Mendez M, Castillo F, Probyn L, Kras S, Tyrrell P N
Institute of Medical Science, University of Toronto, Toronto, ON, Canada.
Department of Medical Imaging, University of Toronto, Toronto, ONM5T 1W7, Canada.
Int J Comput Assist Radiol Surg. 2025 Feb;20(2):415-431. doi: 10.1007/s11548-024-03309-6. Epub 2024 Dec 29.
This study explores the use of deep generative models to create synthetic ultrasound images for the detection of hemarthrosis in hemophilia patients. Addressing the challenge of sparse datasets in rare disease diagnostics, the study aims to enhance AI model robustness and accuracy through the integration of domain knowledge into the synthetic image generation process.
The study employed two ultrasound datasets: a base dataset (Db) of knee recess distension images from non-hemophiliac patients and a target dataset (Dt) of hemarthrosis images from hemophiliac patients. The synthetic generation framework included a content generator (Gc) trained on Db and a context generator (Gs) to adapt these images to match Dt's context. This approach generated a synthetic target dataset (Ds), primed for AI training in rare disease research. The assessment of synthetic image generation involved expert evaluations, statistical analysis, and the use of domain-invariant perceptual distance and Fréchet inception distance for quality measurement.
Expert evaluation revealed that images produced by our synthetic generation framework were comparable to real ones, with no significant difference in overall quality or anatomical accuracy. Additionally, the use of synthetic data in training convolutional neural networks demonstrated robustness in detecting hemarthrosis, especially with limited sample sizes.
This study presents a novel approach for generating synthetic ultrasound images for rare disease detection, such as hemarthrosis in hemophiliac knees. By leveraging deep generative models and integrating domain knowledge, the proposed framework successfully addresses the limitations of sparse datasets and enhances AI model training and robustness. The synthetic images produced are of high quality and contribute significantly to AI-driven diagnostics in rare diseases, highlighting the potential of synthetic data in medical imaging.
本研究探索使用深度生成模型来创建合成超声图像，用于检测血友病患者的关节积血。针对罕见病诊断中稀疏数据集的挑战，该研究旨在通过将领域知识整合到合成图像生成过程中，提高人工智能模型的稳健性和准确性。
该研究使用了两个超声数据集：一个是来自非血友病患者的膝后隐窝扩张图像的基础数据集（Db），另一个是来自血友病患者的关节积血图像的目标数据集（Dt）。合成生成框架包括一个在Db上训练的内容生成器（Gc）和一个上下文生成器（Gs），以使这些图像适应Dt的上下文。这种方法生成了一个合成目标数据集（Ds），为罕见病研究中的人工智能训练做好了准备。合成图像生成的评估包括专家评估、统计分析，以及使用领域不变感知距离和弗雷歇 inception 距离进行质量测量。
专家评估表明，我们的合成生成框架生成的图像与真实图像相当，在整体质量或解剖准确性上没有显著差异。此外，在训练卷积神经网络时使用合成数据在检测关节积血方面表现出稳健性，尤其是在样本量有限的情况下。
本研究提出了一种用于生成合成超声图像以进行罕见病检测的新方法，例如血友病膝关节中的关节积血。通过利用深度生成模型并整合领域知识，所提出的框架成功解决了稀疏数据集的局限性，并增强了人工智能模型的训练和稳健性。生成的合成图像质量很高，对罕见病的人工智能驱动诊断有显著贡献，突出了合成数据在医学成像中的潜力。
