arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2303.09212cs.CV
收藏

GDDS:采用组深度密集监督的肺细支气管分割

GDDS: Pulmonary Bronchioles Segmentation with Group Deep Dense Supervision

University of Science and Technology of China(中国科学技术大学);Second Affiliated Hospital, Naval Medical University(海军军医大学第二附属医院);Suzhou Aerospace Information Research Institute(苏州航天信息研究院)

Mingyue Zhao, Shang Zhao, Quan Quan, Li Fan, Xiaolan Qiu, Shiyuan Liu, S. Kevin Zhou

摘要:

气道分割,特别是细支气管分割,是一个重要的,但具有挑战性的任务,因为远端支气管分布稀疏,规模小。现有的神经网络通常利用稀疏拓扑结构来学习细支气管的连通性,而利用低效的浅层特征来捕获这种高频信息,从而导致单个细支的断裂或错过检测。为了解决这些问题,我们提出了一种新的支气管分割方法的基础上组深度密集监督(GDDS),强调细支气管分割在一个简单而有效的方式。首先,通过巧妙地构造局部稠密拓扑,并在特定的浅特征层上实现稠密拓扑学习,提出了深度稠密监督(DDS)。GDDS进一步赋予浅特征以更好的感知能力来检测细支气管,即使是肉眼不易辨别的细支气管。在BAS基准数据集上进行的大量实验表明,我们的方法促进了网络在捕获细尺度分支方面的高灵敏度,并且在仅引入少量额外参数的情况下,大幅优于最先进的方法(BD为+12.8%,TD为+8.8%)。

英文摘要:

Airway segmentation, especially bronchioles segmentation, is an important but challenging task because distal bronchus are sparsely distributed and of a fine scale. Existing neural networks usually exploit sparse topology to learn the connectivity of bronchioles and inefficient shallow features to capture such high-frequency information, leading to the breakage or missed detection of individual thin branches. To address these problems, we contribute a new bronchial segmentation method based on Group Deep Dense Supervision (GDDS) that emphasizes fine-scale bronchioles segmentation in a simple-but-effective manner. First, Deep Dense Supervision (DDS) is proposed by constructing local dense topology skillfully and implementing dense topological learning on a specific shallow feature layer. GDDS further empowers the shallow features with better perception ability to detect bronchioles, even the ones that are not easily discernible to the naked eye. Extensive experiments on the BAS benchmark dataset have shown that our method promotes the network to have a high sensitivity in capturing fine-scale branches and outperforms state-of-the-art methods by a large margin (+12.8 % in BD and +8.8 % in TD) while only introducing a small number of extra parameters.

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。

↑