Wu Zhe, Deng Lihua, Wu Wanyang, Zeng Bin, Xu Cheng, Liu Li, Liu Mujun, Wu Yi
Department of Digital Medicine, School of Biomedical Engineering and Medical Imaging, Army Medical University (Third Military Medical University), Chongqing, China.
Yu-Yue Pathology Research Center, Jinfeng Laboratory, Chongqing, China.
Med Phys. 2025 May;52(5):2887-2897. doi: 10.1002/mp.17791. Epub 2025 Apr 1.
Sarcopenia is associated with decreased survival in cervical cancer patients treated with radiotherapy. Cone-beam computed tomography (CBCT) was widely used in image-guided radiotherapy. Sarcopenia is assessed by the skeletal muscle index (SMI) of third lumbar vertebra (L3). Whereas, L3 is usually not included on the cervical cancer radiotherapy CBCT images.
We aimed to explore the usefulness of CBCT for evaluating SMI and deep learning (DL)-based automatic segmentation and sarcopenia diagnosis for cervical cancer radiotherapy patients. We evaluated the SMI through fifth lumbar vertebra (L5).
First, L3, L5 skeletal muscle area (SMA) were measured on CT and CBCT. The agreement of L5 skeletal muscle segmentation on CBCT was evaluated using the intraclass correlation coefficient (ICC). The relationships between L5-SMI and L3-SMI, L5-SMI were established and assessed by Pearson analysis, Bland-Altman plots. Second, the consequent CBCT images of 248 cervical cancer radiotherapy patients with whole L5 were collected as DL-based automatic segmentation. An independent external validation dataset was used. We proposed an end-to-end anatomical distance-guided dual branch feature fusion network to segment L5 skeletal muscle on CBCT images. The automatic segmentation results were used for sarcopenia diagnosis evaluation.
The ICC values were greater than 0.95. The Pearson correlation coefficients (PCC) between L5-SMI and L3-SMI is 0.894. The PCC between L5-SMI and L5-SMI is 0.917. The L3-SMI could be estimated through L5-SMI by a linear regression equation. The adjusted R values were greater than 0.7. The dice similarity coefficient of automatic segmentation is 87.09%. Our proposed DL network predicted sarcopenia with 84.38% accuracy and 85.71% F1-score. In external validation dataset, the sarcopenia diagnosis accuracy and F1-score are 80% and 82.61%, respectively.
The SMI quantitative measurement using CBCT for cervical cancer patients is feasible. And the DL network has the potential to assist in the sarcopenia diagnosis using CBCT images.
在接受放疗的宫颈癌患者中，肌肉减少症与生存率降低有关。锥形束计算机断层扫描（CBCT）广泛应用于图像引导放疗。肌肉减少症通过第三腰椎（L3）的骨骼肌指数（SMI）进行评估。然而，L3通常不包含在宫颈癌放疗CBCT图像中。
我们旨在探讨CBCT在评估宫颈癌放疗患者SMI以及基于深度学习（DL）的自动分割和肌肉减少症诊断方面的实用性。我们通过第五腰椎（L5）评估SMI。
首先，在CT和CBCT上测量L3、L5的骨骼肌面积（SMA）。使用组内相关系数（ICC）评估CBCT上L5骨骼肌分割的一致性。通过Pearson分析、Bland-Altman图建立并评估L5-SMI与L3-SMI、L5-SMI之间的关系。其次，收集248例有完整L5的宫颈癌放疗患者的后续CBCT图像作为基于DL的自动分割数据。使用独立的外部验证数据集。我们提出了一种端到端的解剖距离引导双分支特征融合网络，用于在CBCT图像上分割L5骨骼肌。自动分割结果用于肌肉减少症诊断评估。
ICC值大于0.95。L5-SMI与L3-SMI之间的Pearson相关系数（PCC）为0.894。L5-SMI与L5-SMI之间的PCC为0.917。L3-SMI可通过线性回归方程由L5-SMI估计。调整后的R值大于0.7。自动分割的骰子相似系数为87.09%。我们提出的DL网络预测肌肉减少症的准确率为84.38%，F1分数为85.71%。在外部验证数据集中，肌肉减少症诊断的准确率和F1分数分别为80%和82.61%。
使用CBCT对宫颈癌患者进行SMI定量测量是可行的。并且DL网络有潜力辅助使用CBCT图像进行肌肉减少症诊断。
