International Journal of Computer Assisted Radiology and Surgery ( IF 3 ) Pub Date : 2021-04-16 , DOI: 10.1007/s11548-021-02363-8 Pengbo Liu 1 , Hu Han 1 , Yuanqi Du 2 , Heqin Zhu 1 , Yinhao Li 1 , Feng Gu 1, 3 , Honghu Xiao 4 , Jun Li 1 , Chunpeng Zhao 4 , Li Xiao 1 , Xinbao Wu 4 , S Kevin Zhou 1, 5
Purpose:
Pelvic bone segmentation in CT has always been an essential step in clinical diagnosis and surgery planning of pelvic bone diseases. Existing methods for pelvic bone segmentation are either hand-crafted or semi-automatic and achieve limited accuracy when dealing with image appearance variations due to the multi-site domain shift, the presence of contrasted vessels, coprolith and chyme, bone fractures, low dose, metal artifacts, etc. Due to the lack of a large-scale pelvic CT dataset with annotations, deep learning methods are not fully explored.
Methods:
In this paper, we aim to bridge the data gap by curating a large pelvic CT dataset pooled from multiple sources, including 1184 CT volumes with a variety of appearance variations. Then, we propose for the first time, to the best of our knowledge, to learn a deep multi-class network for segmenting lumbar spine, sacrum, left hip, and right hip, from multiple-domain images simultaneously to obtain more effective and robust feature representations. Finally, we introduce a post-processor based on the signed distance function (SDF).
Results:
Extensive experiments on our dataset demonstrate the effectiveness of our automatic method, achieving an average Dice of 0.987 for a metal-free volume. SDF post-processor yields a decrease of 15.1% in Hausdorff distance compared with traditional post-processor.
Conclusion:
We believe this large-scale dataset will promote the development of the whole community and open source the images, annotations, codes, and trained baseline models at https://github.com/ICT-MIRACLE-lab/CTPelvic1K.
中文翻译:
深度学习分割骨盆骨骼:大规模CT数据集和基线模型
目的:
CT的骨盆骨分割术一直是骨盆骨疾病的临床诊断和手术计划中必不可少的步骤。现有的骨盆骨分割方法是手工制作的或半自动的,由于多位域移位,对比血管,共前列腺和食糜的存在,骨折,低剂量,金属制品等。由于缺少带有注释的大型骨盆CT数据集,因此尚未全面探索深度学习方法。
方法:
在本文中,我们旨在通过整理从多个来源汇集的大型骨盆CT数据集来弥合数据鸿沟,包括具有各种外观变化的1184个CT量。然后,根据我们的知识,我们首次建议学习一个深层的多类网络,以同时从多域图像中分割腰椎,ac骨,左髋和右髋,以获取更有效和更强大的功能特征表示。最后,我们介绍一种基于符号距离函数(SDF)的后处理器。
结果:
在我们的数据集上进行的大量实验证明了我们的自动方法的有效性,无金属体积的平均Dice达到0.987。与传统的后处理器相比,SDF后处理器的Hausdorff距离减少了15.1%。
结论:
我们相信,这个大规模的数据集将促进整个社区的发展,并在https://github.com/ICT-MIRACLE-lab/CTPelvic1K上开源图像,注释,代码和经过训练的基线模型。