论文标题
解开启用跨域海马分段
Disentanglement enables cross-domain Hippocampus Segmentation
论文作者
论文摘要
有限的标记培训数据是医学成像中的常见问题。这使得训练良好的模型很难，因此通常会导致未知领域的失败。磁共振成像（MRI）扫描中的海马分割对于诊断和治疗神经心理疾病至关重要。对比度或形状的域差异会显着影响分割。我们通过将T1加权MRI图像分解为其内容和域来解决此问题。这种分离使我们能够执行域转移，从而将数据从新来源转换为培训领域。因此，此步骤简化了细分问题，从而导致更高质量的分割。我们使用拟议的新方法“内容域分解gan”实现了分离，我们建议在转化的输出上重新审查UNET，以处理GAN特定的人工制品。通过这些更改，我们能够将看不见的域的性能提高6-13％，并胜过最先进的域转移方法。
Limited amount of labelled training data are a common problem in medical imaging. This makes it difficult to train a well-generalised model and therefore often leads to failure in unknown domains. Hippocampus segmentation from magnetic resonance imaging (MRI) scans is critical for the diagnosis and treatment of neuropsychatric disorders. Domain differences in contrast or shape can significantly affect segmentation. We address this issue by disentangling a T1-weighted MRI image into its content and domain. This separation enables us to perform a domain transfer and thus convert data from new sources into the training domain. This step thus simplifies the segmentation problem, resulting in higher quality segmentations. We achieve the disentanglement with the proposed novel methodology 'Content Domain Disentanglement GAN', and we propose to retrain the UNet on the transformed outputs to deal with GAN-specific artefacts. With these changes, we are able to improve performance on unseen domains by 6-13% and outperform state-of-the-art domain transfer methods.
