Medical imaging research is often limited by data scarcity and availability. Governance, privacy concerns and the cost of acquisition all restrict access to medical imaging data, which, compounded by the data-hungry nature of deep learning algorithms, limits progress in the field of healthcare AI. Generative models have recently been used to synthesize photorealistic natural images, presenting a potential solution to the data scarcity problem. But are current generative models synthesizing morphologically correct samples? In this work we present a three-dimensional generative model of the human brain that is trained at the necessary scale to generate diverse, realistic-looking, high-resolution and morphologically preserving samples and conditioned on patient characteristics (for example, age and pathology). We show that the synthetic samples generated by the model preserve biological and disease phenotypes and are realistic enough to permit use downstream in well-established image analysis tools. While the proposed model has broad future applicability, such as anomaly detection and learning under limited data, its generative capabilities can be used to directly mitigate data scarcity, limited data availability and algorithmic fairness.

医学影像研究通常受到数据稀缺和可用性的限制。治理、隐私问题和获取成本都限制了对医学成像数据的访问，再加上深度学习算法对数据的需求，限制了医疗保健人工智能领域的进展。生成模型最近被用来合成逼真的自然图像，为数据稀缺问题提供了潜在的解决方案。但当前的生成模型是否合成了形态正确的样本？在这项工作中，我们提出了一个人脑的三维生成模型，该模型以必要的规模进行训练，以生成多样化、逼真、高分辨率和形态保存的样本，并以患者特征（例如年龄和病理）为条件。 。我们表明，该模型生成的合成样本保留了生物和疾病表型，并且足够真实，可以在下游使用完善的图像分析工具。虽然所提出的模型具有广泛的未来适用性，例如有限数据下的异常检测和学习，但其生成能力可用于直接缓解数据稀缺性、有限的数据可用性和算法公平性。