Alsaih K, Yusoff M Z, Tang T B, Faye I, Mériaudeau F
Centre for Intelligent Signal and Imaging Research (CISIR), Universiti Teknologi PETRONAS, 32610 Bandar Seri Iskandar, Perak, Malaysia.
Centre for Intelligent Signal and Imaging Research (CISIR), Universiti Teknologi PETRONAS, 32610 Bandar Seri Iskandar, Perak, Malaysia.
Comput Methods Programs Biomed. 2020 Oct;195:105566. doi: 10.1016/j.cmpb.2020.105566. Epub 2020 May 26.
Aged people usually are more to be diagnosed with retinal diseases in developed countries. Retinal capillaries leakage into the retina swells and causes an acute vision loss, which is called age-related macular degeneration (AMD). The disease can not be adequately diagnosed solely using fundus images as depth information is not available. The variations in retina volume assist in monitoring ophthalmological abnormalities. Therefore, high-fidelity AMD segmentation in optical coherence tomography (OCT) imaging modality has raised the attention of researchers as well as those of the medical doctors. Many methods across the years encompassing machine learning approaches and convolutional neural networks (CNN) strategies have been proposed for object detection and image segmentation.
In this paper, we analyze four wide-spread deep learning models designed for the segmentation of three retinal fluids outputting dense predictions in the RETOUCH challenge data. We aim to demonstrate how a patch-based approach could push the performance for each method. Besides, we also evaluate the methods using the OPTIMA challenge dataset for generalizing network performance. The analysis is driven into two sections: the comparison between the four approaches and the significance of patching the images.
The performance of networks trained on the RETOUCH dataset is higher than human performance. The analysis further generalized the performance of the best network obtained by fine-tuning it and achieved a mean Dice similarity coefficient (DSC) of 0.85. Out of the three types of fluids, intraretinal fluid (IRF) is more recognized, and the highest DSC value of 0.922 is achieved using Spectralis dataset. Additionally, the highest average DSC score is 0.84, which is achieved by PaDeeplabv3+ model using Cirrus dataset.
The proposed method segments the three fluids in the retina with high DSC value. Fine-tuning the networks trained on the RETOUCH dataset makes the network perform better and faster than training from scratch. Enriching the networks with inputting a variety of shapes by extracting patches helped to segment the fluids better than using a full image.
在发达国家，老年人通常更容易被诊断出患有视网膜疾病。视网膜毛细血管渗漏到视网膜中会导致肿胀，并引起急性视力丧失，这被称为年龄相关性黄斑变性（AMD）。仅使用眼底图像无法充分诊断该疾病，因为无法获得深度信息。视网膜体积的变化有助于监测眼科异常情况。因此，光学相干断层扫描（OCT）成像模式下的高保真AMD分割引起了研究人员以及医生的关注。多年来，已经提出了许多方法，包括机器学习方法和卷积神经网络（CNN）策略，用于目标检测和图像分割。
在本文中，我们分析了四种广泛使用的深度学习模型，这些模型用于在RETOUCH挑战数据中对三种视网膜液体进行分割，并输出密集预测。我们旨在展示基于补丁的方法如何提高每种方法的性能。此外，我们还使用OPTIMA挑战数据集评估这些方法，以概括网络性能。分析分为两个部分：四种方法之间的比较以及对图像进行补丁处理的重要性。
在RETOUCH数据集上训练的网络性能高于人类表现。通过对最佳网络进行微调，分析进一步概括了其性能，并实现了平均骰子相似系数（DSC）为0.85。在三种液体类型中，视网膜内液（IRF）的识别度更高，使用Spectralis数据集实现了最高DSC值0.922。此外，使用Cirrus数据集的PaDeeplabv3 +模型实现了最高平均DSC分数0.84。
所提出的方法以高DSC值分割视网膜中的三种液体。对在RETOUCH数据集上训练的网络进行微调，使网络的性能比从头开始训练更好、更快。通过提取补丁输入各种形状来丰富网络，比使用完整图像更有助于更好地分割液体。
