular disease related states utilizing OCTA images, which has a great clinical potential in ocular disease screening and biomarker delivering.
在本文中，我们提出并验证了一种基于多任务的深度学习方法，用于同时分割中心凹无血管区（FAZ）和利用光相干断层扫描血管造影（OCTA）图像对三种与眼病相关的状态（正常、糖尿病和近视）进行分类。这项工作的基本动机是，通过在分类网络和分割网络之间共享同一个编码器，可以从分割网络中提取特征，从而对疾病状态做出可靠的预测。在这项研究中，我们设计了一种联合训练网络结构，用于同时进行眼病鉴别和 FAZ 分割。具体来说，我们在分割网络的编码器后使用分类头，使分类分支利用分割分支中提取的特征信息来提高分类结果。我们提出的网络结构的性能已在 FAZID 数据集上进行了测试和验证，FAZ 分割的最佳 Dice 和 Jaccard 分别为 0.9031±0.0772 和 0.8302 ±0.0990，三种与眼病相关的状态的分类的最佳准确率和 Kappa 分别为 0.7533 和 0.6282。临床意义- 这项工作为利用 OCTA 图像分割 FAZ 和鉴别三种与眼病相关的状态提供了一种有用的工具，在眼病筛查和生物标志物检测方面具有很大的临床潜力。
