第三腰椎水平的骨骼肌分割：低剂量计算机断层扫描的轻量化算法。

Skeletal Muscle Segmentation at the Level of the Third Lumbar Vertebra (L3) in Low-Dose Computed Tomography: A Lightweight Algorithm.

机构信息

School of Electronic and Information Engineering, Beijing Jiaotong University, Beijing 100044, China.

Key Laboratory of Carcinogenesis and Translational Research (Ministry of Education/Beijing), Department of Radiation Oncology, Peking University Cancer Hospital & Institute, Beijing 100142, China.

出版信息

Tomography. 2024 Sep 13;10(9):1513-1526. doi: 10.3390/tomography10090111.

DOI:10.3390/tomography10090111

PMID:39330757

原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC11435900/

Abstract

BACKGROUND

The cross-sectional area of skeletal muscles at the level of the third lumbar vertebra (L3) measured from computed tomography (CT) images is an established imaging biomarker used to assess patients' nutritional status. With the increasing prevalence of low-dose CT scans in clinical practice, accurate and automated skeletal muscle segmentation at the L3 level in low-dose CT images has become an issue to address. This study proposed a lightweight algorithm for automated segmentation of skeletal muscles at the L3 level in low-dose CT images.

METHODS

This study included 57 patients with rectal cancer, with both low-dose plain and contrast-enhanced pelvic CT image series acquired using a radiotherapy CT scanner. A training set of 30 randomly selected patients was used to develop a lightweight segmentation algorithm, and the other 27 patients were used as the test set. A radiologist selected the most representative axial CT image at the L3 level for both the image series for all the patients, and three groups of observers manually annotated the skeletal muscles in the 54 CT images of the test set as the gold standard. The performance of the proposed algorithm was evaluated in terms of the Dice similarity coefficient (DSC), precision, recall, 95th percentile of the Hausdorff distance (HD95), and average surface distance (ASD). The running time of the proposed algorithm was recorded. An open source deep learning-based AutoMATICA algorithm was compared with the proposed algorithm. The inter-observer variations were also used as the reference.

RESULTS

The DSC, precision, recall, HD95, ASD, and running time were 93.2 ± 1.9% (mean ± standard deviation), 96.7 ± 2.9%, 90.0 ± 2.9%, 4.8 ± 1.3 mm, 0.8 ± 0.2 mm, and 303 ± 43 ms (on CPU) for the proposed algorithm, and 94.1 ± 4.1%, 92.7 ± 5.5%, 95.7 ± 4.0%, 7.4 ± 5.7 mm, 0.9 ± 0.6 mm, and 448 ± 40 ms (on GPU) for AutoMATICA, respectively. The differences between the proposed algorithm and the inter-observer reference were 4.7%, 1.2%, 7.9%, 3.2 mm, and 0.6 mm, respectively, for the averaged DSC, precision, recall, HD95, and ASD.

CONCLUSION

The proposed algorithm can be used to segment skeletal muscles at the L3 level in either the plain or enhanced low-dose CT images.

摘要

背景

从计算机断层扫描（CT）图像上测量的第三腰椎（L3）水平的骨骼肌横截面积是一种已建立的成像生物标志物，用于评估患者的营养状况。随着低剂量 CT 扫描在临床实践中的普及，在低剂量 CT 图像中准确且自动地对 L3 水平的骨骼肌进行分割已成为一个亟待解决的问题。本研究提出了一种用于自动分割低剂量 CT 图像中 L3 水平骨骼肌的轻量级算法。

方法

本研究纳入了 57 例直肠癌患者，其均接受了放疗 CT 扫描仪采集的低剂量盆腔 CT 平扫和增强序列。使用 30 名随机患者的训练集来开发轻量级分割算法，其余 27 名患者作为测试集。一名放射科医生为所有患者的两个图像序列均选择了 L3 水平最具代表性的轴向 CT 图像，三组观察者手动注释了测试集的 54 个 CT 图像中的骨骼肌作为金标准。该算法的性能是通过计算 Dice 相似系数（DSC）、精度、召回率、Hausdorff 距离的第 95 百分位数（HD95）和平均表面距离（ASD）来评估的。记录了所提出算法的运行时间。并将一种开源基于深度学习的 AutoMATICA 算法与所提出的算法进行了比较。还使用了观察者间的变异性作为参考。

结果

所提出算法的 DSC、精度、召回率、HD95、ASD 和运行时间分别为 93.2 ± 1.9%（均值 ± 标准差）、96.7 ± 2.9%、90.0 ± 2.9%、4.8 ± 1.3mm、0.8 ± 0.2mm 和 303 ± 43ms（在 CPU 上），而 AutoMATICA 的分别为 94.1 ± 4.1%、92.7 ± 5.5%、95.7 ± 4.0%、7.4 ± 5.7mm、0.9 ± 0.6mm 和 448 ± 40ms（在 GPU 上）。所提出算法与观察者间参考之间的差异分别为 DSC、精度、召回率、HD95 和 ASD 的平均 4.7%、1.2%、7.9%、3.2mm 和 0.6mm。