发表机构
Univ. Lyon; INSA Lyon; UCBL; CNRS; Inserm; CREATIS（里昂大学; 里昂国立应用科学学院; 里昂第一大学; 法国国家科学研究中心; 法国国家健康与医学研究院; CREATIS）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出OTLesMix方法，利用Wasserstein重心与最优传输映射生成多样化合成病灶，在三项脑病灶分割任务上使Dice分数提升2.9至6.6个百分点，性能优于现有混合类方法。
AI 中文摘要
过去十年深度学习的发展革新了医学图像分割，可从海量数据中提取精确描述符以表征病理特征。数据增强被广泛认为是提升模型训练效果的技术，既包含空间操作、强度修改等简单变换，也包含更先进的合成技术，其目标是从现有数据集生成新的真实样本，以丰富训练所用图像。其中多项研究提出不同混合策略来结合真实样本，但这些方法的主要缺陷之一是生成病灶的形状与位置多样性有限。本研究提出一种名为OTLesMix的新型图像合成方法，利用Wasserstein重心与最优传输计划生成真实且多样化的样本。我们在三项脑病灶分割任务上评估了该方法，结果显示，与未使用合成数据训练的模型相比，该方法使Dice分数提升了2.9至6.6个百分点，且优于现有最先进的基于混合的方法。
英文摘要
The development of deep learning over the past decade has revolutionized medical imaging segmentation, allowing the extraction of precise descriptors from large volumes to characterize pathologies. Data augmentation is a technique widely regarded as a way to improve model training. It includes simple transformations like spatial operations or intensity modifications, but also more advanced synthesis techniques. Their goal is to generate new realistic samples from an existing dataset to diversify the images used during training. Among them, several propose different mixing strategies to combine real samples. However, one of their major shortcomings is to yield limited variability in terms of generated lesion shapes and locations. In this work, we introduce a novel image synthesis method, called OTLesMix, that leverages Wasserstein barycenter and optimal transport plan to generate realistic and diverse samples. We evaluated our method on three brain lesion segmentation tasks, on which it improves the Dice score compared to a model trained without synthetic data by 2.9 to 6.6 points, and outperforms state-of-the-art mix-based methods.
