Simulation and Synthesis in Medical Imaging - 7th International Workshop, SASHIMI 2022, Held in Conjunction with MICCAI 2022, Singapore, September 18, 2022, Proceedings
Simulation and Synthesis in Medical Imaging - 7th International Workshop, SASHIMI 2022, Held in Conjunction with MICCAI 2022, Singapore, September 18, 2022, Proceedings
复制标题
医学影像模拟与综合 - 第七届国际研讨会，SASHIMI 2022，与 MICCAI 2022 联合举行，新加坡，2022 年 9 月 18 日，会议记录
DOI：
10.1007/978-3-031-16980-9_8
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
Fernandez V
中科院分区：
文献类型：
--
作者：
Fernandez V
为了实现良好的性能和通用性，医学图像分割模型应该在具有足够可变性的大数据集上进行训练。由于道德和治理方面的限制，以及与标签数据相关的成本，科学发展往往受到抑制，模型在有限的数据上得到训练和测试。数据增广通常用于人为增加数据分布的变异性并提高模型的通用性。最近的工作已经探索了用于图像合成的深度生成模型，因为这种方法将能够有效地生成无限数量的各种数据，解决通用性和数据访问问题。然而，许多提出的解决方案限制了用户对生成内容的控制。在这项工作中，我们提出了brainSPADE，一个模型，它结合了一个合成的基于扩散的标签生成器与语义图像生成器。我们的模型可以按需生成完全合成的大脑标签，无论是否有感兴趣的病理，然后生成任意引导风格的相应MRI图像。实验表明，brainSPADE合成数据可用于训练分割模型，其性能与在真实的数据上训练的模型相当。
In order to achieve good performance and generalisability, medical image segmentation models should be trained on sizeable datasets with sufficient variability. Due to ethics and governance restrictions, and the costs associated with labelling data, scientific development is often stifled, with models trained and tested on limited data. Data augmentation is often used to artificially increase the variability in the data distribution and improve model generalisability. Recent works have explored deep generative models for image synthesis, as such an approach would enable the generation of an effectively infinite amount of varied data, addressing the generalisability and data access problems. However, many proposed solutions limit the user’s control over what is generated. In this work, we propose brainSPADE, a model which combines a synthetic diffusion-based label generator with a semantic image generator. Our model can produce fully synthetic brain labels on-demand, with or without pathology of interest, and then generate a corresponding MRI image of an arbitrary guided style. Experiments show that brainSPADE synthetic data can be used to train segmentation models with performance comparable to that of models trained on real data.