School of Advanced Technologies in Medicine, Medical Image and Signal Processing Research Center, Isfahan University of Medical Sciences, Isfahan, Isfahan, Iran.
Sunderland Eye Infirmary, Sunderland, Tyne and Wear, UK.
Transl Vis Sci Technol. 2022 Oct 3;11(10):10. doi: 10.1167/tvst.11.10.10.
Optical coherence tomography (OCT) has recently emerged as a source for powerful biomarkers in neurodegenerative diseases such as multiple sclerosis (MS) and neuromyelitis optica (NMO). The application of machine learning techniques to the analysis of OCT data has enabled automatic extraction of information with potential to aid the timely diagnosis of neurodegenerative diseases. These algorithms require large amounts of labeled data, but few such OCT data sets are available now.
To address this challenge, here we propose a synthetic data generation method yielding a tailored augmentation of three-dimensional (3D) OCT data and preserving differences between control and disease data. A 3D active shape model is used to produce synthetic retinal layer boundaries, simulating data from healthy controls (HCs) as well as from patients with MS or NMO.
To evaluate the generated data, retinal thickness maps are extracted and evaluated under a broad range of quality metrics. The results show that the proposed model can generate realistic-appearing synthetic maps. Quantitatively, the image histograms of the synthetic thickness maps agree with the real thickness maps, and the cross-correlations between synthetic and real maps are also high. Finally, we use the generated data as an augmentation technique to train stronger diagnostic models than those using only the real data.
This approach provides valuable data augmentation, which can help overcome key bottlenecks of limited data.
By addressing the challenge posed by limited data, the proposed method helps apply machine learning methods to diagnose neurodegenerative diseases from retinal imaging.
光学相干断层扫描（OCT）最近已成为多发性硬化症（MS）和视神经脊髓炎（NMO）等神经退行性疾病的强大生物标志物的来源。机器学习技术在 OCT 数据分析中的应用使得自动提取具有辅助神经退行性疾病及时诊断潜力的信息成为可能。这些算法需要大量的标记数据，但目前很少有这样的 OCT 数据集。
为了解决这个挑战，我们在这里提出了一种合成数据生成方法，对三维（3D）OCT 数据进行有针对性的扩充，并保留了健康对照组和 MS 或 NMO 患者之间的数据差异。使用 3D 主动形状模型生成合成视网膜层边界，模拟健康对照组（HC）和 MS 或 NMO 患者的数据。
为了评估生成的数据，我们在广泛的质量指标下提取和评估视网膜厚度图。结果表明，所提出的模型可以生成逼真的合成图。定量地，合成厚度图的图像直方图与真实厚度图一致，并且合成图和真实图之间的互相关系数也很高。最后，我们使用生成的数据作为增强技术来训练比仅使用真实数据更强的诊断模型。
该方法提供了有价值的数据增强，有助于克服数据有限的关键瓶颈。
田鸽
