Single slice thigh CT muscle group segmentation with domain adaptation and self-training.
Single slice thigh CT muscle group segmentation with domain adaptation and self-training.
复制标题
具有域适应和自我训练的单层大腿 CT 肌肉群分割。
DOI：
10.1117/1.jmi.10.4.044001
复制
发表时间：
2023
期刊：
影响因子：
--
通讯作者：
Landman,BennettA
中科院分区：
文献类型：
--
作者：
Yang,Qi;Yu,Xin;Lee,HoHin;Cai,LeonY;Xu,Kaiwen;Bao,Shunxing;Huo,Yuankai;Moore,AnnZenobia;Makrogiannis,Sokratis;Ferrucci,Luigi;Landman,BennettA
目的大腿肌肉群分割对于评估肌肉解剖学、代谢疾病和衰老很重要。人们在利用磁共振 (MR) 成像量化肌肉组织方面做出了许多努力，包括对单个肌肉进行手动注释。然而，利用 MR 图像中公开可用的注释来实现单切片计算机断层扫描 (CT) 大腿图像上的肌肉群分割具有挑战性。我们提出了一种具有自训练功能的无监督域适应管道，可将标签从三维 MR 转移到单 CT 切片。首先，我们使用 CycleGAN 将图像外观从 MR 转换为 CT，并将合成的 CT 图像同时输入到分割器。根据分割器预测的伪标签的熵，将单个 CT 切片分为困难组和简单组。基于解剖学假设精炼简单队列伪标签后，应用简单和硬分割的自我训练来微调分割器。结果在 152 个保留的单 CT 大腿图像上，所提出的管道在所有肌肉群（包括股薄肌、腿筋、股四头肌和缝匠肌）上实现了 0.888 (0.041) 的平均 Dice。结论据我们所知，这是第一个实现大腿图像从 MR 到 CT 的域适应。所提出的流程有效且稳健地提取二维单层 CT 大腿图像上的肌肉群。该容器可在 GitHub 存储库中供公众使用，网址为：https://github.com/MASILab/DA_CT_muscle_seg。
PurposeThigh muscle group segmentation is important for assessing muscle anatomy, metabolic disease, and aging. Many efforts have been put into quantifying muscle tissues with magnetic resonance (MR) imaging, including manual annotation of individual muscles. However, leveraging publicly available annotations in MR images to achieve muscle group segmentation on single-slice computed tomography (CT) thigh images is challenging.ApproachWe propose an unsupervised domain adaptation pipeline with self-training to transfer labels from three-dimensional MR to single CT slices. First, we transform the image appearance from MR to CT with CycleGAN and feed the synthesized CT images to a segmenter simultaneously. Single CT slices are divided into hard and easy cohorts based on the entropy of pseudo-labels predicted by the segmenter. After refining easy cohort pseudo-labels based on anatomical assumption, self-training with easy and hard splits is applied to fine-tune the segmenter.ResultsOn 152 withheld single CT thigh images, the proposed pipeline achieved a mean Dice of 0.888 (0.041) across all muscle groups, including gracilis, hamstrings, quadriceps femoris, and sartorius muscle.ConclusionsTo our best knowledge, this is the first pipeline to achieve domain adaptation from MR to CT for thigh images. The proposed pipeline effectively and robustly extracts muscle groups on two-dimensional single-slice CT thigh images. The container is available for public use in GitHub repository available at: https://github.com/MASILab/DA_CT_muscle_seg.