Quantification of muscle, bones, and fat on single slice thigh CT.
Quantification of muscle, bones, and fat on single slice thigh CT.
复制标题
单层大腿 CT 上肌肉、骨骼和脂肪的量化。
DOI：
10.1117/12.2611664
复制
发表时间：
2022
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;Tang,Yucheng;Bao,Shunxing;Gravenstein,KristoferS;Moore,AnnZenobia;Makrogiannis,Sokratis;Ferrucci,Luigi;Landman,BennettA
大腿CT切片的肌肉、骨骼和脂肪分割是人体成分研究的基础。逐体素图像分割使得能够量化组织特性，包括面积、强度和纹理。深度学习方法在医学图像分割方面取得了巨大的成功，但它们通常需要大量数据。由于人工标注的成本很高，使用有限的人类标记数据训练深度学习模型是可取的，但也是一个具有挑战性的问题。受迁移学习的启发，我们提出了一个两阶段的深度学习管道来解决大腿分割中的这个问题。我们研究了来自巴尔的摩老化纵向研究（BLSA）的2836个切片和来自转化老化实验室测试（GESTALT）的遗传和表观遗传标记的121个切片。首先，我们使用CT强度和解剖形态学基于近似手工制作的方法生成伪标签。然后，这些伪标签被送入深度神经网络，从头开始训练模型。最后，加载第一阶段模型作为初始化，并使用更有限的专家人类标签集进行微调。在56例大腿CT扫描中，对肌肉、皮质骨、内部骨、皮下脂肪和肌间脂肪5种组织的平均Dice分别为0.979，0.969，0.953，0.980和0.800。我们通过手动审查1752个大腿切片中的3504个外部BLSA单大腿来评估可推广性。结果一致，并通过了人工审查与5个失败的大腿图像，这表明该方法具有很强的推广性。
Muscle, bone, and fat segmentation of CT thigh slice is essential for body composition research. Voxel-wise image segmentation enables quantification of tissue properties including area, intensity and texture. Deep learning approaches have had substantial success in medical image segmentation, but they typically require substantial data. Due to high cost of manual annotation, training deep learning models with limited human labelled data is desirable but also a challenging problem. Inspired by transfer learning, we proposed a two-stage deep learning pipeline to address this issue in thigh segmentation. We study 2836 slices from Baltimore Longitudinal Study of Aging (BLSA) and 121 slices from Genetic and Epigenetic Signatures of Translational Aging Laboratory Testing (GESTALT). First, we generated pseudo-labels based on approximate hand-crafted approaches using CT intensity and anatomical morphology. Then, those pseudo labels are fed into deep neural networks to train models from scratch. Finally, the first stage model is loaded as initialization and fine-tuned with a more limited set of expert human labels. We evaluate the performance of this framework on 56 thigh CT scans and obtained average Dice of 0.979,0.969,0.953,0.980 and 0.800 for five tissues: muscle, cortical bone, internal bone, subcutaneous fat and intermuscular fat respectively. We evaluated generalizability by manually reviewing external 3504 BLSA single thighs from 1752 thigh slices. The result is consistent and passed human review with 5 failed thigh images, which demonstrates that the proposed method has strong generalizability.