Segmentation-guided domain adaptation and data harmonization of multi-device retinal optical coherence tomography using cycle-consistent generative adversarial networks
Segmentation-guided domain adaptation and data harmonization of multi-device retinal optical coherence tomography using cycle-consistent generative adversarial networks
复制标题
DOI：
10.1016/j.compbiomed.2023.106595
复制
发表时间：
2023-04-21
影响因子：
7.7
通讯作者：
Beg, Mirza Faisal
中科院分区：
文献类型：
--
作者：
Chen, Shuo;Ma, Da;Beg, Mirza Faisal
背景：从不同设备获得的医学图像，如光学相干断层扫描（OCT）图像，可能显示出明显不同的强度分布。在一台设备上训练的自动分割模型在应用于另一台设备获取的图像时可能表现不佳，导致缺乏泛化性。本研究使用由循环一致生成对抗网络（CycleGAN）改进的领域自适应方法解决了这个问题，特别是当基础真值标签仅在源域中可用时。方法：提出了一种两阶段流水线的分割方法。第一阶段包括在源域中训练最先进的分割模型。第二阶段是将图像从目标域调整到源域。第一阶段使用该模型对适应后的目标域图像进行分割。对不同的损失函数进行积分烧蚀试验，并报告了这些模型的统计显著性。对分割性能和自适应图像质量指标进行了评价。结果：在分割骰子得分方面，本文提出的模型ssppg与未进行自适应相比，取得了46.24%的显著提高，达到了分割性能上限的87.4%。此外，图像质量指标，包括FID和KID分数，表明具有更好分割的适应图像也具有更好的图像质量。结论：该方法验证了分割驱动的区域自适应在视网膜成像处理中的有效性。它降低了人工标记的人工成本，结合了先前的解剖信息来调节和指导域适应，并为提高无标签图像域的分割质量提供了见解。
Background: Medical images such as Optical Coherence Tomography (OCT) images acquired from different devices may show significantly different intensity profiles. An automatic segmentation model trained on images from one device may perform poorly when applied to images acquired using another device, resulting in a lack of generalizability. This study addresses this issue using domain adaptation methods improved by Cycle-Consistent Generative Adversarial Networks (CycleGAN), especially when the ground-truth labels are only available in the source domain.Methods: A two-stage pipeline is proposed to generate segmentation in the target domain. The first stage involves the training of a state-of-the-art segmentation model in the source domain. The second stage aims to adapt the images from the target domain to the source domain. The adapted target domain images are segmented using the model in the first stage. Ablation tests were performed with integration of different loss functions, and the statistical significance of these models is reported. Both the segmentation performance and the adapted image quality metrics were evaluated.Results: Regarding the segmentation Dice score, the proposed model ssppg achieves a significant improvement of 46.24% compared to without adaptation and reaches 87.4% of the upper limit of the segmentation performance. Furthermore, image quality metrics, including FID and KID scores, indicate that adapted images with better segmentation also have better image qualities. Conclusion: The proposed method demonstrates the effectiveness of segmentation-driven domain adaptation in retinal imaging processing. It reduces the labor cost of manual labeling, incorporates prior anatomic information to regulate and guide domain adaptation, and provides insights into improving segmentation qualities in image domains without labels.