arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 1906.01796cs.CVcs.AIcs.LGeess.IV
收藏

基于跨任务引导注意力的单遍多任务网络脑肿瘤分割

One-pass Multi-task Networks with Cross-task Guided Attention for Brain Tumor Segmentation

South China University of Technology(华南理工大学);Stevens Institute of Technology(史蒂文斯理工学院);Southern Medical University(南方医科大学);UBTech Sydney Artificial Intelligence Centre(优必选悉尼人工智能中心);The University of Sydney(悉尼大学)

Chenhong Zhou, Changxing Ding, Xinchao Wang, Zhentai Lu, Dacheng Tao

摘要:

类不平衡已成为医学图像分割的主要挑战之一。模型级联(MC)策略通过运行一组单独的深度模型进行从粗到细的分割,显著地解决了类不平衡问题。然而,尽管其出色的性能,这种方法导致不希望的系统复杂性,也忽略了模型之间的相关性。为了处理这些缺陷,我们提出了一个轻量级的深度模型,即,单遍多任务网络(OM-Net)比MC更好地解决类不平衡问题,同时只需一遍计算。首先,OM-Net将单独的分割任务集成到一个深度模型中,该模型由用于学习联合特征的共享参数以及用于学习区分特征的特定于任务的参数组成。其次,为了更有效地优化OM-Net,我们利用任务之间的相关性,设计了在线训练数据传输策略和基于课程学习的训练策略。第三,我们进一步提出在任务之间共享预测结果,并设计了一个跨任务引导注意力(CGA)模块,该模块可以根据特定类别的统计数据自适应地重新校准通道特征响应。最后,一个简单而有效的后处理方法,介绍了细化分割结果。进行了大量的实验,以证明所提出的技术的有效性。最令人印象深刻的是,我们在BraTS 2015测试集和BraTS 2017在线验证集上实现了最先进的性能。使用这些方法,我们还在BraTS 2018挑战赛中在64个参赛团队中获得了第三名。该代码可在https://github.com/chenhong-zhou/OM-Net上公开获取。

英文摘要:

Class imbalance has emerged as one of the major challenges for medical image segmentation. The model cascade (MC) strategy significantly alleviates the class imbalance issue via running a set of individual deep models for coarse-to-fine segmentation. Despite its outstanding performance, however, this method leads to undesired system complexity and also ignores the correlation among the models. To handle these flaws, we propose a light-weight deep model, i.e., the One-pass Multi-task Network (OM-Net) to solve class imbalance better than MC does, while requiring only one-pass computation. First, OM-Net integrates the separate segmentation tasks into one deep model, which consists of shared parameters to learn joint features, as well as task-specific parameters to learn discriminative features. Second, to more effectively optimize OM-Net, we take advantage of the correlation among tasks to design both an online training data transfer strategy and a curriculum learning-based training strategy. Third, we further propose sharing prediction results between tasks and design a cross-task guided attention (CGA) module which can adaptively recalibrate channel-wise feature responses based on the category-specific statistics. Finally, a simple yet effective post-processing method is introduced to refine the segmentation results. Extensive experiments are conducted to demonstrate the effectiveness of the proposed techniques. Most impressively, we achieve state-of-the-art performance on the BraTS 2015 testing set and BraTS 2017 online validation set. Using these proposed approaches, we also won joint third place in the BraTS 2018 challenge among 64 participating teams. The code is publicly available at https://github.com/chenhong-zhou/OM-Net.

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。

↑