无需人工标注的用于精细视网膜血管分割的合成光学相干断层扫描血管造影图像
Synthetic optical coherence tomography angiographs for detailed retinal vessel segmentation without human annotations
AI总结：
针对缺乏标注数据集限制OCTA视网膜血管深度学习分割的问题，提出基于空间殖民的轻量级合成方法与三种对比度适应流水线，在三个公开数据集上实现优于传统方法及监督训练的分割效果，并开源全套资源。
摘要：
光学相干断层扫描血管造影（Optical coherence tomography angiography, OCTA）是一种非侵入性成像模态，可获取视网膜脉管系统的高分辨率体数据，辅助眼部、神经和心脏疾病的诊断。分割可见血管是从这些图像中提取定量生物标志物的常见第一步。基于阈值的经典分割算法会受到图像伪影和信噪比有限的强烈影响。由于缺乏带有详细血管标注的大型数据集，现代基于深度学习的分割方法的应用受到了限制。为解决这一问题，近期研究采用了迁移学习，即在合成OCTA图像上训练分割网络，再将其应用于真实数据。但此前提出的模拟方法无法忠实地建模视网膜脉管系统，也无法提供有效的域适应。正因如此，现有方法无法完整分割视网膜脉管系统，尤其是最细小的毛细血管。在本研究中，我们提出了一种基于空间殖民算法的视网膜血管网络轻量级模拟方法，可实现更快、更真实的OCTA合成。随后我们引入了三种对比度适应流水线，以缩小真实图像与人工合成图像之间的域差距。我们在三个公开数据集上开展了大量定量与定性实验，将我们的方法与传统计算机视觉算法以及使用人工标注的监督训练进行对比，证明了我们的方法具备更优的分割性能。最后，我们将整套流水线公开，包括源代码、预训练模型以及一个大型合成OCTA图像数据集。
英文摘要：
Optical coherence tomography angiography (OCTA) is a non-invasive imaging modality that can acquire high-resolution volumes of the retinal vasculature and aid the diagnosis of ocular, neurological and cardiac diseases. Segmenting the visible blood vessels is a common first step when extracting quantitative biomarkers from these images. Classical segmentation algorithms based on thresholding are strongly affected by image artifacts and limited signal-to-noise ratio. The use of modern, deep learning-based segmentation methods has been inhibited by a lack of large datasets with detailed annotations of the blood vessels. To address this issue, recent work has employed transfer learning, where a segmentation network is trained on synthetic OCTA images and is then applied to real data. However, the previously proposed simulations fail to faithfully model the retinal vasculature and do not provide effective domain adaptation. Because of this, current methods are unable to fully segment the retinal vasculature, in particular the smallest capillaries. In this work, we present a lightweight simulation of the retinal vascular network based on space colonization for faster and more realistic OCTA synthesis. We then introduce three contrast adaptation pipelines to decrease the domain gap between real and artificial images. We demonstrate the superior segmentation performance of our approach in extensive quantitative and qualitative experiments on three public datasets that compare our method to traditional computer vision algorithms and supervised training using human annotations. Finally, we make our entire pipeline publicly available, including the source code, pretrained models, and a large dataset of synthetic OCTA images.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
