Laser interstitial thermal therapy (LITT) is a novel minimally invasive treatment that is used to ablate intracranial structures to treat mesial temporal lobe epilepsy (MTLE). Region of interest (ROI) segmentation before and after LITT would enable automated lesion quantification to objectively assess treatment efficacy. Deep learning techniques, such as convolutional neural networks (CNNs) are state-of-the-art solutions for ROI segmentation, but require large amounts of annotated data during the training. However, collecting large datasets from emerging treatments such as LITT is impractical. In this paper, we propose a progressive brain lesion synthesis framework (PAVAE) to expand both the quantity and diversity of the training dataset. Concretely, our framework consists of two sequential networks: a mask synthesis network and a mask-guided lesion synthesis network. To better employ extrinsic information to provide additional supervision during network training, we design a condition embedding block (CEB) and a mask embedding block (MEB) to encode inherent conditions of masks to the feature space. Finally, a segmentation network is trained using raw and synthetic lesion images to evaluate the effectiveness of the proposed framework. Experimental results show that our method can achieve realistic synthetic results and boost the performance of down-stream segmentation tasks above traditional data augmentation techniques.

Keywords: Adversarial variational auto-encoder; Laser interstitial thermal therapy; Progressive lesion synthesis.

激光间质热疗（LITT）是一种新颖的微创治疗方法，用于消融颅内结构以治疗海马硬化伴颞叶癫痫（MTLE）。在进行LITT前后对感兴趣区域（ROI）进行分割可以实现自动化的病变量化，从而客观评估治疗效果。深度学习技术如卷积神经网络（CNNs）是ROI分割的最佳解决方案，但在训练过程中需要大量的标注数据。然而，从新兴的治疗方法如LITT中收集大量数据并不现实。本文提出了一种逐步脑部病灶合成框架（PAVAE），以扩展训练数据集的数量和多样性。具体来说，我们的框架由两个顺序网络组成：一个掩码合成网络和一个基于掩码引导的病灶合成网络。为了更好地利用外部信息在神经网络训练期间提供额外监督，我们设计了一个条件嵌入块（CEB）和一个掩码嵌入块（MEB），以将掩码的固有条件编码到特征空间中。最后，使用原始和合成病变图像来训练分割网络，评估所提出框架的有效性。实验结果表明，我们的方法可以实现逼真的合成效果，并在下游分割任务中的性能优于传统的数据增强技术。

关键词：对抗变分自编码器；激光间质热疗；逐步病灶合成。