arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2008.12205cs.CVeess.IV
收藏

基于随机风格转换的形状与空间信息融合领域泛化网络

Random Style Transfer based Domain Generalization Networks Integrating Shape and Spatial Information

Shanghai Jiao Tong University(上海交通大学);Fudan University(复旦大学);Fuzhou University(福州大学)

Lei Li, Veronika A. Zimmer, Wangbin Ding, Fuping Wu, Liqin Huang, Julia A. Schnabel, Xiahai Zhuang

摘要:

基于深度学习(DL)的模型在医学图像分割中表现出良好的性能。然而,在已知数据集上训练的模型在从不同中心、供应商和疾病人群收集的未知数据集上执行时往往会失败。在这项工作中,我们提出了一个随机风格的传输网络,以解决多供应商和中心心脏图像分割的领域泛化问题。风格转移用于生成具有更宽分布/异质性的训练数据,即域增强。由于目标领域可能是未知的,我们在风格转移阶段随机生成目标模态的模态向量,以模拟未知领域的领域转移。该模型可以通过同时优化监督分割和无监督风格翻译目标以半监督方式进行训练。此外,该框架通过引入两个正则化项,融合了目标的空间信息和形状先验。我们评估了M\&Ms挑战赛2020中40个主题的建议框架,并在未知供应商和中心的数据分割中获得了有希望的性能。

英文摘要:

Deep learning (DL)-based models have demonstrated good performance in medical image segmentation. However, the models trained on a known dataset often fail when performed on an unseen dataset collected from different centers, vendors and disease populations. In this work, we present a random style transfer network to tackle the domain generalization problem for multi-vendor and center cardiac image segmentation. Style transfer is used to generate training data with a wider distribution/ heterogeneity, namely domain augmentation. As the target domain could be unknown, we randomly generate a modality vector for the target modality in the style transfer stage, to simulate the domain shift for unknown domains. The model can be trained in a semi-supervised manner by simultaneously optimizing a supervised segmentation and an unsupervised style translation objective. Besides, the framework incorporates the spatial information and shape prior of the target by introducing two regularization terms. We evaluated the proposed framework on 40 subjects from the M\&Ms challenge2020, and obtained promising performance in the segmentation for data from unknown vendors and centers.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑