arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2005.10439eess.IVcs.CVcs.LG
收藏

HF-UNet:在多任务U-Net中分层学习任务间相关性以实现准确的前列腺分割

HF-UNet: Learning Hierarchically Inter-Task Relevance in Multi-Task U-Net for Accurate Prostate Segmentation

Nanjing University(南京大学);National Institute of Healthcare Data Science at Nanjing University(南京大学医疗健康数据科学国家研究院);Nanjing Drum Tower Hospital, Nanjing University Medical School(南京大学医学院附属鼓楼医院);Shanghai United Imaging Intelligence Co., Ltd.(上海联影智能科技有限公司);Korea University(高丽大学)

Kelei He, Chunfeng Lian, Bing Zhang, Xin Zhang, Xiaohuan Cao, Dong Nie, Yang Gao, Junfeng Zhang, Dinggang Shen

摘要:

前列腺的精确分割是体外放射治疗的关键步骤。在本文中,我们通过两阶段网络解决了CT图像中前列腺分割的挑战性任务,其中1)第一阶段用于快速定位,2)第二阶段用于准确分割前列腺。为了在第二阶段中精确地分割前列腺,我们将前列腺分割制定为多任务学习框架,该框架包括分割前列腺的主任务和描绘前列腺边界的辅助任务。这里,第二个任务被应用于提供CT图像中不清楚的前列腺边界的额外引导。此外,传统的多任务深度网络通常共享大部分参数(即,特征表示),这可能会限制它们的数据拟合能力,因为不同任务的特殊性不可避免地被忽略。相比之下,我们解决他们的层次融合的U-Net结构,即HF-UNet。HF-UNet有两个互补的分支用于两个任务,新提出的基于注意力的任务一致性学习块在两个解码分支之间的每个级别进行通信。因此,HF-UNet赋予了分层学习不同任务的共享表示的能力,并同时保留不同任务的学习表示的特异性。我们对所提出的方法在大型计划CT图像数据集上进行了广泛的评估,其中包括从339名患者采集的图像。实验结果表明,HF-UNet的性能优于传统的多任务网络架构和国家的最先进的方法。

英文摘要:

Accurate segmentation of the prostate is a key step in external beam radiation therapy treatments. In this paper, we tackle the challenging task of prostate segmentation in CT images by a two-stage network with 1) the first stage to fast localize, and 2) the second stage to accurately segment the prostate. To precisely segment the prostate in the second stage, we formulate prostate segmentation into a multi-task learning framework, which includes a main task to segment the prostate, and an auxiliary task to delineate the prostate boundary. Here, the second task is applied to provide additional guidance of unclear prostate boundary in CT images. Besides, the conventional multi-task deep networks typically share most of the parameters (i.e., feature representations) across all tasks, which may limit their data fitting ability, as the specificities of different tasks are inevitably ignored. By contrast, we solve them by a hierarchically-fused U-Net structure, namely HF-UNet. The HF-UNet has two complementary branches for two tasks, with the novel proposed attention-based task consistency learning block to communicate at each level between the two decoding branches. Therefore, HF-UNet endows the ability to learn hierarchically the shared representations for different tasks, and preserve the specificities of learned representations for different tasks simultaneously. We did extensive evaluations of the proposed method on a large planning CT image dataset, including images acquired from 339 patients. The experimental results show HF-UNet outperforms the conventional multi-task network architectures and the state-of-the-art methods.

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。

↑