Deep learning has gained significant attention in medical image segmentation. However, the limited availability of annotated training data presents a challenge to achieving accurate results. In efforts to overcome this challenge, data augmentation techniques have been proposed. However, the majority of these approaches primarily focus on image generation. For segmentation tasks, providing both images and their corresponding target masks is crucial, and the generation of diverse and realistic samples remains a complex task, especially when working with limited training datasets. To this end, we propose a new end-to-end hybrid architecture based on Hamiltonian Variational Autoencoders (HVAE) and a discriminative regularization to improve the quality of generated images. Our method provides an accuracte estimation of the joint distribution of the images and masks, resulting in the generation of realistic medical images with reduced artifacts and off-distribution instances. As generating 3D volumes requires substantial time and memory, our architecture operates on a slice-by-slice basis to segment 3D volumes, capitilizing on the richly augmented dataset. Experiments conducted on two public datasets, BRATS (MRI modality) and HECKTOR (PET modality), demonstrate the efficacy of our proposed method on different medical imaging modalities with limited data.

翻译：深度学习在医学图像分割领域已获得显著关注。然而，标注训练数据的有限性对实现精确分割结果构成了挑战。为克服这一挑战，数据增强技术已被提出。然而，这些方法大多主要聚焦于图像生成。对于分割任务而言，同时提供图像及其对应的目标掩码至关重要，而生成多样且真实的样本仍是一项复杂任务，尤其是在训练数据集有限的情况下。为此，我们提出了一种基于哈密顿变分自编码器（HVAE）与判别式正则化的新型端到端混合架构，以提升生成图像的质量。我们的方法能够精确估计图像与掩码的联合分布，从而生成伪影减少且分布外实例更少的真实医学图像。由于生成三维体数据需要大量时间与内存，我们的架构采用逐切片处理方式对三维体数据进行分割，充分利用了经强数据增强的数据集。在BRATS（MRI模态）与HECKTOR（PET模态）两个公开数据集上进行的实验表明，所提方法在不同医学成像模态且数据有限的场景下均具有显著效能。